diff options
| author | Luke Chen <luke.chen@mongodb.com> | 2022-01-11 12:07:30 +1100 |
|---|---|---|
| committer | Evergreen Agent <no-reply@evergreen.mongodb.com> | 2022-01-11 01:44:40 +0000 |
| commit | eb546401b77e41540281bcbbf972f7b17cd18c9b (patch) | |
| tree | 7cb8671d3dd729b70f28c77bf086ab896591fe77 | |
| parent | 5cbefbbd5ee7798c429198a689821b5f6a55bdbe (diff) | |
| download | mongo-eb546401b77e41540281bcbbf972f7b17cd18c9b.tar.gz | |
Import wiredtiger: b4eabd7093752f76dafb2cbee9f3ad03da56cbb5 from branch mongodb-5.2
ref: 265e20d6a6..b4eabd7093
for: 5.2.0-rc5
WT-8473 Power8 vector intrinsic CRC32 implementation
12 files changed, 1974 insertions, 1713 deletions
diff --git a/src/third_party/wiredtiger/cmake/configs/ppc64le/linux/config.cmake b/src/third_party/wiredtiger/cmake/configs/ppc64le/linux/config.cmake index 4d1821c9e18..45d7e9c9c3e 100644 --- a/src/third_party/wiredtiger/cmake/configs/ppc64le/linux/config.cmake +++ b/src/third_party/wiredtiger/cmake/configs/ppc64le/linux/config.cmake @@ -17,11 +17,3 @@ set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -D_GNU_SOURCE" CACHE STRING "" FORCE) # Linux requires buffers aligned to 4KB boundaries for O_DIRECT to work. set(WT_BUFFER_ALIGNMENT_DEFAULT "4096" CACHE STRING "") - -# Allow assembler to detect '.sx' file extensions. -list(APPEND CMAKE_ASM_SOURCE_FILE_EXTENSION "sx") - -# Our ASM-based checksum utility 'crc32.sx' triggers unused-macros diagnostic errors -# when compiling. To avoid editing the original source, override the usage '-Wunused-macros' -# for this specific file. -set_source_files_properties(src/checksum/power8/crc32.sx PROPERTIES COMPILE_FLAGS -Wno-unused-macros) diff --git a/src/third_party/wiredtiger/dist/filelist b/src/third_party/wiredtiger/dist/filelist index fe205cf10f3..1ca6bf4f32b 100644 --- a/src/third_party/wiredtiger/dist/filelist +++ b/src/third_party/wiredtiger/dist/filelist @@ -48,8 +48,8 @@ src/btree/row_key.c src/btree/row_modify.c src/btree/row_srch.c src/checksum/arm64/crc32-arm64.c ARM64_HOST -src/checksum/power8/crc32.sx POWERPC_HOST src/checksum/power8/crc32_wrapper.c POWERPC_HOST +src/checksum/power8/vec_crc32.c POWERPC_HOST src/checksum/riscv64/crc32-riscv64.c RISCV64_HOST src/checksum/software/checksum.c src/checksum/x86/crc32-x86-alt.c X86_HOST diff --git a/src/third_party/wiredtiger/dist/s_funcs.list b/src/third_party/wiredtiger/dist/s_funcs.list index 4f3d2a2ca87..a5f61123e88 100644 --- a/src/third_party/wiredtiger/dist/s_funcs.list +++ b/src/third_party/wiredtiger/dist/s_funcs.list @@ -1,6 +1,4 @@ # List of functions that aren't found by s_funcs, but that's OK. -FUNC_END -FUNC_START WT_CRC32_ENTRY WT_CURDUMP_PASS __bit_ffs diff --git a/src/third_party/wiredtiger/dist/s_string.ok b/src/third_party/wiredtiger/dist/s_string.ok index e10b2be439e..c40fe06f231 100644 --- a/src/third_party/wiredtiger/dist/s_string.ok +++ b/src/third_party/wiredtiger/dist/s_string.ok @@ -21,6 +21,7 @@ Ailamaki Alakuijala Alexandrescu's Alloc +Alves Async AsyncOp Athanassoulis @@ -122,12 +123,14 @@ EACCES EAGAIN EB EBUSY +EDC EEXIST EINTR EINVAL EMSG EMail ENCRYPTOR +ENDIAN ENOENT ENOMEM ENOTSUP @@ -176,6 +179,7 @@ Fsync Fuerst GBR GCC +GF GIDs GLIBC Gcc @@ -212,6 +216,7 @@ INMEM INPROGRESS INSN INTL +INTRINSICS INULL INUSE ISA @@ -301,6 +306,7 @@ NOLL NOLOCK NONINFRINGEMENT NOOP +NOP NOTFOUND NOTREACHED NOVALUE @@ -377,6 +383,7 @@ Redistributions Refactor Resize RocksDB +Rogerio Runtime SIMD SLIST @@ -869,6 +876,7 @@ fnv foc fopen formatmessage +foward fp fprintf fread @@ -938,6 +946,7 @@ ibackup icount idlems idx +ie ifdef ifdef's iflag @@ -978,6 +987,7 @@ intpack intptr intr intrin +intrinsics inuse io ip @@ -1007,6 +1017,7 @@ iters jjj jprx json +kB kb kbits keycmp @@ -1273,6 +1284,7 @@ pvA pwrite py qdown +qn qqq qrrSS qsort @@ -1537,6 +1549,8 @@ valuev vanishingly variable's variadic +vdata +vec vectorized versa vfprintf @@ -1544,6 +1558,7 @@ vh vm vpack vpmsum +vpmsumd vprintf vrfy vsize @@ -1584,6 +1599,7 @@ xF xdeadbeef xff xfff +xxpermdi xxxx xxxxx xxxxxx diff --git a/src/third_party/wiredtiger/import.data b/src/third_party/wiredtiger/import.data index 039c0c3f1fa..af0f846eea6 100644 --- a/src/third_party/wiredtiger/import.data +++ b/src/third_party/wiredtiger/import.data @@ -2,5 +2,5 @@ "vendor": "wiredtiger", "github": "wiredtiger/wiredtiger.git", "branch": "mongodb-5.2", - "commit": "265e20d6a6d8173a54b1ada48308dd80e290bc1a" + "commit": "b4eabd7093752f76dafb2cbee9f3ad03da56cbb5" } diff --git a/src/third_party/wiredtiger/src/checksum/power8/README.md b/src/third_party/wiredtiger/src/checksum/power8/README.md index 579d841a02c..7a0122ad801 100644 --- a/src/third_party/wiredtiger/src/checksum/power8/README.md +++ b/src/third_party/wiredtiger/src/checksum/power8/README.md @@ -34,18 +34,53 @@ to mitigate any I/O induced variability. Quick start ----------- +There's two different versions of crc32. They are, basically, the same +algorithm. The only difference is that one is implemented in pure assembly +(crc32.S) and the other in C using gcc (power8) vector intrinsics and +builtins (vec_crc32.c) to make the compiler generate the asm instructions +instead. + - Modify CRC and OPTIONS in the Makefile. There are examples for the two most common crc32s. - Type make to create the constants (crc32_constants.h) -- Import the code into your application (crc32.sx crc32_wrapper.c - crc32_constants.h ppc-opcode.h) and call the CRC: +**If you will use the pure asm version** + +- Import the code into your application (crc32.S crc32_wrapper.c + crc32_constants.h ppc-opcode.h) + +**If you will use the C version** + +- Import the code into your application (vec_crc32.c crc32_constants.h) + +- Call the CRC: + ``` unsigned int crc32_vpmsum(unsigned int crc, unsigned char *p, unsigned long len); ``` +Advanced Usage +-------------- + +Occasionally you may have a number of CRC32 polynomial implementations. + +To do this you'll need to compile the C or assembler implementation with a +different constants header file and change the function names to avoid linker +conflicts. + +To facilitate this optional defines can be introduced: + +- CRC32_CONSTANTS_HEADER to be set to the *quoted* header filename. + +- CRC32_FUNCTION to be set to the crc32 function name (instead of crc32_vpmsum) + +- CRC32_FUNCTION_ASM (asm version only) to be set to the assember function name used +by crc32_wrapper.c (defaults to __crc32_vpmsum). + +An example of this is with crc32_two_implementations as found in the Makefile. + CRC background -------------- @@ -201,8 +236,39 @@ Examples - final_fold2: A second method of reduction +Run time detection +------------------ + +The kernel sets the PPC_FEATURE2_VEC_CRYPTO bit in the HWCAP2 field +when the vpmsum instructions are available. An example of run time +detection: + +``` +#include <sys/auxv.h> + +#ifndef PPC_FEATURE2_VEC_CRYPTO +#define PPC_FEATURE2_VEC_CRYPTO 0x02000000 +#endif + +#ifndef AT_HWCAP2 +#define AT_HWCAP2 26 +#endif + +... + + if (getauxval(AT_HWCAP2) & PPC_FEATURE2_VEC_CRYPTO) { + /* Use crc32-vpmsum optimised version */ + } else { + /* fall back to non accelerated version */ + } +``` + Acknowledgements ---------------- Thanks to Michael Gschwind, Jeff Derby, Lorena Pesantez and Stewart Smith for their ideas and assistance. + +Thanks Rogerio Alves for writing the C implementation. + +Thanks Daniel Black for cleanup and testing. diff --git a/src/third_party/wiredtiger/src/checksum/power8/clang_workaround.h b/src/third_party/wiredtiger/src/checksum/power8/clang_workaround.h new file mode 100644 index 00000000000..aa792012c26 --- /dev/null +++ b/src/third_party/wiredtiger/src/checksum/power8/clang_workaround.h @@ -0,0 +1,89 @@ +#ifndef CLANG_WORKAROUND_H +#define CLANG_WORKAROUND_H + +/* + * These stubs fix clang incompatibilities with GCC builtins. + */ + +#ifndef __builtin_crypto_vpmsumw +#define __builtin_crypto_vpmsumw __builtin_crypto_vpmsumb +#endif +#ifndef __builtin_crypto_vpmsumd +#define __builtin_crypto_vpmsumd __builtin_crypto_vpmsumb +#endif + +static inline __vector unsigned long long __attribute__((overloadable)) +vec_ld(int __a, const __vector unsigned long long *__b) +{ + return (__vector unsigned long long)__builtin_altivec_lvx(__a, __b); +} + +/* + * GCC __builtin_pack_vector_int128 returns a vector __int128_t but Clang does not recognize this + * type. On GCC this builtin is translated to a xxpermdi instruction that only moves the registers + * __a, __b instead generates a load. + * + * Clang has vec_xxpermdi intrinsics. It was implemented in 4.0.0. + */ +static inline __vector unsigned long long +__builtin_pack_vector(unsigned long __a, unsigned long __b) +{ +#if defined(__BIG_ENDIAN__) + __vector unsigned long long __v = {__a, __b}; +#else + __vector unsigned long long __v = {__b, __a}; +#endif + return __v; +} + +/* + * Clang 7 changed the behavior of vec_xxpermdi in order to provide the same behavior of GCC. That + * means code adapted to Clang >= 7 does not work on Clang <= 6. So, fallback to + * __builtin_unpack_vector() on Clang <= 6. + */ +#if !defined vec_xxpermdi || __clang_major__ <= 6 + +static inline unsigned long +__builtin_unpack_vector(__vector unsigned long long __v, int __o) +{ + return __v[__o]; +} + +#if defined(__BIG_ENDIAN__) +#define __builtin_unpack_vector_0(a) __builtin_unpack_vector((a), 0) +#ifndef REFLECT +#define __builtin_unpack_vector_1(a) __builtin_unpack_vector((a), 1) +#endif +#else +#define __builtin_unpack_vector_0(a) __builtin_unpack_vector((a), 1) +#ifndef REFLECT +#define __builtin_unpack_vector_1(a) __builtin_unpack_vector((a), 0) +#endif +#endif + +#else + +static inline unsigned long +__builtin_unpack_vector_0(__vector unsigned long long __v) +{ +#if defined(__BIG_ENDIAN__) + return vec_xxpermdi(__v, __v, 0x0)[0]; +#else + return vec_xxpermdi(__v, __v, 0x3)[0]; +#endif +} + +#ifndef REFLECT +static inline unsigned long +__builtin_unpack_vector_1(__vector unsigned long long __v) +{ +#if defined(__BIG_ENDIAN__) + return vec_xxpermdi(__v, __v, 0x3)[0]; +#else + return vec_xxpermdi(__v, __v, 0x0)[0]; +#endif +} +#endif +#endif /* vec_xxpermdi */ + +#endif diff --git a/src/third_party/wiredtiger/src/checksum/power8/crc32.sx b/src/third_party/wiredtiger/src/checksum/power8/crc32.sx deleted file mode 100644 index 3eca99bdc53..00000000000 --- a/src/third_party/wiredtiger/src/checksum/power8/crc32.sx +++ /dev/null @@ -1,782 +0,0 @@ -#include <wiredtiger_config.h> -#if defined(__powerpc64__) && !defined(HAVE_NO_CRC32_HARDWARE) - -/* - * Calculate the checksum of data that is 16 byte aligned and a multiple of - * 16 bytes. - * - * The first step is to reduce it to 1024 bits. We do this in 8 parallel - * chunks in order to mask the latency of the vpmsum instructions. If we - * have more than 32 kB of data to checksum we repeat this step multiple - * times, passing in the previous 1024 bits. - * - * The next step is to reduce the 1024 bits to 64 bits. This step adds - * 32 bits of 0s to the end - this matches what a CRC does. We just - * calculate constants that land the data in this 32 bits. - * - * We then use fixed point Barrett reduction to compute a mod n over GF(2) - * for n = CRC using POWER8 instructions. We use x = 32. - * - * http://en.wikipedia.org/wiki/Barrett_reduction - * - * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ -#include <ppc-asm.h> -#include "ppc-opcode.h" - -#undef toc - -#ifndef r1 -#define r1 1 -#endif - -#ifndef r2 -#define r2 2 -#endif - - .section .rodata -.balign 16 - -.byteswap_constant: - /* byte reverse permute constant */ - .octa 0x0F0E0D0C0B0A09080706050403020100 - -#define __ASSEMBLY__ -#include "crc32_constants.h" - - .text - -#if defined(__BIG_ENDIAN__) && defined(REFLECT) -#define BYTESWAP_DATA -#elif defined(__LITTLE_ENDIAN__) && !defined(REFLECT) -#define BYTESWAP_DATA -#else -#undef BYTESWAP_DATA -#endif - -#define off16 r25 -#define off32 r26 -#define off48 r27 -#define off64 r28 -#define off80 r29 -#define off96 r30 -#define off112 r31 - -#define const1 v24 -#define const2 v25 - -#define byteswap v26 -#define mask_32bit v27 -#define mask_64bit v28 -#define zeroes v29 - -#ifdef BYTESWAP_DATA -#define VPERM(A, B, C, D) vperm A, B, C, D -#else -#define VPERM(A, B, C, D) -#endif - -/* unsigned int __crc32_vpmsum(unsigned int crc, void *p, unsigned long len) */ -FUNC_START(__crc32_vpmsum) - std r31,-8(r1) - std r30,-16(r1) - std r29,-24(r1) - std r28,-32(r1) - std r27,-40(r1) - std r26,-48(r1) - std r25,-56(r1) - - li off16,16 - li off32,32 - li off48,48 - li off64,64 - li off80,80 - li off96,96 - li off112,112 - li r0,0 - - /* Enough room for saving 10 non volatile VMX registers */ - subi r6,r1,56+10*16 - subi r7,r1,56+2*16 - - stvx v20,0,r6 - stvx v21,off16,r6 - stvx v22,off32,r6 - stvx v23,off48,r6 - stvx v24,off64,r6 - stvx v25,off80,r6 - stvx v26,off96,r6 - stvx v27,off112,r6 - stvx v28,0,r7 - stvx v29,off16,r7 - - mr r10,r3 - - vxor zeroes,zeroes,zeroes - vspltisw v0,-1 - - vsldoi mask_32bit,zeroes,v0,4 - vsldoi mask_64bit,zeroes,v0,8 - - /* Get the initial value into v8 */ - vxor v8,v8,v8 - MTVRD(v8, r3) -#ifdef REFLECT - vsldoi v8,zeroes,v8,8 /* shift into bottom 32 bits */ -#else - vsldoi v8,v8,zeroes,4 /* shift into top 32 bits */ -#endif - -#ifdef BYTESWAP_DATA - addis r3,r2,.byteswap_constant@toc@ha - addi r3,r3,.byteswap_constant@toc@l - - lvx byteswap,0,r3 - addi r3,r3,16 -#endif - - cmpdi r5,256 - blt .Lshort - - rldicr r6,r5,0,56 - - /* Checksum in blocks of MAX_SIZE */ -1: lis r7,MAX_SIZE@h - ori r7,r7,MAX_SIZE@l - mr r9,r7 - cmpd r6,r7 - bgt 2f - mr r7,r6 -2: subf r6,r7,r6 - - /* our main loop does 128 bytes at a time */ - srdi r7,r7,7 - - /* - * Work out the offset into the constants table to start at. Each - * constant is 16 bytes, and it is used against 128 bytes of input - * data - 128 / 16 = 8 - */ - sldi r8,r7,4 - srdi r9,r9,3 - subf r8,r8,r9 - - /* We reduce our final 128 bytes in a separate step */ - addi r7,r7,-1 - mtctr r7 - - addis r3,r2,.constants@toc@ha - addi r3,r3,.constants@toc@l - - /* Find the start of our constants */ - add r3,r3,r8 - - /* zero v0-v7 which will contain our checksums */ - vxor v0,v0,v0 - vxor v1,v1,v1 - vxor v2,v2,v2 - vxor v3,v3,v3 - vxor v4,v4,v4 - vxor v5,v5,v5 - vxor v6,v6,v6 - vxor v7,v7,v7 - - lvx const1,0,r3 - - /* - * If we are looping back to consume more data we use the values - * already in v16-v23. - */ - cmpdi r0,1 - beq 2f - - /* First warm up pass */ - lvx v16,0,r4 - lvx v17,off16,r4 - VPERM(v16,v16,v16,byteswap) - VPERM(v17,v17,v17,byteswap) - lvx v18,off32,r4 - lvx v19,off48,r4 - VPERM(v18,v18,v18,byteswap) - VPERM(v19,v19,v19,byteswap) - lvx v20,off64,r4 - lvx v21,off80,r4 - VPERM(v20,v20,v20,byteswap) - VPERM(v21,v21,v21,byteswap) - lvx v22,off96,r4 - lvx v23,off112,r4 - VPERM(v22,v22,v22,byteswap) - VPERM(v23,v23,v23,byteswap) - addi r4,r4,8*16 - - /* xor in initial value */ - vxor v16,v16,v8 - -2: bdz .Lfirst_warm_up_done - - addi r3,r3,16 - lvx const2,0,r3 - - /* Second warm up pass */ - VPMSUMD(v8,v16,const1) - lvx v16,0,r4 - VPERM(v16,v16,v16,byteswap) - ori r2,r2,0 - - VPMSUMD(v9,v17,const1) - lvx v17,off16,r4 - VPERM(v17,v17,v17,byteswap) - ori r2,r2,0 - - VPMSUMD(v10,v18,const1) - lvx v18,off32,r4 - VPERM(v18,v18,v18,byteswap) - ori r2,r2,0 - - VPMSUMD(v11,v19,const1) - lvx v19,off48,r4 - VPERM(v19,v19,v19,byteswap) - ori r2,r2,0 - - VPMSUMD(v12,v20,const1) - lvx v20,off64,r4 - VPERM(v20,v20,v20,byteswap) - ori r2,r2,0 - - VPMSUMD(v13,v21,const1) - lvx v21,off80,r4 - VPERM(v21,v21,v21,byteswap) - ori r2,r2,0 - - VPMSUMD(v14,v22,const1) - lvx v22,off96,r4 - VPERM(v22,v22,v22,byteswap) - ori r2,r2,0 - - VPMSUMD(v15,v23,const1) - lvx v23,off112,r4 - VPERM(v23,v23,v23,byteswap) - - addi r4,r4,8*16 - - bdz .Lfirst_cool_down - - /* - * main loop. We modulo schedule it such that it takes three iterations - * to complete - first iteration load, second iteration vpmsum, third - * iteration xor. - */ - .balign 16 -4: lvx const1,0,r3 - addi r3,r3,16 - ori r2,r2,0 - - vxor v0,v0,v8 - VPMSUMD(v8,v16,const2) - lvx v16,0,r4 - VPERM(v16,v16,v16,byteswap) - ori r2,r2,0 - - vxor v1,v1,v9 - VPMSUMD(v9,v17,const2) - lvx v17,off16,r4 - VPERM(v17,v17,v17,byteswap) - ori r2,r2,0 - - vxor v2,v2,v10 - VPMSUMD(v10,v18,const2) - lvx v18,off32,r4 - VPERM(v18,v18,v18,byteswap) - ori r2,r2,0 - - vxor v3,v3,v11 - VPMSUMD(v11,v19,const2) - lvx v19,off48,r4 - VPERM(v19,v19,v19,byteswap) - lvx const2,0,r3 - ori r2,r2,0 - - vxor v4,v4,v12 - VPMSUMD(v12,v20,const1) - lvx v20,off64,r4 - VPERM(v20,v20,v20,byteswap) - ori r2,r2,0 - - vxor v5,v5,v13 - VPMSUMD(v13,v21,const1) - lvx v21,off80,r4 - VPERM(v21,v21,v21,byteswap) - ori r2,r2,0 - - vxor v6,v6,v14 - VPMSUMD(v14,v22,const1) - lvx v22,off96,r4 - VPERM(v22,v22,v22,byteswap) - ori r2,r2,0 - - vxor v7,v7,v15 - VPMSUMD(v15,v23,const1) - lvx v23,off112,r4 - VPERM(v23,v23,v23,byteswap) - - addi r4,r4,8*16 - - bdnz 4b - -.Lfirst_cool_down: - /* First cool down pass */ - lvx const1,0,r3 - addi r3,r3,16 - - vxor v0,v0,v8 - VPMSUMD(v8,v16,const1) - ori r2,r2,0 - - vxor v1,v1,v9 - VPMSUMD(v9,v17,const1) - ori r2,r2,0 - - vxor v2,v2,v10 - VPMSUMD(v10,v18,const1) - ori r2,r2,0 - - vxor v3,v3,v11 - VPMSUMD(v11,v19,const1) - ori r2,r2,0 - - vxor v4,v4,v12 - VPMSUMD(v12,v20,const1) - ori r2,r2,0 - - vxor v5,v5,v13 - VPMSUMD(v13,v21,const1) - ori r2,r2,0 - - vxor v6,v6,v14 - VPMSUMD(v14,v22,const1) - ori r2,r2,0 - - vxor v7,v7,v15 - VPMSUMD(v15,v23,const1) - ori r2,r2,0 - -.Lsecond_cool_down: - /* Second cool down pass */ - vxor v0,v0,v8 - vxor v1,v1,v9 - vxor v2,v2,v10 - vxor v3,v3,v11 - vxor v4,v4,v12 - vxor v5,v5,v13 - vxor v6,v6,v14 - vxor v7,v7,v15 - -#ifdef REFLECT - /* - * vpmsumd produces a 96 bit result in the least significant bits - * of the register. Since we are bit reflected we have to shift it - * left 32 bits so it occupies the least significant bits in the - * bit reflected domain. - */ - vsldoi v0,v0,zeroes,4 - vsldoi v1,v1,zeroes,4 - vsldoi v2,v2,zeroes,4 - vsldoi v3,v3,zeroes,4 - vsldoi v4,v4,zeroes,4 - vsldoi v5,v5,zeroes,4 - vsldoi v6,v6,zeroes,4 - vsldoi v7,v7,zeroes,4 -#endif - - /* xor with last 1024 bits */ - lvx v8,0,r4 - lvx v9,off16,r4 - VPERM(v8,v8,v8,byteswap) - VPERM(v9,v9,v9,byteswap) - lvx v10,off32,r4 - lvx v11,off48,r4 - VPERM(v10,v10,v10,byteswap) - VPERM(v11,v11,v11,byteswap) - lvx v12,off64,r4 - lvx v13,off80,r4 - VPERM(v12,v12,v12,byteswap) - VPERM(v13,v13,v13,byteswap) - lvx v14,off96,r4 - lvx v15,off112,r4 - VPERM(v14,v14,v14,byteswap) - VPERM(v15,v15,v15,byteswap) - - addi r4,r4,8*16 - - vxor v16,v0,v8 - vxor v17,v1,v9 - vxor v18,v2,v10 - vxor v19,v3,v11 - vxor v20,v4,v12 - vxor v21,v5,v13 - vxor v22,v6,v14 - vxor v23,v7,v15 - - li r0,1 - cmpdi r6,0 - addi r6,r6,128 - bne 1b - - /* Work out how many bytes we have left */ - andi. r5,r5,127 - - /* Calculate where in the constant table we need to start */ - subfic r6,r5,128 - add r3,r3,r6 - - /* How many 16 byte chunks are in the tail */ - srdi r7,r5,4 - mtctr r7 - - /* - * Reduce the previously calculated 1024 bits to 64 bits, shifting - * 32 bits to include the trailing 32 bits of zeros - */ - lvx v0,0,r3 - lvx v1,off16,r3 - lvx v2,off32,r3 - lvx v3,off48,r3 - lvx v4,off64,r3 - lvx v5,off80,r3 - lvx v6,off96,r3 - lvx v7,off112,r3 - addi r3,r3,8*16 - - VPMSUMW(v0,v16,v0) - VPMSUMW(v1,v17,v1) - VPMSUMW(v2,v18,v2) - VPMSUMW(v3,v19,v3) - VPMSUMW(v4,v20,v4) - VPMSUMW(v5,v21,v5) - VPMSUMW(v6,v22,v6) - VPMSUMW(v7,v23,v7) - - /* Now reduce the tail (0 - 112 bytes) */ - cmpdi r7,0 - beq 1f - - lvx v16,0,r4 - lvx v17,0,r3 - VPERM(v16,v16,v16,byteswap) - VPMSUMW(v16,v16,v17) - vxor v0,v0,v16 - bdz 1f - - lvx v16,off16,r4 - lvx v17,off16,r3 - VPERM(v16,v16,v16,byteswap) - VPMSUMW(v16,v16,v17) - vxor v0,v0,v16 - bdz 1f - - lvx v16,off32,r4 - lvx v17,off32,r3 - VPERM(v16,v16,v16,byteswap) - VPMSUMW(v16,v16,v17) - vxor v0,v0,v16 - bdz 1f - - lvx v16,off48,r4 - lvx v17,off48,r3 - VPERM(v16,v16,v16,byteswap) - VPMSUMW(v16,v16,v17) - vxor v0,v0,v16 - bdz 1f - - lvx v16,off64,r4 - lvx v17,off64,r3 - VPERM(v16,v16,v16,byteswap) - VPMSUMW(v16,v16,v17) - vxor v0,v0,v16 - bdz 1f - - lvx v16,off80,r4 - lvx v17,off80,r3 - VPERM(v16,v16,v16,byteswap) - VPMSUMW(v16,v16,v17) - vxor v0,v0,v16 - bdz 1f - - lvx v16,off96,r4 - lvx v17,off96,r3 - VPERM(v16,v16,v16,byteswap) - VPMSUMW(v16,v16,v17) - vxor v0,v0,v16 - - /* Now xor all the parallel chunks together */ -1: vxor v0,v0,v1 - vxor v2,v2,v3 - vxor v4,v4,v5 - vxor v6,v6,v7 - - vxor v0,v0,v2 - vxor v4,v4,v6 - - vxor v0,v0,v4 - -.Lbarrett_reduction: - /* Barrett constants */ - addis r3,r2,.barrett_constants@toc@ha - addi r3,r3,.barrett_constants@toc@l - - lvx const1,0,r3 - lvx const2,off16,r3 - - vsldoi v1,v0,v0,8 - vxor v0,v0,v1 /* xor two 64 bit results together */ - -#ifdef REFLECT - /* shift left one bit */ - vspltisb v1,1 - vsl v0,v0,v1 -#endif - - vand v0,v0,mask_64bit - -#ifndef REFLECT - /* - * Now for the Barrett reduction algorithm. The idea is to calculate q, - * the multiple of our polynomial that we need to subtract. By - * doing the computation 2x bits higher (ie 64 bits) and shifting the - * result back down 2x bits, we round down to the nearest multiple. - */ - VPMSUMD(v1,v0,const1) /* ma */ - vsldoi v1,zeroes,v1,8 /* q = floor(ma/(2^64)) */ - VPMSUMD(v1,v1,const2) /* qn */ - vxor v0,v0,v1 /* a - qn, subtraction is xor in GF(2) */ - - /* - * Get the result into r3. We need to shift it left 8 bytes: - * V0 [ 0 1 2 X ] - * V0 [ 0 X 2 3 ] - */ - vsldoi v0,v0,zeroes,8 /* shift result into top 64 bits */ -#else - /* - * The reflected version of Barrett reduction. Instead of bit - * reflecting our data (which is expensive to do), we bit reflect our - * constants and our algorithm, which means the intermediate data in - * our vector registers goes from 0-63 instead of 63-0. We can reflect - * the algorithm because we don't carry in mod 2 arithmetic. - */ - vand v1,v0,mask_32bit /* bottom 32 bits of a */ - VPMSUMD(v1,v1,const1) /* ma */ - vand v1,v1,mask_32bit /* bottom 32bits of ma */ - VPMSUMD(v1,v1,const2) /* qn */ - vxor v0,v0,v1 /* a - qn, subtraction is xor in GF(2) */ - - /* - * Since we are bit reflected, the result (ie the low 32 bits) is in - * the high 32 bits. We just need to shift it left 4 bytes - * V0 [ 0 1 X 3 ] - * V0 [ 0 X 2 3 ] - */ - vsldoi v0,v0,zeroes,4 /* shift result into top 64 bits of */ -#endif - - /* Get it into r3 */ - MFVRD(r3, v0) - -.Lout: - subi r6,r1,56+10*16 - subi r7,r1,56+2*16 - - lvx v20,0,r6 - lvx v21,off16,r6 - lvx v22,off32,r6 - lvx v23,off48,r6 - lvx v24,off64,r6 - lvx v25,off80,r6 - lvx v26,off96,r6 - lvx v27,off112,r6 - lvx v28,0,r7 - lvx v29,off16,r7 - - ld r31,-8(r1) - ld r30,-16(r1) - ld r29,-24(r1) - ld r28,-32(r1) - ld r27,-40(r1) - ld r26,-48(r1) - ld r25,-56(r1) - - blr - -.Lfirst_warm_up_done: - lvx const1,0,r3 - addi r3,r3,16 - - VPMSUMD(v8,v16,const1) - VPMSUMD(v9,v17,const1) - VPMSUMD(v10,v18,const1) - VPMSUMD(v11,v19,const1) - VPMSUMD(v12,v20,const1) - VPMSUMD(v13,v21,const1) - VPMSUMD(v14,v22,const1) - VPMSUMD(v15,v23,const1) - - b .Lsecond_cool_down - -.Lshort: - cmpdi r5,0 - beq .Lzero - - addis r3,r2,.short_constants@toc@ha - addi r3,r3,.short_constants@toc@l - - /* Calculate where in the constant table we need to start */ - subfic r6,r5,256 - add r3,r3,r6 - - /* How many 16 byte chunks? */ - srdi r7,r5,4 - mtctr r7 - - vxor v19,v19,v19 - vxor v20,v20,v20 - - lvx v0,0,r4 - lvx v16,0,r3 - VPERM(v0,v0,v16,byteswap) - vxor v0,v0,v8 /* xor in initial value */ - VPMSUMW(v0,v0,v16) - bdz .Lv0 - - lvx v1,off16,r4 - lvx v17,off16,r3 - VPERM(v1,v1,v17,byteswap) - VPMSUMW(v1,v1,v17) - bdz .Lv1 - - lvx v2,off32,r4 - lvx v16,off32,r3 - VPERM(v2,v2,v16,byteswap) - VPMSUMW(v2,v2,v16) - bdz .Lv2 - - lvx v3,off48,r4 - lvx v17,off48,r3 - VPERM(v3,v3,v17,byteswap) - VPMSUMW(v3,v3,v17) - bdz .Lv3 - - lvx v4,off64,r4 - lvx v16,off64,r3 - VPERM(v4,v4,v16,byteswap) - VPMSUMW(v4,v4,v16) - bdz .Lv4 - - lvx v5,off80,r4 - lvx v17,off80,r3 - VPERM(v5,v5,v17,byteswap) - VPMSUMW(v5,v5,v17) - bdz .Lv5 - - lvx v6,off96,r4 - lvx v16,off96,r3 - VPERM(v6,v6,v16,byteswap) - VPMSUMW(v6,v6,v16) - bdz .Lv6 - - lvx v7,off112,r4 - lvx v17,off112,r3 - VPERM(v7,v7,v17,byteswap) - VPMSUMW(v7,v7,v17) - bdz .Lv7 - - addi r3,r3,128 - addi r4,r4,128 - - lvx v8,0,r4 - lvx v16,0,r3 - VPERM(v8,v8,v16,byteswap) - VPMSUMW(v8,v8,v16) - bdz .Lv8 - - lvx v9,off16,r4 - lvx v17,off16,r3 - VPERM(v9,v9,v17,byteswap) - VPMSUMW(v9,v9,v17) - bdz .Lv9 - - lvx v10,off32,r4 - lvx v16,off32,r3 - VPERM(v10,v10,v16,byteswap) - VPMSUMW(v10,v10,v16) - bdz .Lv10 - - lvx v11,off48,r4 - lvx v17,off48,r3 - VPERM(v11,v11,v17,byteswap) - VPMSUMW(v11,v11,v17) - bdz .Lv11 - - lvx v12,off64,r4 - lvx v16,off64,r3 - VPERM(v12,v12,v16,byteswap) - VPMSUMW(v12,v12,v16) - bdz .Lv12 - - lvx v13,off80,r4 - lvx v17,off80,r3 - VPERM(v13,v13,v17,byteswap) - VPMSUMW(v13,v13,v17) - bdz .Lv13 - - lvx v14,off96,r4 - lvx v16,off96,r3 - VPERM(v14,v14,v16,byteswap) - VPMSUMW(v14,v14,v16) - bdz .Lv14 - - lvx v15,off112,r4 - lvx v17,off112,r3 - VPERM(v15,v15,v17,byteswap) - VPMSUMW(v15,v15,v17) - -.Lv15: vxor v19,v19,v15 -.Lv14: vxor v20,v20,v14 -.Lv13: vxor v19,v19,v13 -.Lv12: vxor v20,v20,v12 -.Lv11: vxor v19,v19,v11 -.Lv10: vxor v20,v20,v10 -.Lv9: vxor v19,v19,v9 -.Lv8: vxor v20,v20,v8 -.Lv7: vxor v19,v19,v7 -.Lv6: vxor v20,v20,v6 -.Lv5: vxor v19,v19,v5 -.Lv4: vxor v20,v20,v4 -.Lv3: vxor v19,v19,v3 -.Lv2: vxor v20,v20,v2 -.Lv1: vxor v19,v19,v1 -.Lv0: vxor v20,v20,v0 - - vxor v0,v19,v20 - - b .Lbarrett_reduction - -.Lzero: - mr r3,r10 - b .Lout - -FUNC_END(__crc32_vpmsum) -#endif - -/* Make sure the stack isn't executable with GCC (regardless of platform). */ -#ifdef __ELF__ -.section .note.GNU-stack,"",@progbits -#endif -/* - * DO NOT add an #endif after this line, this section must always be output - * and can never be #ifdef'd out as part of conditional compilation. - */ diff --git a/src/third_party/wiredtiger/src/checksum/power8/crc32_constants.h b/src/third_party/wiredtiger/src/checksum/power8/crc32_constants.h index bcdf3a8b8a3..c0b6e101a78 100644 --- a/src/third_party/wiredtiger/src/checksum/power8/crc32_constants.h +++ b/src/third_party/wiredtiger/src/checksum/power8/crc32_constants.h @@ -1,8 +1,19 @@ +/* +* +* THIS FILE IS GENERATED WITH +./crc32_constants -r -x -c 0x11EDC6F41 + +* This is from https://github.com/antonblanchard/crc32-vpmsum/ +* DO NOT MODIFY IT MANUALLY! +* +*/ + #define CRC 0x1edc6f41 #define CRC_XOR #define REFLECT +#define MAX_SIZE 32768 -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #ifdef CRC_TABLE static const unsigned int crc_table[] = { 0x00000000, @@ -263,832 +274,1122 @@ static const unsigned int crc_table[] = { 0xad7d5351, }; -#endif -#else -#define MAX_SIZE 32768 -.constants : - - /* Reduce 262144 kbits to 1024 bits */ - /* x^261120 mod p(x)` << 1, x^261184 mod p(x)` << 1 */ - .octa 0x00000000b6ca9e20000000009c37c408 - - /* x^260096 mod p(x)` << 1, x^260160 mod p(x)` << 1 */ - .octa 0x00000000350249a800000001b51df26c - - /* x^259072 mod p(x)` << 1, x^259136 mod p(x)` << 1 */ - .octa 0x00000001862dac54000000000724b9d0 - - /* x^258048 mod p(x)` << 1, x^258112 mod p(x)` << 1 */ - .octa 0x00000001d87fb48c00000001c00532fe - - /* x^257024 mod p(x)` << 1, x^257088 mod p(x)` << 1 */ - .octa 0x00000001f39b699e00000000f05a9362 - - /* x^256000 mod p(x)` << 1, x^256064 mod p(x)` << 1 */ - .octa 0x0000000101da11b400000001e1007970 - - /* x^254976 mod p(x)` << 1, x^255040 mod p(x)` << 1 */ - .octa 0x00000001cab571e000000000a57366ee - - /* x^253952 mod p(x)` << 1, x^254016 mod p(x)` << 1 */ - .octa 0x00000000c7020cfe0000000192011284 - - /* x^252928 mod p(x)` << 1, x^252992 mod p(x)` << 1 */ - .octa 0x00000000cdaed1ae0000000162716d9a - - /* x^251904 mod p(x)` << 1, x^251968 mod p(x)` << 1 */ - .octa 0x00000001e804effc00000000cd97ecde - - /* x^250880 mod p(x)` << 1, x^250944 mod p(x)` << 1 */ - .octa 0x0000000077c3ea3a0000000058812bc0 - - /* x^249856 mod p(x)` << 1, x^249920 mod p(x)` << 1 */ - .octa 0x0000000068df31b40000000088b8c12e - - /* x^248832 mod p(x)` << 1, x^248896 mod p(x)` << 1 */ - .octa 0x00000000b059b6c200000001230b234c - - /* x^247808 mod p(x)` << 1, x^247872 mod p(x)` << 1 */ - .octa 0x0000000145fb8ed800000001120b416e - - /* x^246784 mod p(x)` << 1, x^246848 mod p(x)` << 1 */ - .octa 0x00000000cbc0916800000001974aecb0 - - /* x^245760 mod p(x)` << 1, x^245824 mod p(x)` << 1 */ - .octa 0x000000005ceeedc2000000008ee3f226 - - /* x^244736 mod p(x)` << 1, x^244800 mod p(x)` << 1 */ - .octa 0x0000000047d74e8600000001089aba9a - - /* x^243712 mod p(x)` << 1, x^243776 mod p(x)` << 1 */ - .octa 0x00000001407e9e220000000065113872 - - /* x^242688 mod p(x)` << 1, x^242752 mod p(x)` << 1 */ - .octa 0x00000001da967bda000000005c07ec10 - - /* x^241664 mod p(x)` << 1, x^241728 mod p(x)` << 1 */ - .octa 0x000000006c8983680000000187590924 - - /* x^240640 mod p(x)` << 1, x^240704 mod p(x)` << 1 */ - .octa 0x00000000f2d14c9800000000e35da7c6 - - /* x^239616 mod p(x)` << 1, x^239680 mod p(x)` << 1 */ - .octa 0x00000001993c6ad4000000000415855a - - /* x^238592 mod p(x)` << 1, x^238656 mod p(x)` << 1 */ - .octa 0x000000014683d1ac0000000073617758 - - /* x^237568 mod p(x)` << 1, x^237632 mod p(x)` << 1 */ - .octa 0x00000001a7c93e6c0000000176021d28 - - /* x^236544 mod p(x)` << 1, x^236608 mod p(x)` << 1 */ - .octa 0x000000010211e90a00000001c358fd0a - - /* x^235520 mod p(x)` << 1, x^235584 mod p(x)` << 1 */ - .octa 0x000000001119403e00000001ff7a2c18 - - /* x^234496 mod p(x)` << 1, x^234560 mod p(x)` << 1 */ - .octa 0x000000001c3261aa00000000f2d9f7e4 - - /* x^233472 mod p(x)` << 1, x^233536 mod p(x)` << 1 */ - .octa 0x000000014e37a634000000016cf1f9c8 - - /* x^232448 mod p(x)` << 1, x^232512 mod p(x)` << 1 */ - .octa 0x0000000073786c0c000000010af9279a - - /* x^231424 mod p(x)` << 1, x^231488 mod p(x)` << 1 */ - .octa 0x000000011dc037f80000000004f101e8 - - /* x^230400 mod p(x)` << 1, x^230464 mod p(x)` << 1 */ - .octa 0x0000000031433dfc0000000070bcf184 - - /* x^229376 mod p(x)` << 1, x^229440 mod p(x)` << 1 */ - .octa 0x000000009cde8348000000000a8de642 - - /* x^228352 mod p(x)` << 1, x^228416 mod p(x)` << 1 */ - .octa 0x0000000038d3c2a60000000062ea130c - - /* x^227328 mod p(x)` << 1, x^227392 mod p(x)` << 1 */ - .octa 0x000000011b25f26000000001eb31cbb2 - - /* x^226304 mod p(x)` << 1, x^226368 mod p(x)` << 1 */ - .octa 0x000000001629e6f00000000170783448 - - /* x^225280 mod p(x)` << 1, x^225344 mod p(x)` << 1 */ - .octa 0x0000000160838b4c00000001a684b4c6 - - /* x^224256 mod p(x)` << 1, x^224320 mod p(x)` << 1 */ - .octa 0x000000007a44011c00000000253ca5b4 - - /* x^223232 mod p(x)` << 1, x^223296 mod p(x)` << 1 */ - .octa 0x00000000226f417a0000000057b4b1e2 - - /* x^222208 mod p(x)` << 1, x^222272 mod p(x)` << 1 */ - .octa 0x0000000045eb2eb400000000b6bd084c - - /* x^221184 mod p(x)` << 1, x^221248 mod p(x)` << 1 */ - .octa 0x000000014459d70c0000000123c2d592 - - /* x^220160 mod p(x)` << 1, x^220224 mod p(x)` << 1 */ - .octa 0x00000001d406ed8200000000159dafce - - /* x^219136 mod p(x)` << 1, x^219200 mod p(x)` << 1 */ - .octa 0x0000000160c8e1a80000000127e1a64e - - /* x^218112 mod p(x)` << 1, x^218176 mod p(x)` << 1 */ - .octa 0x0000000027ba80980000000056860754 - - /* x^217088 mod p(x)` << 1, x^217152 mod p(x)` << 1 */ - .octa 0x000000006d92d01800000001e661aae8 - - /* x^216064 mod p(x)` << 1, x^216128 mod p(x)` << 1 */ - .octa 0x000000012ed7e3f200000000f82c6166 - - /* x^215040 mod p(x)` << 1, x^215104 mod p(x)` << 1 */ - .octa 0x000000002dc8778800000000c4f9c7ae - - /* x^214016 mod p(x)` << 1, x^214080 mod p(x)` << 1 */ - .octa 0x0000000018240bb80000000074203d20 - - /* x^212992 mod p(x)` << 1, x^213056 mod p(x)` << 1 */ - .octa 0x000000001ad381580000000198173052 - - /* x^211968 mod p(x)` << 1, x^212032 mod p(x)` << 1 */ - .octa 0x00000001396b78f200000001ce8aba54 - - /* x^210944 mod p(x)` << 1, x^211008 mod p(x)` << 1 */ - .octa 0x000000011a68133400000001850d5d94 - - /* x^209920 mod p(x)` << 1, x^209984 mod p(x)` << 1 */ - .octa 0x000000012104732e00000001d609239c - - /* x^208896 mod p(x)` << 1, x^208960 mod p(x)` << 1 */ - .octa 0x00000000a140d90c000000001595f048 - - /* x^207872 mod p(x)` << 1, x^207936 mod p(x)` << 1 */ - .octa 0x00000001b7215eda0000000042ccee08 - - /* x^206848 mod p(x)` << 1, x^206912 mod p(x)` << 1 */ - .octa 0x00000001aaf1df3c000000010a389d74 - - /* x^205824 mod p(x)` << 1, x^205888 mod p(x)` << 1 */ - .octa 0x0000000029d15b8a000000012a840da6 - - /* x^204800 mod p(x)` << 1, x^204864 mod p(x)` << 1 */ - .octa 0x00000000f1a96922000000001d181c0c - - /* x^203776 mod p(x)` << 1, x^203840 mod p(x)` << 1 */ - .octa 0x00000001ac80d03c0000000068b7d1f6 - - /* x^202752 mod p(x)` << 1, x^202816 mod p(x)` << 1 */ - .octa 0x000000000f11d56a000000005b0f14fc - - /* x^201728 mod p(x)` << 1, x^201792 mod p(x)` << 1 */ - .octa 0x00000001f1c022a20000000179e9e730 - - /* x^200704 mod p(x)` << 1, x^200768 mod p(x)` << 1 */ - .octa 0x0000000173d00ae200000001ce1368d6 - - /* x^199680 mod p(x)` << 1, x^199744 mod p(x)` << 1 */ - .octa 0x00000001d4ffe4ac0000000112c3a84c - - /* x^198656 mod p(x)` << 1, x^198720 mod p(x)` << 1 */ - .octa 0x000000016edc5ae400000000de940fee - - /* x^197632 mod p(x)` << 1, x^197696 mod p(x)` << 1 */ - .octa 0x00000001f1a0214000000000fe896b7e - - /* x^196608 mod p(x)` << 1, x^196672 mod p(x)` << 1 */ - .octa 0x00000000ca0b28a000000001f797431c - - /* x^195584 mod p(x)` << 1, x^195648 mod p(x)` << 1 */ - .octa 0x00000001928e30a20000000053e989ba - - /* x^194560 mod p(x)` << 1, x^194624 mod p(x)` << 1 */ - .octa 0x0000000097b1b002000000003920cd16 - - /* x^193536 mod p(x)` << 1, x^193600 mod p(x)` << 1 */ - .octa 0x00000000b15bf90600000001e6f579b8 - - /* x^192512 mod p(x)` << 1, x^192576 mod p(x)` << 1 */ - .octa 0x00000000411c5d52000000007493cb0a - - /* x^191488 mod p(x)` << 1, x^191552 mod p(x)` << 1 */ - .octa 0x00000001c36f330000000001bdd376d8 - - /* x^190464 mod p(x)` << 1, x^190528 mod p(x)` << 1 */ - .octa 0x00000001119227e0000000016badfee6 - - /* x^189440 mod p(x)` << 1, x^189504 mod p(x)` << 1 */ - .octa 0x00000000114d47020000000071de5c58 - - /* x^188416 mod p(x)` << 1, x^188480 mod p(x)` << 1 */ - .octa 0x00000000458b5b9800000000453f317c - - /* x^187392 mod p(x)` << 1, x^187456 mod p(x)` << 1 */ - .octa 0x000000012e31fb8e0000000121675cce - - /* x^186368 mod p(x)` << 1, x^186432 mod p(x)` << 1 */ - .octa 0x000000005cf619d800000001f409ee92 - - /* x^185344 mod p(x)` << 1, x^185408 mod p(x)` << 1 */ - .octa 0x0000000063f4d8b200000000f36b9c88 - - /* x^184320 mod p(x)` << 1, x^184384 mod p(x)` << 1 */ - .octa 0x000000004138dc8a0000000036b398f4 - - /* x^183296 mod p(x)` << 1, x^183360 mod p(x)` << 1 */ - .octa 0x00000001d29ee8e000000001748f9adc - - /* x^182272 mod p(x)` << 1, x^182336 mod p(x)` << 1 */ - .octa 0x000000006a08ace800000001be94ec00 - - /* x^181248 mod p(x)` << 1, x^181312 mod p(x)` << 1 */ - .octa 0x0000000127d4201000000000b74370d6 - - /* x^180224 mod p(x)` << 1, x^180288 mod p(x)` << 1 */ - .octa 0x0000000019d76b6200000001174d0b98 - - /* x^179200 mod p(x)` << 1, x^179264 mod p(x)` << 1 */ - .octa 0x00000001b1471f6e00000000befc06a4 - - /* x^178176 mod p(x)` << 1, x^178240 mod p(x)` << 1 */ - .octa 0x00000001f64c19cc00000001ae125288 - - /* x^177152 mod p(x)` << 1, x^177216 mod p(x)` << 1 */ - .octa 0x00000000003c0ea00000000095c19b34 - - /* x^176128 mod p(x)` << 1, x^176192 mod p(x)` << 1 */ - .octa 0x000000014d73abf600000001a78496f2 - - /* x^175104 mod p(x)` << 1, x^175168 mod p(x)` << 1 */ - .octa 0x00000001620eb84400000001ac5390a0 - - /* x^174080 mod p(x)` << 1, x^174144 mod p(x)` << 1 */ - .octa 0x0000000147655048000000002a80ed6e - - /* x^173056 mod p(x)` << 1, x^173120 mod p(x)` << 1 */ - .octa 0x0000000067b5077e00000001fa9b0128 - - /* x^172032 mod p(x)` << 1, x^172096 mod p(x)` << 1 */ - .octa 0x0000000010ffe20600000001ea94929e - - /* x^171008 mod p(x)` << 1, x^171072 mod p(x)` << 1 */ - .octa 0x000000000fee8f1e0000000125f4305c - - /* x^169984 mod p(x)` << 1, x^170048 mod p(x)` << 1 */ - .octa 0x00000001da26fbae00000001471e2002 - - /* x^168960 mod p(x)` << 1, x^169024 mod p(x)` << 1 */ - .octa 0x00000001b3a8bd880000000132d2253a - - /* x^167936 mod p(x)` << 1, x^168000 mod p(x)` << 1 */ - .octa 0x00000000e8f3898e00000000f26b3592 - - /* x^166912 mod p(x)` << 1, x^166976 mod p(x)` << 1 */ - .octa 0x00000000b0d0d28c00000000bc8b67b0 - - /* x^165888 mod p(x)` << 1, x^165952 mod p(x)` << 1 */ - .octa 0x0000000030f2a798000000013a826ef2 - - /* x^164864 mod p(x)` << 1, x^164928 mod p(x)` << 1 */ - .octa 0x000000000fba10020000000081482c84 - - /* x^163840 mod p(x)` << 1, x^163904 mod p(x)` << 1 */ - .octa 0x00000000bdb9bd7200000000e77307c2 - - /* x^162816 mod p(x)` << 1, x^162880 mod p(x)` << 1 */ - .octa 0x0000000075d3bf5a00000000d4a07ec8 - - /* x^161792 mod p(x)` << 1, x^161856 mod p(x)` << 1 */ - .octa 0x00000000ef1f98a00000000017102100 - - /* x^160768 mod p(x)` << 1, x^160832 mod p(x)` << 1 */ - .octa 0x00000000689c760200000000db406486 - - /* x^159744 mod p(x)` << 1, x^159808 mod p(x)` << 1 */ - .octa 0x000000016d5fa5fe0000000192db7f88 - - /* x^158720 mod p(x)` << 1, x^158784 mod p(x)` << 1 */ - .octa 0x00000001d0d2b9ca000000018bf67b1e - - /* x^157696 mod p(x)` << 1, x^157760 mod p(x)` << 1 */ - .octa 0x0000000041e7b470000000007c09163e - - /* x^156672 mod p(x)` << 1, x^156736 mod p(x)` << 1 */ - .octa 0x00000001cbb6495e000000000adac060 - - /* x^155648 mod p(x)` << 1, x^155712 mod p(x)` << 1 */ - .octa 0x000000010052a0b000000000bd8316ae - - /* x^154624 mod p(x)` << 1, x^154688 mod p(x)` << 1 */ - .octa 0x00000001d8effb5c000000019f09ab54 - - /* x^153600 mod p(x)` << 1, x^153664 mod p(x)` << 1 */ - .octa 0x00000001d969853c0000000125155542 - - /* x^152576 mod p(x)` << 1, x^152640 mod p(x)` << 1 */ - .octa 0x00000000523ccce2000000018fdb5882 - - /* x^151552 mod p(x)` << 1, x^151616 mod p(x)` << 1 */ - .octa 0x000000001e2436bc00000000e794b3f4 - - /* x^150528 mod p(x)` << 1, x^150592 mod p(x)` << 1 */ - .octa 0x00000000ddd1c3a2000000016f9bb022 - - /* x^149504 mod p(x)` << 1, x^149568 mod p(x)` << 1 */ - .octa 0x0000000019fcfe3800000000290c9978 - - /* x^148480 mod p(x)` << 1, x^148544 mod p(x)` << 1 */ - .octa 0x00000001ce95db640000000083c0f350 - - /* x^147456 mod p(x)` << 1, x^147520 mod p(x)` << 1 */ - .octa 0x00000000af5828060000000173ea6628 - - /* x^146432 mod p(x)` << 1, x^146496 mod p(x)` << 1 */ - .octa 0x00000001006388f600000001c8b4e00a - - /* x^145408 mod p(x)` << 1, x^145472 mod p(x)` << 1 */ - .octa 0x0000000179eca00a00000000de95d6aa - - /* x^144384 mod p(x)` << 1, x^144448 mod p(x)` << 1 */ - .octa 0x0000000122410a6a000000010b7f7248 - - /* x^143360 mod p(x)` << 1, x^143424 mod p(x)` << 1 */ - .octa 0x000000004288e87c00000001326e3a06 - - /* x^142336 mod p(x)` << 1, x^142400 mod p(x)` << 1 */ - .octa 0x000000016c5490da00000000bb62c2e6 - - /* x^141312 mod p(x)` << 1, x^141376 mod p(x)` << 1 */ - .octa 0x00000000d1c71f6e0000000156a4b2c2 - - /* x^140288 mod p(x)` << 1, x^140352 mod p(x)` << 1 */ - .octa 0x00000001b4ce08a6000000011dfe763a - - /* x^139264 mod p(x)` << 1, x^139328 mod p(x)` << 1 */ - .octa 0x00000001466ba60c000000007bcca8e2 - - /* x^138240 mod p(x)` << 1, x^138304 mod p(x)` << 1 */ - .octa 0x00000001f6c488a40000000186118faa - - /* x^137216 mod p(x)` << 1, x^137280 mod p(x)` << 1 */ - .octa 0x000000013bfb06820000000111a65a88 - - /* x^136192 mod p(x)` << 1, x^136256 mod p(x)` << 1 */ - .octa 0x00000000690e9e54000000003565e1c4 - - /* x^135168 mod p(x)` << 1, x^135232 mod p(x)` << 1 */ - .octa 0x00000000281346b6000000012ed02a82 - - /* x^134144 mod p(x)` << 1, x^134208 mod p(x)` << 1 */ - .octa 0x000000015646402400000000c486ecfc - - /* x^133120 mod p(x)` << 1, x^133184 mod p(x)` << 1 */ - .octa 0x000000016063a8dc0000000001b951b2 - - /* x^132096 mod p(x)` << 1, x^132160 mod p(x)` << 1 */ - .octa 0x0000000116a663620000000048143916 - - /* x^131072 mod p(x)` << 1, x^131136 mod p(x)` << 1 */ - .octa 0x000000017e8aa4d200000001dc2ae124 - - /* x^130048 mod p(x)` << 1, x^130112 mod p(x)` << 1 */ - .octa 0x00000001728eb10c00000001416c58d6 - - /* x^129024 mod p(x)` << 1, x^129088 mod p(x)` << 1 */ - .octa 0x00000001b08fd7fa00000000a479744a - - /* x^128000 mod p(x)` << 1, x^128064 mod p(x)` << 1 */ - .octa 0x00000001092a16e80000000096ca3a26 - - /* x^126976 mod p(x)` << 1, x^127040 mod p(x)` << 1 */ - .octa 0x00000000a505637c00000000ff223d4e - - /* x^125952 mod p(x)` << 1, x^126016 mod p(x)` << 1 */ - .octa 0x00000000d94869b2000000010e84da42 - - /* x^124928 mod p(x)` << 1, x^124992 mod p(x)` << 1 */ - .octa 0x00000001c8b203ae00000001b61ba3d0 - - /* x^123904 mod p(x)` << 1, x^123968 mod p(x)` << 1 */ - .octa 0x000000005704aea000000000680f2de8 - - /* x^122880 mod p(x)` << 1, x^122944 mod p(x)` << 1 */ - .octa 0x000000012e295fa2000000008772a9a8 - - /* x^121856 mod p(x)` << 1, x^121920 mod p(x)` << 1 */ - .octa 0x000000011d0908bc0000000155f295bc - - /* x^120832 mod p(x)` << 1, x^120896 mod p(x)` << 1 */ - .octa 0x0000000193ed97ea00000000595f9282 - - /* x^119808 mod p(x)` << 1, x^119872 mod p(x)` << 1 */ - .octa 0x000000013a0f1c520000000164b1c25a - - /* x^118784 mod p(x)` << 1, x^118848 mod p(x)` << 1 */ - .octa 0x000000010c2c40c000000000fbd67c50 - - /* x^117760 mod p(x)` << 1, x^117824 mod p(x)` << 1 */ - .octa 0x00000000ff6fac3e0000000096076268 - - /* x^116736 mod p(x)` << 1, x^116800 mod p(x)` << 1 */ - .octa 0x000000017b3609c000000001d288e4cc - - /* x^115712 mod p(x)` << 1, x^115776 mod p(x)` << 1 */ - .octa 0x0000000088c8c92200000001eaac1bdc - - /* x^114688 mod p(x)` << 1, x^114752 mod p(x)` << 1 */ - .octa 0x00000001751baae600000001f1ea39e2 - - /* x^113664 mod p(x)` << 1, x^113728 mod p(x)` << 1 */ - .octa 0x000000010795297200000001eb6506fc - - /* x^112640 mod p(x)` << 1, x^112704 mod p(x)` << 1 */ - .octa 0x0000000162b00abe000000010f806ffe - - /* x^111616 mod p(x)` << 1, x^111680 mod p(x)` << 1 */ - .octa 0x000000000d7b404c000000010408481e - - /* x^110592 mod p(x)` << 1, x^110656 mod p(x)` << 1 */ - .octa 0x00000000763b13d40000000188260534 - - /* x^109568 mod p(x)` << 1, x^109632 mod p(x)` << 1 */ - .octa 0x00000000f6dc22d80000000058fc73e0 - - /* x^108544 mod p(x)` << 1, x^108608 mod p(x)` << 1 */ - .octa 0x000000007daae06000000000391c59b8 - - /* x^107520 mod p(x)` << 1, x^107584 mod p(x)` << 1 */ - .octa 0x000000013359ab7c000000018b638400 - - /* x^106496 mod p(x)` << 1, x^106560 mod p(x)` << 1 */ - .octa 0x000000008add438a000000011738f5c4 - - /* x^105472 mod p(x)` << 1, x^105536 mod p(x)` << 1 */ - .octa 0x00000001edbefdea000000008cf7c6da - - /* x^104448 mod p(x)` << 1, x^104512 mod p(x)` << 1 */ - .octa 0x000000004104e0f800000001ef97fb16 - - /* x^103424 mod p(x)` << 1, x^103488 mod p(x)` << 1 */ - .octa 0x00000000b48a82220000000102130e20 - - /* x^102400 mod p(x)` << 1, x^102464 mod p(x)` << 1 */ - .octa 0x00000001bcb4684400000000db968898 - - /* x^101376 mod p(x)` << 1, x^101440 mod p(x)` << 1 */ - .octa 0x000000013293ce0a00000000b5047b5e - - /* x^100352 mod p(x)` << 1, x^100416 mod p(x)` << 1 */ - .octa 0x00000001710d0844000000010b90fdb2 - - /* x^99328 mod p(x)` << 1, x^99392 mod p(x)` << 1 */ - .octa 0x0000000117907f6e000000004834a32e - - /* x^98304 mod p(x)` << 1, x^98368 mod p(x)` << 1 */ - .octa 0x0000000087ddf93e0000000059c8f2b0 - - /* x^97280 mod p(x)` << 1, x^97344 mod p(x)` << 1 */ - .octa 0x000000005970e9b00000000122cec508 - - /* x^96256 mod p(x)` << 1, x^96320 mod p(x)` << 1 */ - .octa 0x0000000185b2b7d0000000000a330cda - - /* x^95232 mod p(x)` << 1, x^95296 mod p(x)` << 1 */ - .octa 0x00000001dcee0efc000000014a47148c - - /* x^94208 mod p(x)` << 1, x^94272 mod p(x)` << 1 */ - .octa 0x0000000030da27220000000042c61cb8 - - /* x^93184 mod p(x)` << 1, x^93248 mod p(x)` << 1 */ - .octa 0x000000012f925a180000000012fe6960 - - /* x^92160 mod p(x)` << 1, x^92224 mod p(x)` << 1 */ - .octa 0x00000000dd2e357c00000000dbda2c20 - - /* x^91136 mod p(x)` << 1, x^91200 mod p(x)` << 1 */ - .octa 0x00000000071c80de000000011122410c - - /* x^90112 mod p(x)` << 1, x^90176 mod p(x)` << 1 */ - .octa 0x000000011513140a00000000977b2070 - - /* x^89088 mod p(x)` << 1, x^89152 mod p(x)` << 1 */ - .octa 0x00000001df876e8e000000014050438e - - /* x^88064 mod p(x)` << 1, x^88128 mod p(x)` << 1 */ - .octa 0x000000015f81d6ce0000000147c840e8 - - /* x^87040 mod p(x)` << 1, x^87104 mod p(x)` << 1 */ - .octa 0x000000019dd94dbe00000001cc7c88ce - - /* x^86016 mod p(x)` << 1, x^86080 mod p(x)` << 1 */ - .octa 0x00000001373d206e00000001476b35a4 - - /* x^84992 mod p(x)` << 1, x^85056 mod p(x)` << 1 */ - .octa 0x00000000668ccade000000013d52d508 - - /* x^83968 mod p(x)` << 1, x^84032 mod p(x)` << 1 */ - .octa 0x00000001b192d268000000008e4be32e - - /* x^82944 mod p(x)` << 1, x^83008 mod p(x)` << 1 */ - .octa 0x00000000e30f3a7800000000024120fe - - /* x^81920 mod p(x)` << 1, x^81984 mod p(x)` << 1 */ - .octa 0x000000010ef1f7bc00000000ddecddb4 - - /* x^80896 mod p(x)` << 1, x^80960 mod p(x)` << 1 */ - .octa 0x00000001f5ac738000000000d4d403bc - - /* x^79872 mod p(x)` << 1, x^79936 mod p(x)` << 1 */ - .octa 0x000000011822ea7000000001734b89aa - - /* x^78848 mod p(x)` << 1, x^78912 mod p(x)` << 1 */ - .octa 0x00000000c3a33848000000010e7a58d6 - - /* x^77824 mod p(x)` << 1, x^77888 mod p(x)` << 1 */ - .octa 0x00000001bd151c2400000001f9f04e9c - - /* x^76800 mod p(x)` << 1, x^76864 mod p(x)` << 1 */ - .octa 0x0000000056002d7600000000b692225e - - /* x^75776 mod p(x)` << 1, x^75840 mod p(x)` << 1 */ - .octa 0x000000014657c4f4000000019b8d3f3e - - /* x^74752 mod p(x)` << 1, x^74816 mod p(x)` << 1 */ - .octa 0x0000000113742d7c00000001a874f11e - - /* x^73728 mod p(x)` << 1, x^73792 mod p(x)` << 1 */ - .octa 0x000000019c5920ba000000010d5a4254 - - /* x^72704 mod p(x)` << 1, x^72768 mod p(x)` << 1 */ - .octa 0x000000005216d2d600000000bbb2f5d6 - - /* x^71680 mod p(x)` << 1, x^71744 mod p(x)` << 1 */ - .octa 0x0000000136f5ad8a0000000179cc0e36 - - /* x^70656 mod p(x)` << 1, x^70720 mod p(x)` << 1 */ - .octa 0x000000018b07beb600000001dca1da4a - - /* x^69632 mod p(x)` << 1, x^69696 mod p(x)` << 1 */ - .octa 0x00000000db1e93b000000000feb1a192 - - /* x^68608 mod p(x)` << 1, x^68672 mod p(x)` << 1 */ - .octa 0x000000000b96fa3a00000000d1eeedd6 - - /* x^67584 mod p(x)` << 1, x^67648 mod p(x)` << 1 */ - .octa 0x00000001d9968af0000000008fad9bb4 - - /* x^66560 mod p(x)` << 1, x^66624 mod p(x)` << 1 */ - .octa 0x000000000e4a77a200000001884938e4 - - /* x^65536 mod p(x)` << 1, x^65600 mod p(x)` << 1 */ - .octa 0x00000000508c2ac800000001bc2e9bc0 - - /* x^64512 mod p(x)` << 1, x^64576 mod p(x)` << 1 */ - .octa 0x0000000021572a8000000001f9658a68 - - /* x^63488 mod p(x)` << 1, x^63552 mod p(x)` << 1 */ - .octa 0x00000001b859daf2000000001b9224fc - - /* x^62464 mod p(x)` << 1, x^62528 mod p(x)` << 1 */ - .octa 0x000000016f7884740000000055b2fb84 - - /* x^61440 mod p(x)` << 1, x^61504 mod p(x)` << 1 */ - .octa 0x00000001b438810e000000018b090348 - - /* x^60416 mod p(x)` << 1, x^60480 mod p(x)` << 1 */ - .octa 0x0000000095ddc6f2000000011ccbd5ea - - /* x^59392 mod p(x)` << 1, x^59456 mod p(x)` << 1 */ - .octa 0x00000001d977c20c0000000007ae47f8 - - /* x^58368 mod p(x)` << 1, x^58432 mod p(x)` << 1 */ - .octa 0x00000000ebedb99a0000000172acbec0 - - /* x^57344 mod p(x)` << 1, x^57408 mod p(x)` << 1 */ - .octa 0x00000001df9e9e9200000001c6e3ff20 - - /* x^56320 mod p(x)` << 1, x^56384 mod p(x)` << 1 */ - .octa 0x00000001a4a3f95200000000e1b38744 - - /* x^55296 mod p(x)` << 1, x^55360 mod p(x)` << 1 */ - .octa 0x00000000e2f5122000000000791585b2 - - /* x^54272 mod p(x)` << 1, x^54336 mod p(x)` << 1 */ - .octa 0x000000004aa01f3e00000000ac53b894 - - /* x^53248 mod p(x)` << 1, x^53312 mod p(x)` << 1 */ - .octa 0x00000000b3e90a5800000001ed5f2cf4 - - /* x^52224 mod p(x)` << 1, x^52288 mod p(x)` << 1 */ - .octa 0x000000000c9ca2aa00000001df48b2e0 - - /* x^51200 mod p(x)` << 1, x^51264 mod p(x)` << 1 */ - .octa 0x000000015168231600000000049c1c62 - - /* x^50176 mod p(x)` << 1, x^50240 mod p(x)` << 1 */ - .octa 0x0000000036fce78c000000017c460c12 - - /* x^49152 mod p(x)` << 1, x^49216 mod p(x)` << 1 */ - .octa 0x000000009037dc10000000015be4da7e - - /* x^48128 mod p(x)` << 1, x^48192 mod p(x)` << 1 */ - .octa 0x00000000d3298582000000010f38f668 - - /* x^47104 mod p(x)` << 1, x^47168 mod p(x)` << 1 */ - .octa 0x00000001b42e8ad60000000039f40a00 - - /* x^46080 mod p(x)` << 1, x^46144 mod p(x)` << 1 */ - .octa 0x00000000142a983800000000bd4c10c4 - - /* x^45056 mod p(x)` << 1, x^45120 mod p(x)` << 1 */ - .octa 0x0000000109c7f1900000000042db1d98 - - /* x^44032 mod p(x)` << 1, x^44096 mod p(x)` << 1 */ - .octa 0x0000000056ff931000000001c905bae6 - - /* x^43008 mod p(x)` << 1, x^43072 mod p(x)` << 1 */ - .octa 0x00000001594513aa00000000069d40ea - - /* x^41984 mod p(x)` << 1, x^42048 mod p(x)` << 1 */ - .octa 0x00000001e3b5b1e8000000008e4fbad0 - - /* x^40960 mod p(x)` << 1, x^41024 mod p(x)` << 1 */ - .octa 0x000000011dd5fc080000000047bedd46 - - /* x^39936 mod p(x)` << 1, x^40000 mod p(x)` << 1 */ - .octa 0x00000001675f0cc20000000026396bf8 - - /* x^38912 mod p(x)` << 1, x^38976 mod p(x)` << 1 */ - .octa 0x00000000d1c8dd4400000000379beb92 - - /* x^37888 mod p(x)` << 1, x^37952 mod p(x)` << 1 */ - .octa 0x0000000115ebd3d8000000000abae54a - - /* x^36864 mod p(x)` << 1, x^36928 mod p(x)` << 1 */ - .octa 0x00000001ecbd0dac0000000007e6a128 - - /* x^35840 mod p(x)` << 1, x^35904 mod p(x)` << 1 */ - .octa 0x00000000cdf67af2000000000ade29d2 - - /* x^34816 mod p(x)` << 1, x^34880 mod p(x)` << 1 */ - .octa 0x000000004c01ff4c00000000f974c45c - - /* x^33792 mod p(x)` << 1, x^33856 mod p(x)` << 1 */ - .octa 0x00000000f2d8657e00000000e77ac60a - - /* x^32768 mod p(x)` << 1, x^32832 mod p(x)` << 1 */ - .octa 0x000000006bae74c40000000145895816 - - /* x^31744 mod p(x)` << 1, x^31808 mod p(x)` << 1 */ - .octa 0x0000000152af8aa00000000038e362be - - /* x^30720 mod p(x)` << 1, x^30784 mod p(x)` << 1 */ - .octa 0x0000000004663802000000007f991a64 - - /* x^29696 mod p(x)` << 1, x^29760 mod p(x)` << 1 */ - .octa 0x00000001ab2f5afc00000000fa366d3a - - /* x^28672 mod p(x)` << 1, x^28736 mod p(x)` << 1 */ - .octa 0x0000000074a4ebd400000001a2bb34f0 - - /* x^27648 mod p(x)` << 1, x^27712 mod p(x)` << 1 */ - .octa 0x00000001d7ab3a4c0000000028a9981e - - /* x^26624 mod p(x)` << 1, x^26688 mod p(x)` << 1 */ - .octa 0x00000001a8da60c600000001dbc672be - - /* x^25600 mod p(x)` << 1, x^25664 mod p(x)` << 1 */ - .octa 0x000000013cf6382000000000b04d77f6 - - /* x^24576 mod p(x)` << 1, x^24640 mod p(x)` << 1 */ - .octa 0x00000000bec12e1e0000000124400d96 - - /* x^23552 mod p(x)` << 1, x^23616 mod p(x)` << 1 */ - .octa 0x00000001c6368010000000014ca4b414 - - /* x^22528 mod p(x)` << 1, x^22592 mod p(x)` << 1 */ - .octa 0x00000001e6e78758000000012fe2c938 - - /* x^21504 mod p(x)` << 1, x^21568 mod p(x)` << 1 */ - .octa 0x000000008d7f2b3c00000001faed01e6 - - /* x^20480 mod p(x)` << 1, x^20544 mod p(x)` << 1 */ - .octa 0x000000016b4a156e000000007e80ecfe - - /* x^19456 mod p(x)` << 1, x^19520 mod p(x)` << 1 */ - .octa 0x00000001c63cfeb60000000098daee94 - - /* x^18432 mod p(x)` << 1, x^18496 mod p(x)` << 1 */ - .octa 0x000000015f902670000000010a04edea - - /* x^17408 mod p(x)` << 1, x^17472 mod p(x)` << 1 */ - .octa 0x00000001cd5de11e00000001c00b4524 - - /* x^16384 mod p(x)` << 1, x^16448 mod p(x)` << 1 */ - .octa 0x000000001acaec540000000170296550 - - /* x^15360 mod p(x)` << 1, x^15424 mod p(x)` << 1 */ - .octa 0x000000002bd0ca780000000181afaa48 - - /* x^14336 mod p(x)` << 1, x^14400 mod p(x)` << 1 */ - .octa 0x0000000032d63d5c0000000185a31ffa - - /* x^13312 mod p(x)` << 1, x^13376 mod p(x)` << 1 */ - .octa 0x000000001c6d4e4c000000002469f608 - - /* x^12288 mod p(x)` << 1, x^12352 mod p(x)` << 1 */ - .octa 0x0000000106a60b92000000006980102a - - /* x^11264 mod p(x)` << 1, x^11328 mod p(x)` << 1 */ - .octa 0x00000000d3855e120000000111ea9ca8 - - /* x^10240 mod p(x)` << 1, x^10304 mod p(x)` << 1 */ - .octa 0x00000000e312563600000001bd1d29ce - - /* x^9216 mod p(x)` << 1, x^9280 mod p(x)` << 1 */ - .octa 0x000000009e8f7ea400000001b34b9580 - - /* x^8192 mod p(x)` << 1, x^8256 mod p(x)` << 1 */ - .octa 0x00000001c82e562c000000003076054e - - /* x^7168 mod p(x)` << 1, x^7232 mod p(x)` << 1 */ - .octa 0x00000000ca9f09ce000000012a608ea4 - - /* x^6144 mod p(x)` << 1, x^6208 mod p(x)` << 1 */ - .octa 0x00000000c63764e600000000784d05fe - - /* x^5120 mod p(x)` << 1, x^5184 mod p(x)` << 1 */ - .octa 0x0000000168d2e49e000000016ef0d82a - - /* x^4096 mod p(x)` << 1, x^4160 mod p(x)` << 1 */ - .octa 0x00000000e986c1480000000075bda454 - - /* x^3072 mod p(x)` << 1, x^3136 mod p(x)` << 1 */ - .octa 0x00000000cfb65894000000003dc0a1c4 - - /* x^2048 mod p(x)` << 1, x^2112 mod p(x)` << 1 */ - .octa 0x0000000111cadee400000000e9a5d8be - - /* x^1024 mod p(x)` << 1, x^1088 mod p(x)` << 1 */ - .octa 0x0000000171fb63ce00000001609bc4b4 - - .short_constants : - - /* Reduce final 1024-2048 bits to 64 bits, shifting 32 bits to include the trailing 32 bits of - zeros */ - /* x^1952 mod p(x)`, x^1984 mod p(x)`, x^2016 mod p(x)`, x^2048 mod p(x)` */ - .octa 0x7fec2963e5bf80485cf015c388e56f72 - - /* x^1824 mod p(x)`, x^1856 mod p(x)`, x^1888 mod p(x)`, x^1920 mod p(x)` */ - .octa 0x38e888d4844752a9963a18920246e2e6 - - /* x^1696 mod p(x)`, x^1728 mod p(x)`, x^1760 mod p(x)`, x^1792 mod p(x)` */ - .octa 0x42316c00730206ad419a441956993a31 - - /* x^1568 mod p(x)`, x^1600 mod p(x)`, x^1632 mod p(x)`, x^1664 mod p(x)` */ - .octa 0x543d5c543e65ddf9924752ba2b830011 - - /* x^1440 mod p(x)`, x^1472 mod p(x)`, x^1504 mod p(x)`, x^1536 mod p(x)` */ - .octa 0x78e87aaf56767c9255bd7f9518e4a304 - - /* x^1312 mod p(x)`, x^1344 mod p(x)`, x^1376 mod p(x)`, x^1408 mod p(x)` */ - .octa 0x8f68fcec1903da7f6d76739fe0553f1e - - /* x^1184 mod p(x)`, x^1216 mod p(x)`, x^1248 mod p(x)`, x^1280 mod p(x)` */ - .octa 0x3f4840246791d588c133722b1fe0b5c3 - - /* x^1056 mod p(x)`, x^1088 mod p(x)`, x^1120 mod p(x)`, x^1152 mod p(x)` */ - .octa 0x34c96751b04de25a64b67ee0e55ef1f3 - - /* x^928 mod p(x)`, x^960 mod p(x)`, x^992 mod p(x)`, x^1024 mod p(x)` */ - .octa 0x156c8e180b4a395b069db049b8fdb1e7 - - /* x^800 mod p(x)`, x^832 mod p(x)`, x^864 mod p(x)`, x^896 mod p(x)` */ - .octa 0xe0b99ccbe661f7bea11bfaf3c9e90b9e - - /* x^672 mod p(x)`, x^704 mod p(x)`, x^736 mod p(x)`, x^768 mod p(x)` */ - .octa 0x041d37768cd75659817cdc5119b29a35 - - /* x^544 mod p(x)`, x^576 mod p(x)`, x^608 mod p(x)`, x^640 mod p(x)` */ - .octa 0x3a0777818cfaa9651ce9d94b36c41f1c - - /* x^416 mod p(x)`, x^448 mod p(x)`, x^480 mod p(x)`, x^512 mod p(x)` */ - .octa 0x0e148e8252377a554f256efcb82be955 +#endif /* CRC_TABLE */ +#ifdef POWER8_INTRINSICS + +/* Constants */ + +/* Reduce 262144 kbits to 1024 bits */ +static const __vector unsigned long long vcrc_const[255] __attribute__((aligned(16))) = { +#ifdef __LITTLE_ENDIAN__ + /* x^261120 mod p(x)` << 1, x^261184 mod p(x)` << 1 */ + {0x000000009c37c408, 0x00000000b6ca9e20}, + /* x^260096 mod p(x)` << 1, x^260160 mod p(x)` << 1 */ + {0x00000001b51df26c, 0x00000000350249a8}, + /* x^259072 mod p(x)` << 1, x^259136 mod p(x)` << 1 */ + {0x000000000724b9d0, 0x00000001862dac54}, + /* x^258048 mod p(x)` << 1, x^258112 mod p(x)` << 1 */ + {0x00000001c00532fe, 0x00000001d87fb48c}, + /* x^257024 mod p(x)` << 1, x^257088 mod p(x)` << 1 */ + {0x00000000f05a9362, 0x00000001f39b699e}, + /* x^256000 mod p(x)` << 1, x^256064 mod p(x)` << 1 */ + {0x00000001e1007970, 0x0000000101da11b4}, + /* x^254976 mod p(x)` << 1, x^255040 mod p(x)` << 1 */ + {0x00000000a57366ee, 0x00000001cab571e0}, + /* x^253952 mod p(x)` << 1, x^254016 mod p(x)` << 1 */ + {0x0000000192011284, 0x00000000c7020cfe}, + /* x^252928 mod p(x)` << 1, x^252992 mod p(x)` << 1 */ + {0x0000000162716d9a, 0x00000000cdaed1ae}, + /* x^251904 mod p(x)` << 1, x^251968 mod p(x)` << 1 */ + {0x00000000cd97ecde, 0x00000001e804effc}, + /* x^250880 mod p(x)` << 1, x^250944 mod p(x)` << 1 */ + {0x0000000058812bc0, 0x0000000077c3ea3a}, + /* x^249856 mod p(x)` << 1, x^249920 mod p(x)` << 1 */ + {0x0000000088b8c12e, 0x0000000068df31b4}, + /* x^248832 mod p(x)` << 1, x^248896 mod p(x)` << 1 */ + {0x00000001230b234c, 0x00000000b059b6c2}, + /* x^247808 mod p(x)` << 1, x^247872 mod p(x)` << 1 */ + {0x00000001120b416e, 0x0000000145fb8ed8}, + /* x^246784 mod p(x)` << 1, x^246848 mod p(x)` << 1 */ + {0x00000001974aecb0, 0x00000000cbc09168}, + /* x^245760 mod p(x)` << 1, x^245824 mod p(x)` << 1 */ + {0x000000008ee3f226, 0x000000005ceeedc2}, + /* x^244736 mod p(x)` << 1, x^244800 mod p(x)` << 1 */ + {0x00000001089aba9a, 0x0000000047d74e86}, + /* x^243712 mod p(x)` << 1, x^243776 mod p(x)` << 1 */ + {0x0000000065113872, 0x00000001407e9e22}, + /* x^242688 mod p(x)` << 1, x^242752 mod p(x)` << 1 */ + {0x000000005c07ec10, 0x00000001da967bda}, + /* x^241664 mod p(x)` << 1, x^241728 mod p(x)` << 1 */ + {0x0000000187590924, 0x000000006c898368}, + /* x^240640 mod p(x)` << 1, x^240704 mod p(x)` << 1 */ + {0x00000000e35da7c6, 0x00000000f2d14c98}, + /* x^239616 mod p(x)` << 1, x^239680 mod p(x)` << 1 */ + {0x000000000415855a, 0x00000001993c6ad4}, + /* x^238592 mod p(x)` << 1, x^238656 mod p(x)` << 1 */ + {0x0000000073617758, 0x000000014683d1ac}, + /* x^237568 mod p(x)` << 1, x^237632 mod p(x)` << 1 */ + {0x0000000176021d28, 0x00000001a7c93e6c}, + /* x^236544 mod p(x)` << 1, x^236608 mod p(x)` << 1 */ + {0x00000001c358fd0a, 0x000000010211e90a}, + /* x^235520 mod p(x)` << 1, x^235584 mod p(x)` << 1 */ + {0x00000001ff7a2c18, 0x000000001119403e}, + /* x^234496 mod p(x)` << 1, x^234560 mod p(x)` << 1 */ + {0x00000000f2d9f7e4, 0x000000001c3261aa}, + /* x^233472 mod p(x)` << 1, x^233536 mod p(x)` << 1 */ + {0x000000016cf1f9c8, 0x000000014e37a634}, + /* x^232448 mod p(x)` << 1, x^232512 mod p(x)` << 1 */ + {0x000000010af9279a, 0x0000000073786c0c}, + /* x^231424 mod p(x)` << 1, x^231488 mod p(x)` << 1 */ + {0x0000000004f101e8, 0x000000011dc037f8}, + /* x^230400 mod p(x)` << 1, x^230464 mod p(x)` << 1 */ + {0x0000000070bcf184, 0x0000000031433dfc}, + /* x^229376 mod p(x)` << 1, x^229440 mod p(x)` << 1 */ + {0x000000000a8de642, 0x000000009cde8348}, + /* x^228352 mod p(x)` << 1, x^228416 mod p(x)` << 1 */ + {0x0000000062ea130c, 0x0000000038d3c2a6}, + /* x^227328 mod p(x)` << 1, x^227392 mod p(x)` << 1 */ + {0x00000001eb31cbb2, 0x000000011b25f260}, + /* x^226304 mod p(x)` << 1, x^226368 mod p(x)` << 1 */ + {0x0000000170783448, 0x000000001629e6f0}, + /* x^225280 mod p(x)` << 1, x^225344 mod p(x)` << 1 */ + {0x00000001a684b4c6, 0x0000000160838b4c}, + /* x^224256 mod p(x)` << 1, x^224320 mod p(x)` << 1 */ + {0x00000000253ca5b4, 0x000000007a44011c}, + /* x^223232 mod p(x)` << 1, x^223296 mod p(x)` << 1 */ + {0x0000000057b4b1e2, 0x00000000226f417a}, + /* x^222208 mod p(x)` << 1, x^222272 mod p(x)` << 1 */ + {0x00000000b6bd084c, 0x0000000045eb2eb4}, + /* x^221184 mod p(x)` << 1, x^221248 mod p(x)` << 1 */ + {0x0000000123c2d592, 0x000000014459d70c}, + /* x^220160 mod p(x)` << 1, x^220224 mod p(x)` << 1 */ + {0x00000000159dafce, 0x00000001d406ed82}, + /* x^219136 mod p(x)` << 1, x^219200 mod p(x)` << 1 */ + {0x0000000127e1a64e, 0x0000000160c8e1a8}, + /* x^218112 mod p(x)` << 1, x^218176 mod p(x)` << 1 */ + {0x0000000056860754, 0x0000000027ba8098}, + /* x^217088 mod p(x)` << 1, x^217152 mod p(x)` << 1 */ + {0x00000001e661aae8, 0x000000006d92d018}, + /* x^216064 mod p(x)` << 1, x^216128 mod p(x)` << 1 */ + {0x00000000f82c6166, 0x000000012ed7e3f2}, + /* x^215040 mod p(x)` << 1, x^215104 mod p(x)` << 1 */ + {0x00000000c4f9c7ae, 0x000000002dc87788}, + /* x^214016 mod p(x)` << 1, x^214080 mod p(x)` << 1 */ + {0x0000000074203d20, 0x0000000018240bb8}, + /* x^212992 mod p(x)` << 1, x^213056 mod p(x)` << 1 */ + {0x0000000198173052, 0x000000001ad38158}, + /* x^211968 mod p(x)` << 1, x^212032 mod p(x)` << 1 */ + {0x00000001ce8aba54, 0x00000001396b78f2}, + /* x^210944 mod p(x)` << 1, x^211008 mod p(x)` << 1 */ + {0x00000001850d5d94, 0x000000011a681334}, + /* x^209920 mod p(x)` << 1, x^209984 mod p(x)` << 1 */ + {0x00000001d609239c, 0x000000012104732e}, + /* x^208896 mod p(x)` << 1, x^208960 mod p(x)` << 1 */ + {0x000000001595f048, 0x00000000a140d90c}, + /* x^207872 mod p(x)` << 1, x^207936 mod p(x)` << 1 */ + {0x0000000042ccee08, 0x00000001b7215eda}, + /* x^206848 mod p(x)` << 1, x^206912 mod p(x)` << 1 */ + {0x000000010a389d74, 0x00000001aaf1df3c}, + /* x^205824 mod p(x)` << 1, x^205888 mod p(x)` << 1 */ + {0x000000012a840da6, 0x0000000029d15b8a}, + /* x^204800 mod p(x)` << 1, x^204864 mod p(x)` << 1 */ + {0x000000001d181c0c, 0x00000000f1a96922}, + /* x^203776 mod p(x)` << 1, x^203840 mod p(x)` << 1 */ + {0x0000000068b7d1f6, 0x00000001ac80d03c}, + /* x^202752 mod p(x)` << 1, x^202816 mod p(x)` << 1 */ + {0x000000005b0f14fc, 0x000000000f11d56a}, + /* x^201728 mod p(x)` << 1, x^201792 mod p(x)` << 1 */ + {0x0000000179e9e730, 0x00000001f1c022a2}, + /* x^200704 mod p(x)` << 1, x^200768 mod p(x)` << 1 */ + {0x00000001ce1368d6, 0x0000000173d00ae2}, + /* x^199680 mod p(x)` << 1, x^199744 mod p(x)` << 1 */ + {0x0000000112c3a84c, 0x00000001d4ffe4ac}, + /* x^198656 mod p(x)` << 1, x^198720 mod p(x)` << 1 */ + {0x00000000de940fee, 0x000000016edc5ae4}, + /* x^197632 mod p(x)` << 1, x^197696 mod p(x)` << 1 */ + {0x00000000fe896b7e, 0x00000001f1a02140}, + /* x^196608 mod p(x)` << 1, x^196672 mod p(x)` << 1 */ + {0x00000001f797431c, 0x00000000ca0b28a0}, + /* x^195584 mod p(x)` << 1, x^195648 mod p(x)` << 1 */ + {0x0000000053e989ba, 0x00000001928e30a2}, + /* x^194560 mod p(x)` << 1, x^194624 mod p(x)` << 1 */ + {0x000000003920cd16, 0x0000000097b1b002}, + /* x^193536 mod p(x)` << 1, x^193600 mod p(x)` << 1 */ + {0x00000001e6f579b8, 0x00000000b15bf906}, + /* x^192512 mod p(x)` << 1, x^192576 mod p(x)` << 1 */ + {0x000000007493cb0a, 0x00000000411c5d52}, + /* x^191488 mod p(x)` << 1, x^191552 mod p(x)` << 1 */ + {0x00000001bdd376d8, 0x00000001c36f3300}, + /* x^190464 mod p(x)` << 1, x^190528 mod p(x)` << 1 */ + {0x000000016badfee6, 0x00000001119227e0}, + /* x^189440 mod p(x)` << 1, x^189504 mod p(x)` << 1 */ + {0x0000000071de5c58, 0x00000000114d4702}, + /* x^188416 mod p(x)` << 1, x^188480 mod p(x)` << 1 */ + {0x00000000453f317c, 0x00000000458b5b98}, + /* x^187392 mod p(x)` << 1, x^187456 mod p(x)` << 1 */ + {0x0000000121675cce, 0x000000012e31fb8e}, + /* x^186368 mod p(x)` << 1, x^186432 mod p(x)` << 1 */ + {0x00000001f409ee92, 0x000000005cf619d8}, + /* x^185344 mod p(x)` << 1, x^185408 mod p(x)` << 1 */ + {0x00000000f36b9c88, 0x0000000063f4d8b2}, + /* x^184320 mod p(x)` << 1, x^184384 mod p(x)` << 1 */ + {0x0000000036b398f4, 0x000000004138dc8a}, + /* x^183296 mod p(x)` << 1, x^183360 mod p(x)` << 1 */ + {0x00000001748f9adc, 0x00000001d29ee8e0}, + /* x^182272 mod p(x)` << 1, x^182336 mod p(x)` << 1 */ + {0x00000001be94ec00, 0x000000006a08ace8}, + /* x^181248 mod p(x)` << 1, x^181312 mod p(x)` << 1 */ + {0x00000000b74370d6, 0x0000000127d42010}, + /* x^180224 mod p(x)` << 1, x^180288 mod p(x)` << 1 */ + {0x00000001174d0b98, 0x0000000019d76b62}, + /* x^179200 mod p(x)` << 1, x^179264 mod p(x)` << 1 */ + {0x00000000befc06a4, 0x00000001b1471f6e}, + /* x^178176 mod p(x)` << 1, x^178240 mod p(x)` << 1 */ + {0x00000001ae125288, 0x00000001f64c19cc}, + /* x^177152 mod p(x)` << 1, x^177216 mod p(x)` << 1 */ + {0x0000000095c19b34, 0x00000000003c0ea0}, + /* x^176128 mod p(x)` << 1, x^176192 mod p(x)` << 1 */ + {0x00000001a78496f2, 0x000000014d73abf6}, + /* x^175104 mod p(x)` << 1, x^175168 mod p(x)` << 1 */ + {0x00000001ac5390a0, 0x00000001620eb844}, + /* x^174080 mod p(x)` << 1, x^174144 mod p(x)` << 1 */ + {0x000000002a80ed6e, 0x0000000147655048}, + /* x^173056 mod p(x)` << 1, x^173120 mod p(x)` << 1 */ + {0x00000001fa9b0128, 0x0000000067b5077e}, + /* x^172032 mod p(x)` << 1, x^172096 mod p(x)` << 1 */ + {0x00000001ea94929e, 0x0000000010ffe206}, + /* x^171008 mod p(x)` << 1, x^171072 mod p(x)` << 1 */ + {0x0000000125f4305c, 0x000000000fee8f1e}, + /* x^169984 mod p(x)` << 1, x^170048 mod p(x)` << 1 */ + {0x00000001471e2002, 0x00000001da26fbae}, + /* x^168960 mod p(x)` << 1, x^169024 mod p(x)` << 1 */ + {0x0000000132d2253a, 0x00000001b3a8bd88}, + /* x^167936 mod p(x)` << 1, x^168000 mod p(x)` << 1 */ + {0x00000000f26b3592, 0x00000000e8f3898e}, + /* x^166912 mod p(x)` << 1, x^166976 mod p(x)` << 1 */ + {0x00000000bc8b67b0, 0x00000000b0d0d28c}, + /* x^165888 mod p(x)` << 1, x^165952 mod p(x)` << 1 */ + {0x000000013a826ef2, 0x0000000030f2a798}, + /* x^164864 mod p(x)` << 1, x^164928 mod p(x)` << 1 */ + {0x0000000081482c84, 0x000000000fba1002}, + /* x^163840 mod p(x)` << 1, x^163904 mod p(x)` << 1 */ + {0x00000000e77307c2, 0x00000000bdb9bd72}, + /* x^162816 mod p(x)` << 1, x^162880 mod p(x)` << 1 */ + {0x00000000d4a07ec8, 0x0000000075d3bf5a}, + /* x^161792 mod p(x)` << 1, x^161856 mod p(x)` << 1 */ + {0x0000000017102100, 0x00000000ef1f98a0}, + /* x^160768 mod p(x)` << 1, x^160832 mod p(x)` << 1 */ + {0x00000000db406486, 0x00000000689c7602}, + /* x^159744 mod p(x)` << 1, x^159808 mod p(x)` << 1 */ + {0x0000000192db7f88, 0x000000016d5fa5fe}, + /* x^158720 mod p(x)` << 1, x^158784 mod p(x)` << 1 */ + {0x000000018bf67b1e, 0x00000001d0d2b9ca}, + /* x^157696 mod p(x)` << 1, x^157760 mod p(x)` << 1 */ + {0x000000007c09163e, 0x0000000041e7b470}, + /* x^156672 mod p(x)` << 1, x^156736 mod p(x)` << 1 */ + {0x000000000adac060, 0x00000001cbb6495e}, + /* x^155648 mod p(x)` << 1, x^155712 mod p(x)` << 1 */ + {0x00000000bd8316ae, 0x000000010052a0b0}, + /* x^154624 mod p(x)` << 1, x^154688 mod p(x)` << 1 */ + {0x000000019f09ab54, 0x00000001d8effb5c}, + /* x^153600 mod p(x)` << 1, x^153664 mod p(x)` << 1 */ + {0x0000000125155542, 0x00000001d969853c}, + /* x^152576 mod p(x)` << 1, x^152640 mod p(x)` << 1 */ + {0x000000018fdb5882, 0x00000000523ccce2}, + /* x^151552 mod p(x)` << 1, x^151616 mod p(x)` << 1 */ + {0x00000000e794b3f4, 0x000000001e2436bc}, + /* x^150528 mod p(x)` << 1, x^150592 mod p(x)` << 1 */ + {0x000000016f9bb022, 0x00000000ddd1c3a2}, + /* x^149504 mod p(x)` << 1, x^149568 mod p(x)` << 1 */ + {0x00000000290c9978, 0x0000000019fcfe38}, + /* x^148480 mod p(x)` << 1, x^148544 mod p(x)` << 1 */ + {0x0000000083c0f350, 0x00000001ce95db64}, + /* x^147456 mod p(x)` << 1, x^147520 mod p(x)` << 1 */ + {0x0000000173ea6628, 0x00000000af582806}, + /* x^146432 mod p(x)` << 1, x^146496 mod p(x)` << 1 */ + {0x00000001c8b4e00a, 0x00000001006388f6}, + /* x^145408 mod p(x)` << 1, x^145472 mod p(x)` << 1 */ + {0x00000000de95d6aa, 0x0000000179eca00a}, + /* x^144384 mod p(x)` << 1, x^144448 mod p(x)` << 1 */ + {0x000000010b7f7248, 0x0000000122410a6a}, + /* x^143360 mod p(x)` << 1, x^143424 mod p(x)` << 1 */ + {0x00000001326e3a06, 0x000000004288e87c}, + /* x^142336 mod p(x)` << 1, x^142400 mod p(x)` << 1 */ + {0x00000000bb62c2e6, 0x000000016c5490da}, + /* x^141312 mod p(x)` << 1, x^141376 mod p(x)` << 1 */ + {0x0000000156a4b2c2, 0x00000000d1c71f6e}, + /* x^140288 mod p(x)` << 1, x^140352 mod p(x)` << 1 */ + {0x000000011dfe763a, 0x00000001b4ce08a6}, + /* x^139264 mod p(x)` << 1, x^139328 mod p(x)` << 1 */ + {0x000000007bcca8e2, 0x00000001466ba60c}, + /* x^138240 mod p(x)` << 1, x^138304 mod p(x)` << 1 */ + {0x0000000186118faa, 0x00000001f6c488a4}, + /* x^137216 mod p(x)` << 1, x^137280 mod p(x)` << 1 */ + {0x0000000111a65a88, 0x000000013bfb0682}, + /* x^136192 mod p(x)` << 1, x^136256 mod p(x)` << 1 */ + {0x000000003565e1c4, 0x00000000690e9e54}, + /* x^135168 mod p(x)` << 1, x^135232 mod p(x)` << 1 */ + {0x000000012ed02a82, 0x00000000281346b6}, + /* x^134144 mod p(x)` << 1, x^134208 mod p(x)` << 1 */ + {0x00000000c486ecfc, 0x0000000156464024}, + /* x^133120 mod p(x)` << 1, x^133184 mod p(x)` << 1 */ + {0x0000000001b951b2, 0x000000016063a8dc}, + /* x^132096 mod p(x)` << 1, x^132160 mod p(x)` << 1 */ + {0x0000000048143916, 0x0000000116a66362}, + /* x^131072 mod p(x)` << 1, x^131136 mod p(x)` << 1 */ + {0x00000001dc2ae124, 0x000000017e8aa4d2}, + /* x^130048 mod p(x)` << 1, x^130112 mod p(x)` << 1 */ + {0x00000001416c58d6, 0x00000001728eb10c}, + /* x^129024 mod p(x)` << 1, x^129088 mod p(x)` << 1 */ + {0x00000000a479744a, 0x00000001b08fd7fa}, + /* x^128000 mod p(x)` << 1, x^128064 mod p(x)` << 1 */ + {0x0000000096ca3a26, 0x00000001092a16e8}, + /* x^126976 mod p(x)` << 1, x^127040 mod p(x)` << 1 */ + {0x00000000ff223d4e, 0x00000000a505637c}, + /* x^125952 mod p(x)` << 1, x^126016 mod p(x)` << 1 */ + {0x000000010e84da42, 0x00000000d94869b2}, + /* x^124928 mod p(x)` << 1, x^124992 mod p(x)` << 1 */ + {0x00000001b61ba3d0, 0x00000001c8b203ae}, + /* x^123904 mod p(x)` << 1, x^123968 mod p(x)` << 1 */ + {0x00000000680f2de8, 0x000000005704aea0}, + /* x^122880 mod p(x)` << 1, x^122944 mod p(x)` << 1 */ + {0x000000008772a9a8, 0x000000012e295fa2}, + /* x^121856 mod p(x)` << 1, x^121920 mod p(x)` << 1 */ + {0x0000000155f295bc, 0x000000011d0908bc}, + /* x^120832 mod p(x)` << 1, x^120896 mod p(x)` << 1 */ + {0x00000000595f9282, 0x0000000193ed97ea}, + /* x^119808 mod p(x)` << 1, x^119872 mod p(x)` << 1 */ + {0x0000000164b1c25a, 0x000000013a0f1c52}, + /* x^118784 mod p(x)` << 1, x^118848 mod p(x)` << 1 */ + {0x00000000fbd67c50, 0x000000010c2c40c0}, + /* x^117760 mod p(x)` << 1, x^117824 mod p(x)` << 1 */ + {0x0000000096076268, 0x00000000ff6fac3e}, + /* x^116736 mod p(x)` << 1, x^116800 mod p(x)` << 1 */ + {0x00000001d288e4cc, 0x000000017b3609c0}, + /* x^115712 mod p(x)` << 1, x^115776 mod p(x)` << 1 */ + {0x00000001eaac1bdc, 0x0000000088c8c922}, + /* x^114688 mod p(x)` << 1, x^114752 mod p(x)` << 1 */ + {0x00000001f1ea39e2, 0x00000001751baae6}, + /* x^113664 mod p(x)` << 1, x^113728 mod p(x)` << 1 */ + {0x00000001eb6506fc, 0x0000000107952972}, + /* x^112640 mod p(x)` << 1, x^112704 mod p(x)` << 1 */ + {0x000000010f806ffe, 0x0000000162b00abe}, + /* x^111616 mod p(x)` << 1, x^111680 mod p(x)` << 1 */ + {0x000000010408481e, 0x000000000d7b404c}, + /* x^110592 mod p(x)` << 1, x^110656 mod p(x)` << 1 */ + {0x0000000188260534, 0x00000000763b13d4}, + /* x^109568 mod p(x)` << 1, x^109632 mod p(x)` << 1 */ + {0x0000000058fc73e0, 0x00000000f6dc22d8}, + /* x^108544 mod p(x)` << 1, x^108608 mod p(x)` << 1 */ + {0x00000000391c59b8, 0x000000007daae060}, + /* x^107520 mod p(x)` << 1, x^107584 mod p(x)` << 1 */ + {0x000000018b638400, 0x000000013359ab7c}, + /* x^106496 mod p(x)` << 1, x^106560 mod p(x)` << 1 */ + {0x000000011738f5c4, 0x000000008add438a}, + /* x^105472 mod p(x)` << 1, x^105536 mod p(x)` << 1 */ + {0x000000008cf7c6da, 0x00000001edbefdea}, + /* x^104448 mod p(x)` << 1, x^104512 mod p(x)` << 1 */ + {0x00000001ef97fb16, 0x000000004104e0f8}, + /* x^103424 mod p(x)` << 1, x^103488 mod p(x)` << 1 */ + {0x0000000102130e20, 0x00000000b48a8222}, + /* x^102400 mod p(x)` << 1, x^102464 mod p(x)` << 1 */ + {0x00000000db968898, 0x00000001bcb46844}, + /* x^101376 mod p(x)` << 1, x^101440 mod p(x)` << 1 */ + {0x00000000b5047b5e, 0x000000013293ce0a}, + /* x^100352 mod p(x)` << 1, x^100416 mod p(x)` << 1 */ + {0x000000010b90fdb2, 0x00000001710d0844}, + /* x^99328 mod p(x)` << 1, x^99392 mod p(x)` << 1 */ + {0x000000004834a32e, 0x0000000117907f6e}, + /* x^98304 mod p(x)` << 1, x^98368 mod p(x)` << 1 */ + {0x0000000059c8f2b0, 0x0000000087ddf93e}, + /* x^97280 mod p(x)` << 1, x^97344 mod p(x)` << 1 */ + {0x0000000122cec508, 0x000000005970e9b0}, + /* x^96256 mod p(x)` << 1, x^96320 mod p(x)` << 1 */ + {0x000000000a330cda, 0x0000000185b2b7d0}, + /* x^95232 mod p(x)` << 1, x^95296 mod p(x)` << 1 */ + {0x000000014a47148c, 0x00000001dcee0efc}, + /* x^94208 mod p(x)` << 1, x^94272 mod p(x)` << 1 */ + {0x0000000042c61cb8, 0x0000000030da2722}, + /* x^93184 mod p(x)` << 1, x^93248 mod p(x)` << 1 */ + {0x0000000012fe6960, 0x000000012f925a18}, + /* x^92160 mod p(x)` << 1, x^92224 mod p(x)` << 1 */ + {0x00000000dbda2c20, 0x00000000dd2e357c}, + /* x^91136 mod p(x)` << 1, x^91200 mod p(x)` << 1 */ + {0x000000011122410c, 0x00000000071c80de}, + /* x^90112 mod p(x)` << 1, x^90176 mod p(x)` << 1 */ + {0x00000000977b2070, 0x000000011513140a}, + /* x^89088 mod p(x)` << 1, x^89152 mod p(x)` << 1 */ + {0x000000014050438e, 0x00000001df876e8e}, + /* x^88064 mod p(x)` << 1, x^88128 mod p(x)` << 1 */ + {0x0000000147c840e8, 0x000000015f81d6ce}, + /* x^87040 mod p(x)` << 1, x^87104 mod p(x)` << 1 */ + {0x00000001cc7c88ce, 0x000000019dd94dbe}, + /* x^86016 mod p(x)` << 1, x^86080 mod p(x)` << 1 */ + {0x00000001476b35a4, 0x00000001373d206e}, + /* x^84992 mod p(x)` << 1, x^85056 mod p(x)` << 1 */ + {0x000000013d52d508, 0x00000000668ccade}, + /* x^83968 mod p(x)` << 1, x^84032 mod p(x)` << 1 */ + {0x000000008e4be32e, 0x00000001b192d268}, + /* x^82944 mod p(x)` << 1, x^83008 mod p(x)` << 1 */ + {0x00000000024120fe, 0x00000000e30f3a78}, + /* x^81920 mod p(x)` << 1, x^81984 mod p(x)` << 1 */ + {0x00000000ddecddb4, 0x000000010ef1f7bc}, + /* x^80896 mod p(x)` << 1, x^80960 mod p(x)` << 1 */ + {0x00000000d4d403bc, 0x00000001f5ac7380}, + /* x^79872 mod p(x)` << 1, x^79936 mod p(x)` << 1 */ + {0x00000001734b89aa, 0x000000011822ea70}, + /* x^78848 mod p(x)` << 1, x^78912 mod p(x)` << 1 */ + {0x000000010e7a58d6, 0x00000000c3a33848}, + /* x^77824 mod p(x)` << 1, x^77888 mod p(x)` << 1 */ + {0x00000001f9f04e9c, 0x00000001bd151c24}, + /* x^76800 mod p(x)` << 1, x^76864 mod p(x)` << 1 */ + {0x00000000b692225e, 0x0000000056002d76}, + /* x^75776 mod p(x)` << 1, x^75840 mod p(x)` << 1 */ + {0x000000019b8d3f3e, 0x000000014657c4f4}, + /* x^74752 mod p(x)` << 1, x^74816 mod p(x)` << 1 */ + {0x00000001a874f11e, 0x0000000113742d7c}, + /* x^73728 mod p(x)` << 1, x^73792 mod p(x)` << 1 */ + {0x000000010d5a4254, 0x000000019c5920ba}, + /* x^72704 mod p(x)` << 1, x^72768 mod p(x)` << 1 */ + {0x00000000bbb2f5d6, 0x000000005216d2d6}, + /* x^71680 mod p(x)` << 1, x^71744 mod p(x)` << 1 */ + {0x0000000179cc0e36, 0x0000000136f5ad8a}, + /* x^70656 mod p(x)` << 1, x^70720 mod p(x)` << 1 */ + {0x00000001dca1da4a, 0x000000018b07beb6}, + /* x^69632 mod p(x)` << 1, x^69696 mod p(x)` << 1 */ + {0x00000000feb1a192, 0x00000000db1e93b0}, + /* x^68608 mod p(x)` << 1, x^68672 mod p(x)` << 1 */ + {0x00000000d1eeedd6, 0x000000000b96fa3a}, + /* x^67584 mod p(x)` << 1, x^67648 mod p(x)` << 1 */ + {0x000000008fad9bb4, 0x00000001d9968af0}, + /* x^66560 mod p(x)` << 1, x^66624 mod p(x)` << 1 */ + {0x00000001884938e4, 0x000000000e4a77a2}, + /* x^65536 mod p(x)` << 1, x^65600 mod p(x)` << 1 */ + {0x00000001bc2e9bc0, 0x00000000508c2ac8}, + /* x^64512 mod p(x)` << 1, x^64576 mod p(x)` << 1 */ + {0x00000001f9658a68, 0x0000000021572a80}, + /* x^63488 mod p(x)` << 1, x^63552 mod p(x)` << 1 */ + {0x000000001b9224fc, 0x00000001b859daf2}, + /* x^62464 mod p(x)` << 1, x^62528 mod p(x)` << 1 */ + {0x0000000055b2fb84, 0x000000016f788474}, + /* x^61440 mod p(x)` << 1, x^61504 mod p(x)` << 1 */ + {0x000000018b090348, 0x00000001b438810e}, + /* x^60416 mod p(x)` << 1, x^60480 mod p(x)` << 1 */ + {0x000000011ccbd5ea, 0x0000000095ddc6f2}, + /* x^59392 mod p(x)` << 1, x^59456 mod p(x)` << 1 */ + {0x0000000007ae47f8, 0x00000001d977c20c}, + /* x^58368 mod p(x)` << 1, x^58432 mod p(x)` << 1 */ + {0x0000000172acbec0, 0x00000000ebedb99a}, + /* x^57344 mod p(x)` << 1, x^57408 mod p(x)` << 1 */ + {0x00000001c6e3ff20, 0x00000001df9e9e92}, + /* x^56320 mod p(x)` << 1, x^56384 mod p(x)` << 1 */ + {0x00000000e1b38744, 0x00000001a4a3f952}, + /* x^55296 mod p(x)` << 1, x^55360 mod p(x)` << 1 */ + {0x00000000791585b2, 0x00000000e2f51220}, + /* x^54272 mod p(x)` << 1, x^54336 mod p(x)` << 1 */ + {0x00000000ac53b894, 0x000000004aa01f3e}, + /* x^53248 mod p(x)` << 1, x^53312 mod p(x)` << 1 */ + {0x00000001ed5f2cf4, 0x00000000b3e90a58}, + /* x^52224 mod p(x)` << 1, x^52288 mod p(x)` << 1 */ + {0x00000001df48b2e0, 0x000000000c9ca2aa}, + /* x^51200 mod p(x)` << 1, x^51264 mod p(x)` << 1 */ + {0x00000000049c1c62, 0x0000000151682316}, + /* x^50176 mod p(x)` << 1, x^50240 mod p(x)` << 1 */ + {0x000000017c460c12, 0x0000000036fce78c}, + /* x^49152 mod p(x)` << 1, x^49216 mod p(x)` << 1 */ + {0x000000015be4da7e, 0x000000009037dc10}, + /* x^48128 mod p(x)` << 1, x^48192 mod p(x)` << 1 */ + {0x000000010f38f668, 0x00000000d3298582}, + /* x^47104 mod p(x)` << 1, x^47168 mod p(x)` << 1 */ + {0x0000000039f40a00, 0x00000001b42e8ad6}, + /* x^46080 mod p(x)` << 1, x^46144 mod p(x)` << 1 */ + {0x00000000bd4c10c4, 0x00000000142a9838}, + /* x^45056 mod p(x)` << 1, x^45120 mod p(x)` << 1 */ + {0x0000000042db1d98, 0x0000000109c7f190}, + /* x^44032 mod p(x)` << 1, x^44096 mod p(x)` << 1 */ + {0x00000001c905bae6, 0x0000000056ff9310}, + /* x^43008 mod p(x)` << 1, x^43072 mod p(x)` << 1 */ + {0x00000000069d40ea, 0x00000001594513aa}, + /* x^41984 mod p(x)` << 1, x^42048 mod p(x)` << 1 */ + {0x000000008e4fbad0, 0x00000001e3b5b1e8}, + /* x^40960 mod p(x)` << 1, x^41024 mod p(x)` << 1 */ + {0x0000000047bedd46, 0x000000011dd5fc08}, + /* x^39936 mod p(x)` << 1, x^40000 mod p(x)` << 1 */ + {0x0000000026396bf8, 0x00000001675f0cc2}, + /* x^38912 mod p(x)` << 1, x^38976 mod p(x)` << 1 */ + {0x00000000379beb92, 0x00000000d1c8dd44}, + /* x^37888 mod p(x)` << 1, x^37952 mod p(x)` << 1 */ + {0x000000000abae54a, 0x0000000115ebd3d8}, + /* x^36864 mod p(x)` << 1, x^36928 mod p(x)` << 1 */ + {0x0000000007e6a128, 0x00000001ecbd0dac}, + /* x^35840 mod p(x)` << 1, x^35904 mod p(x)` << 1 */ + {0x000000000ade29d2, 0x00000000cdf67af2}, + /* x^34816 mod p(x)` << 1, x^34880 mod p(x)` << 1 */ + {0x00000000f974c45c, 0x000000004c01ff4c}, + /* x^33792 mod p(x)` << 1, x^33856 mod p(x)` << 1 */ + {0x00000000e77ac60a, 0x00000000f2d8657e}, + /* x^32768 mod p(x)` << 1, x^32832 mod p(x)` << 1 */ + {0x0000000145895816, 0x000000006bae74c4}, + /* x^31744 mod p(x)` << 1, x^31808 mod p(x)` << 1 */ + {0x0000000038e362be, 0x0000000152af8aa0}, + /* x^30720 mod p(x)` << 1, x^30784 mod p(x)` << 1 */ + {0x000000007f991a64, 0x0000000004663802}, + /* x^29696 mod p(x)` << 1, x^29760 mod p(x)` << 1 */ + {0x00000000fa366d3a, 0x00000001ab2f5afc}, + /* x^28672 mod p(x)` << 1, x^28736 mod p(x)` << 1 */ + {0x00000001a2bb34f0, 0x0000000074a4ebd4}, + /* x^27648 mod p(x)` << 1, x^27712 mod p(x)` << 1 */ + {0x0000000028a9981e, 0x00000001d7ab3a4c}, + /* x^26624 mod p(x)` << 1, x^26688 mod p(x)` << 1 */ + {0x00000001dbc672be, 0x00000001a8da60c6}, + /* x^25600 mod p(x)` << 1, x^25664 mod p(x)` << 1 */ + {0x00000000b04d77f6, 0x000000013cf63820}, + /* x^24576 mod p(x)` << 1, x^24640 mod p(x)` << 1 */ + {0x0000000124400d96, 0x00000000bec12e1e}, + /* x^23552 mod p(x)` << 1, x^23616 mod p(x)` << 1 */ + {0x000000014ca4b414, 0x00000001c6368010}, + /* x^22528 mod p(x)` << 1, x^22592 mod p(x)` << 1 */ + {0x000000012fe2c938, 0x00000001e6e78758}, + /* x^21504 mod p(x)` << 1, x^21568 mod p(x)` << 1 */ + {0x00000001faed01e6, 0x000000008d7f2b3c}, + /* x^20480 mod p(x)` << 1, x^20544 mod p(x)` << 1 */ + {0x000000007e80ecfe, 0x000000016b4a156e}, + /* x^19456 mod p(x)` << 1, x^19520 mod p(x)` << 1 */ + {0x0000000098daee94, 0x00000001c63cfeb6}, + /* x^18432 mod p(x)` << 1, x^18496 mod p(x)` << 1 */ + {0x000000010a04edea, 0x000000015f902670}, + /* x^17408 mod p(x)` << 1, x^17472 mod p(x)` << 1 */ + {0x00000001c00b4524, 0x00000001cd5de11e}, + /* x^16384 mod p(x)` << 1, x^16448 mod p(x)` << 1 */ + {0x0000000170296550, 0x000000001acaec54}, + /* x^15360 mod p(x)` << 1, x^15424 mod p(x)` << 1 */ + {0x0000000181afaa48, 0x000000002bd0ca78}, + /* x^14336 mod p(x)` << 1, x^14400 mod p(x)` << 1 */ + {0x0000000185a31ffa, 0x0000000032d63d5c}, + /* x^13312 mod p(x)` << 1, x^13376 mod p(x)` << 1 */ + {0x000000002469f608, 0x000000001c6d4e4c}, + /* x^12288 mod p(x)` << 1, x^12352 mod p(x)` << 1 */ + {0x000000006980102a, 0x0000000106a60b92}, + /* x^11264 mod p(x)` << 1, x^11328 mod p(x)` << 1 */ + {0x0000000111ea9ca8, 0x00000000d3855e12}, + /* x^10240 mod p(x)` << 1, x^10304 mod p(x)` << 1 */ + {0x00000001bd1d29ce, 0x00000000e3125636}, + /* x^9216 mod p(x)` << 1, x^9280 mod p(x)` << 1 */ + {0x00000001b34b9580, 0x000000009e8f7ea4}, + /* x^8192 mod p(x)` << 1, x^8256 mod p(x)` << 1 */ + {0x000000003076054e, 0x00000001c82e562c}, + /* x^7168 mod p(x)` << 1, x^7232 mod p(x)` << 1 */ + {0x000000012a608ea4, 0x00000000ca9f09ce}, + /* x^6144 mod p(x)` << 1, x^6208 mod p(x)` << 1 */ + {0x00000000784d05fe, 0x00000000c63764e6}, + /* x^5120 mod p(x)` << 1, x^5184 mod p(x)` << 1 */ + {0x000000016ef0d82a, 0x0000000168d2e49e}, + /* x^4096 mod p(x)` << 1, x^4160 mod p(x)` << 1 */ + {0x0000000075bda454, 0x00000000e986c148}, + /* x^3072 mod p(x)` << 1, x^3136 mod p(x)` << 1 */ + {0x000000003dc0a1c4, 0x00000000cfb65894}, + /* x^2048 mod p(x)` << 1, x^2112 mod p(x)` << 1 */ + {0x00000000e9a5d8be, 0x0000000111cadee4}, + /* x^1024 mod p(x)` << 1, x^1088 mod p(x)` << 1 */ + {0x00000001609bc4b4, 0x0000000171fb63ce} +#else /* __LITTLE_ENDIAN__ */ + /* x^261120 mod p(x)` << 1, x^261184 mod p(x)` << 1 */ + {0x00000000b6ca9e20, 0x000000009c37c408}, + /* x^260096 mod p(x)` << 1, x^260160 mod p(x)` << 1 */ + {0x00000000350249a8, 0x00000001b51df26c}, + /* x^259072 mod p(x)` << 1, x^259136 mod p(x)` << 1 */ + {0x00000001862dac54, 0x000000000724b9d0}, + /* x^258048 mod p(x)` << 1, x^258112 mod p(x)` << 1 */ + {0x00000001d87fb48c, 0x00000001c00532fe}, + /* x^257024 mod p(x)` << 1, x^257088 mod p(x)` << 1 */ + {0x00000001f39b699e, 0x00000000f05a9362}, + /* x^256000 mod p(x)` << 1, x^256064 mod p(x)` << 1 */ + {0x0000000101da11b4, 0x00000001e1007970}, + /* x^254976 mod p(x)` << 1, x^255040 mod p(x)` << 1 */ + {0x00000001cab571e0, 0x00000000a57366ee}, + /* x^253952 mod p(x)` << 1, x^254016 mod p(x)` << 1 */ + {0x00000000c7020cfe, 0x0000000192011284}, + /* x^252928 mod p(x)` << 1, x^252992 mod p(x)` << 1 */ + {0x00000000cdaed1ae, 0x0000000162716d9a}, + /* x^251904 mod p(x)` << 1, x^251968 mod p(x)` << 1 */ + {0x00000001e804effc, 0x00000000cd97ecde}, + /* x^250880 mod p(x)` << 1, x^250944 mod p(x)` << 1 */ + {0x0000000077c3ea3a, 0x0000000058812bc0}, + /* x^249856 mod p(x)` << 1, x^249920 mod p(x)` << 1 */ + {0x0000000068df31b4, 0x0000000088b8c12e}, + /* x^248832 mod p(x)` << 1, x^248896 mod p(x)` << 1 */ + {0x00000000b059b6c2, 0x00000001230b234c}, + /* x^247808 mod p(x)` << 1, x^247872 mod p(x)` << 1 */ + {0x0000000145fb8ed8, 0x00000001120b416e}, + /* x^246784 mod p(x)` << 1, x^246848 mod p(x)` << 1 */ + {0x00000000cbc09168, 0x00000001974aecb0}, + /* x^245760 mod p(x)` << 1, x^245824 mod p(x)` << 1 */ + {0x000000005ceeedc2, 0x000000008ee3f226}, + /* x^244736 mod p(x)` << 1, x^244800 mod p(x)` << 1 */ + {0x0000000047d74e86, 0x00000001089aba9a}, + /* x^243712 mod p(x)` << 1, x^243776 mod p(x)` << 1 */ + {0x00000001407e9e22, 0x0000000065113872}, + /* x^242688 mod p(x)` << 1, x^242752 mod p(x)` << 1 */ + {0x00000001da967bda, 0x000000005c07ec10}, + /* x^241664 mod p(x)` << 1, x^241728 mod p(x)` << 1 */ + {0x000000006c898368, 0x0000000187590924}, + /* x^240640 mod p(x)` << 1, x^240704 mod p(x)` << 1 */ + {0x00000000f2d14c98, 0x00000000e35da7c6}, + /* x^239616 mod p(x)` << 1, x^239680 mod p(x)` << 1 */ + {0x00000001993c6ad4, 0x000000000415855a}, + /* x^238592 mod p(x)` << 1, x^238656 mod p(x)` << 1 */ + {0x000000014683d1ac, 0x0000000073617758}, + /* x^237568 mod p(x)` << 1, x^237632 mod p(x)` << 1 */ + {0x00000001a7c93e6c, 0x0000000176021d28}, + /* x^236544 mod p(x)` << 1, x^236608 mod p(x)` << 1 */ + {0x000000010211e90a, 0x00000001c358fd0a}, + /* x^235520 mod p(x)` << 1, x^235584 mod p(x)` << 1 */ + {0x000000001119403e, 0x00000001ff7a2c18}, + /* x^234496 mod p(x)` << 1, x^234560 mod p(x)` << 1 */ + {0x000000001c3261aa, 0x00000000f2d9f7e4}, + /* x^233472 mod p(x)` << 1, x^233536 mod p(x)` << 1 */ + {0x000000014e37a634, 0x000000016cf1f9c8}, + /* x^232448 mod p(x)` << 1, x^232512 mod p(x)` << 1 */ + {0x0000000073786c0c, 0x000000010af9279a}, + /* x^231424 mod p(x)` << 1, x^231488 mod p(x)` << 1 */ + {0x000000011dc037f8, 0x0000000004f101e8}, + /* x^230400 mod p(x)` << 1, x^230464 mod p(x)` << 1 */ + {0x0000000031433dfc, 0x0000000070bcf184}, + /* x^229376 mod p(x)` << 1, x^229440 mod p(x)` << 1 */ + {0x000000009cde8348, 0x000000000a8de642}, + /* x^228352 mod p(x)` << 1, x^228416 mod p(x)` << 1 */ + {0x0000000038d3c2a6, 0x0000000062ea130c}, + /* x^227328 mod p(x)` << 1, x^227392 mod p(x)` << 1 */ + {0x000000011b25f260, 0x00000001eb31cbb2}, + /* x^226304 mod p(x)` << 1, x^226368 mod p(x)` << 1 */ + {0x000000001629e6f0, 0x0000000170783448}, + /* x^225280 mod p(x)` << 1, x^225344 mod p(x)` << 1 */ + {0x0000000160838b4c, 0x00000001a684b4c6}, + /* x^224256 mod p(x)` << 1, x^224320 mod p(x)` << 1 */ + {0x000000007a44011c, 0x00000000253ca5b4}, + /* x^223232 mod p(x)` << 1, x^223296 mod p(x)` << 1 */ + {0x00000000226f417a, 0x0000000057b4b1e2}, + /* x^222208 mod p(x)` << 1, x^222272 mod p(x)` << 1 */ + {0x0000000045eb2eb4, 0x00000000b6bd084c}, + /* x^221184 mod p(x)` << 1, x^221248 mod p(x)` << 1 */ + {0x000000014459d70c, 0x0000000123c2d592}, + /* x^220160 mod p(x)` << 1, x^220224 mod p(x)` << 1 */ + {0x00000001d406ed82, 0x00000000159dafce}, + /* x^219136 mod p(x)` << 1, x^219200 mod p(x)` << 1 */ + {0x0000000160c8e1a8, 0x0000000127e1a64e}, + /* x^218112 mod p(x)` << 1, x^218176 mod p(x)` << 1 */ + {0x0000000027ba8098, 0x0000000056860754}, + /* x^217088 mod p(x)` << 1, x^217152 mod p(x)` << 1 */ + {0x000000006d92d018, 0x00000001e661aae8}, + /* x^216064 mod p(x)` << 1, x^216128 mod p(x)` << 1 */ + {0x000000012ed7e3f2, 0x00000000f82c6166}, + /* x^215040 mod p(x)` << 1, x^215104 mod p(x)` << 1 */ + {0x000000002dc87788, 0x00000000c4f9c7ae}, + /* x^214016 mod p(x)` << 1, x^214080 mod p(x)` << 1 */ + {0x0000000018240bb8, 0x0000000074203d20}, + /* x^212992 mod p(x)` << 1, x^213056 mod p(x)` << 1 */ + {0x000000001ad38158, 0x0000000198173052}, + /* x^211968 mod p(x)` << 1, x^212032 mod p(x)` << 1 */ + {0x00000001396b78f2, 0x00000001ce8aba54}, + /* x^210944 mod p(x)` << 1, x^211008 mod p(x)` << 1 */ + {0x000000011a681334, 0x00000001850d5d94}, + /* x^209920 mod p(x)` << 1, x^209984 mod p(x)` << 1 */ + {0x000000012104732e, 0x00000001d609239c}, + /* x^208896 mod p(x)` << 1, x^208960 mod p(x)` << 1 */ + {0x00000000a140d90c, 0x000000001595f048}, + /* x^207872 mod p(x)` << 1, x^207936 mod p(x)` << 1 */ + {0x00000001b7215eda, 0x0000000042ccee08}, + /* x^206848 mod p(x)` << 1, x^206912 mod p(x)` << 1 */ + {0x00000001aaf1df3c, 0x000000010a389d74}, + /* x^205824 mod p(x)` << 1, x^205888 mod p(x)` << 1 */ + {0x0000000029d15b8a, 0x000000012a840da6}, + /* x^204800 mod p(x)` << 1, x^204864 mod p(x)` << 1 */ + {0x00000000f1a96922, 0x000000001d181c0c}, + /* x^203776 mod p(x)` << 1, x^203840 mod p(x)` << 1 */ + {0x00000001ac80d03c, 0x0000000068b7d1f6}, + /* x^202752 mod p(x)` << 1, x^202816 mod p(x)` << 1 */ + {0x000000000f11d56a, 0x000000005b0f14fc}, + /* x^201728 mod p(x)` << 1, x^201792 mod p(x)` << 1 */ + {0x00000001f1c022a2, 0x0000000179e9e730}, + /* x^200704 mod p(x)` << 1, x^200768 mod p(x)` << 1 */ + {0x0000000173d00ae2, 0x00000001ce1368d6}, + /* x^199680 mod p(x)` << 1, x^199744 mod p(x)` << 1 */ + {0x00000001d4ffe4ac, 0x0000000112c3a84c}, + /* x^198656 mod p(x)` << 1, x^198720 mod p(x)` << 1 */ + {0x000000016edc5ae4, 0x00000000de940fee}, + /* x^197632 mod p(x)` << 1, x^197696 mod p(x)` << 1 */ + {0x00000001f1a02140, 0x00000000fe896b7e}, + /* x^196608 mod p(x)` << 1, x^196672 mod p(x)` << 1 */ + {0x00000000ca0b28a0, 0x00000001f797431c}, + /* x^195584 mod p(x)` << 1, x^195648 mod p(x)` << 1 */ + {0x00000001928e30a2, 0x0000000053e989ba}, + /* x^194560 mod p(x)` << 1, x^194624 mod p(x)` << 1 */ + {0x0000000097b1b002, 0x000000003920cd16}, + /* x^193536 mod p(x)` << 1, x^193600 mod p(x)` << 1 */ + {0x00000000b15bf906, 0x00000001e6f579b8}, + /* x^192512 mod p(x)` << 1, x^192576 mod p(x)` << 1 */ + {0x00000000411c5d52, 0x000000007493cb0a}, + /* x^191488 mod p(x)` << 1, x^191552 mod p(x)` << 1 */ + {0x00000001c36f3300, 0x00000001bdd376d8}, + /* x^190464 mod p(x)` << 1, x^190528 mod p(x)` << 1 */ + {0x00000001119227e0, 0x000000016badfee6}, + /* x^189440 mod p(x)` << 1, x^189504 mod p(x)` << 1 */ + {0x00000000114d4702, 0x0000000071de5c58}, + /* x^188416 mod p(x)` << 1, x^188480 mod p(x)` << 1 */ + {0x00000000458b5b98, 0x00000000453f317c}, + /* x^187392 mod p(x)` << 1, x^187456 mod p(x)` << 1 */ + {0x000000012e31fb8e, 0x0000000121675cce}, + /* x^186368 mod p(x)` << 1, x^186432 mod p(x)` << 1 */ + {0x000000005cf619d8, 0x00000001f409ee92}, + /* x^185344 mod p(x)` << 1, x^185408 mod p(x)` << 1 */ + {0x0000000063f4d8b2, 0x00000000f36b9c88}, + /* x^184320 mod p(x)` << 1, x^184384 mod p(x)` << 1 */ + {0x000000004138dc8a, 0x0000000036b398f4}, + /* x^183296 mod p(x)` << 1, x^183360 mod p(x)` << 1 */ + {0x00000001d29ee8e0, 0x00000001748f9adc}, + /* x^182272 mod p(x)` << 1, x^182336 mod p(x)` << 1 */ + {0x000000006a08ace8, 0x00000001be94ec00}, + /* x^181248 mod p(x)` << 1, x^181312 mod p(x)` << 1 */ + {0x0000000127d42010, 0x00000000b74370d6}, + /* x^180224 mod p(x)` << 1, x^180288 mod p(x)` << 1 */ + {0x0000000019d76b62, 0x00000001174d0b98}, + /* x^179200 mod p(x)` << 1, x^179264 mod p(x)` << 1 */ + {0x00000001b1471f6e, 0x00000000befc06a4}, + /* x^178176 mod p(x)` << 1, x^178240 mod p(x)` << 1 */ + {0x00000001f64c19cc, 0x00000001ae125288}, + /* x^177152 mod p(x)` << 1, x^177216 mod p(x)` << 1 */ + {0x00000000003c0ea0, 0x0000000095c19b34}, + /* x^176128 mod p(x)` << 1, x^176192 mod p(x)` << 1 */ + {0x000000014d73abf6, 0x00000001a78496f2}, + /* x^175104 mod p(x)` << 1, x^175168 mod p(x)` << 1 */ + {0x00000001620eb844, 0x00000001ac5390a0}, + /* x^174080 mod p(x)` << 1, x^174144 mod p(x)` << 1 */ + {0x0000000147655048, 0x000000002a80ed6e}, + /* x^173056 mod p(x)` << 1, x^173120 mod p(x)` << 1 */ + {0x0000000067b5077e, 0x00000001fa9b0128}, + /* x^172032 mod p(x)` << 1, x^172096 mod p(x)` << 1 */ + {0x0000000010ffe206, 0x00000001ea94929e}, + /* x^171008 mod p(x)` << 1, x^171072 mod p(x)` << 1 */ + {0x000000000fee8f1e, 0x0000000125f4305c}, + /* x^169984 mod p(x)` << 1, x^170048 mod p(x)` << 1 */ + {0x00000001da26fbae, 0x00000001471e2002}, + /* x^168960 mod p(x)` << 1, x^169024 mod p(x)` << 1 */ + {0x00000001b3a8bd88, 0x0000000132d2253a}, + /* x^167936 mod p(x)` << 1, x^168000 mod p(x)` << 1 */ + {0x00000000e8f3898e, 0x00000000f26b3592}, + /* x^166912 mod p(x)` << 1, x^166976 mod p(x)` << 1 */ + {0x00000000b0d0d28c, 0x00000000bc8b67b0}, + /* x^165888 mod p(x)` << 1, x^165952 mod p(x)` << 1 */ + {0x0000000030f2a798, 0x000000013a826ef2}, + /* x^164864 mod p(x)` << 1, x^164928 mod p(x)` << 1 */ + {0x000000000fba1002, 0x0000000081482c84}, + /* x^163840 mod p(x)` << 1, x^163904 mod p(x)` << 1 */ + {0x00000000bdb9bd72, 0x00000000e77307c2}, + /* x^162816 mod p(x)` << 1, x^162880 mod p(x)` << 1 */ + {0x0000000075d3bf5a, 0x00000000d4a07ec8}, + /* x^161792 mod p(x)` << 1, x^161856 mod p(x)` << 1 */ + {0x00000000ef1f98a0, 0x0000000017102100}, + /* x^160768 mod p(x)` << 1, x^160832 mod p(x)` << 1 */ + {0x00000000689c7602, 0x00000000db406486}, + /* x^159744 mod p(x)` << 1, x^159808 mod p(x)` << 1 */ + {0x000000016d5fa5fe, 0x0000000192db7f88}, + /* x^158720 mod p(x)` << 1, x^158784 mod p(x)` << 1 */ + {0x00000001d0d2b9ca, 0x000000018bf67b1e}, + /* x^157696 mod p(x)` << 1, x^157760 mod p(x)` << 1 */ + {0x0000000041e7b470, 0x000000007c09163e}, + /* x^156672 mod p(x)` << 1, x^156736 mod p(x)` << 1 */ + {0x00000001cbb6495e, 0x000000000adac060}, + /* x^155648 mod p(x)` << 1, x^155712 mod p(x)` << 1 */ + {0x000000010052a0b0, 0x00000000bd8316ae}, + /* x^154624 mod p(x)` << 1, x^154688 mod p(x)` << 1 */ + {0x00000001d8effb5c, 0x000000019f09ab54}, + /* x^153600 mod p(x)` << 1, x^153664 mod p(x)` << 1 */ + {0x00000001d969853c, 0x0000000125155542}, + /* x^152576 mod p(x)` << 1, x^152640 mod p(x)` << 1 */ + {0x00000000523ccce2, 0x000000018fdb5882}, + /* x^151552 mod p(x)` << 1, x^151616 mod p(x)` << 1 */ + {0x000000001e2436bc, 0x00000000e794b3f4}, + /* x^150528 mod p(x)` << 1, x^150592 mod p(x)` << 1 */ + {0x00000000ddd1c3a2, 0x000000016f9bb022}, + /* x^149504 mod p(x)` << 1, x^149568 mod p(x)` << 1 */ + {0x0000000019fcfe38, 0x00000000290c9978}, + /* x^148480 mod p(x)` << 1, x^148544 mod p(x)` << 1 */ + {0x00000001ce95db64, 0x0000000083c0f350}, + /* x^147456 mod p(x)` << 1, x^147520 mod p(x)` << 1 */ + {0x00000000af582806, 0x0000000173ea6628}, + /* x^146432 mod p(x)` << 1, x^146496 mod p(x)` << 1 */ + {0x00000001006388f6, 0x00000001c8b4e00a}, + /* x^145408 mod p(x)` << 1, x^145472 mod p(x)` << 1 */ + {0x0000000179eca00a, 0x00000000de95d6aa}, + /* x^144384 mod p(x)` << 1, x^144448 mod p(x)` << 1 */ + {0x0000000122410a6a, 0x000000010b7f7248}, + /* x^143360 mod p(x)` << 1, x^143424 mod p(x)` << 1 */ + {0x000000004288e87c, 0x00000001326e3a06}, + /* x^142336 mod p(x)` << 1, x^142400 mod p(x)` << 1 */ + {0x000000016c5490da, 0x00000000bb62c2e6}, + /* x^141312 mod p(x)` << 1, x^141376 mod p(x)` << 1 */ + {0x00000000d1c71f6e, 0x0000000156a4b2c2}, + /* x^140288 mod p(x)` << 1, x^140352 mod p(x)` << 1 */ + {0x00000001b4ce08a6, 0x000000011dfe763a}, + /* x^139264 mod p(x)` << 1, x^139328 mod p(x)` << 1 */ + {0x00000001466ba60c, 0x000000007bcca8e2}, + /* x^138240 mod p(x)` << 1, x^138304 mod p(x)` << 1 */ + {0x00000001f6c488a4, 0x0000000186118faa}, + /* x^137216 mod p(x)` << 1, x^137280 mod p(x)` << 1 */ + {0x000000013bfb0682, 0x0000000111a65a88}, + /* x^136192 mod p(x)` << 1, x^136256 mod p(x)` << 1 */ + {0x00000000690e9e54, 0x000000003565e1c4}, + /* x^135168 mod p(x)` << 1, x^135232 mod p(x)` << 1 */ + {0x00000000281346b6, 0x000000012ed02a82}, + /* x^134144 mod p(x)` << 1, x^134208 mod p(x)` << 1 */ + {0x0000000156464024, 0x00000000c486ecfc}, + /* x^133120 mod p(x)` << 1, x^133184 mod p(x)` << 1 */ + {0x000000016063a8dc, 0x0000000001b951b2}, + /* x^132096 mod p(x)` << 1, x^132160 mod p(x)` << 1 */ + {0x0000000116a66362, 0x0000000048143916}, + /* x^131072 mod p(x)` << 1, x^131136 mod p(x)` << 1 */ + {0x000000017e8aa4d2, 0x00000001dc2ae124}, + /* x^130048 mod p(x)` << 1, x^130112 mod p(x)` << 1 */ + {0x00000001728eb10c, 0x00000001416c58d6}, + /* x^129024 mod p(x)` << 1, x^129088 mod p(x)` << 1 */ + {0x00000001b08fd7fa, 0x00000000a479744a}, + /* x^128000 mod p(x)` << 1, x^128064 mod p(x)` << 1 */ + {0x00000001092a16e8, 0x0000000096ca3a26}, + /* x^126976 mod p(x)` << 1, x^127040 mod p(x)` << 1 */ + {0x00000000a505637c, 0x00000000ff223d4e}, + /* x^125952 mod p(x)` << 1, x^126016 mod p(x)` << 1 */ + {0x00000000d94869b2, 0x000000010e84da42}, + /* x^124928 mod p(x)` << 1, x^124992 mod p(x)` << 1 */ + {0x00000001c8b203ae, 0x00000001b61ba3d0}, + /* x^123904 mod p(x)` << 1, x^123968 mod p(x)` << 1 */ + {0x000000005704aea0, 0x00000000680f2de8}, + /* x^122880 mod p(x)` << 1, x^122944 mod p(x)` << 1 */ + {0x000000012e295fa2, 0x000000008772a9a8}, + /* x^121856 mod p(x)` << 1, x^121920 mod p(x)` << 1 */ + {0x000000011d0908bc, 0x0000000155f295bc}, + /* x^120832 mod p(x)` << 1, x^120896 mod p(x)` << 1 */ + {0x0000000193ed97ea, 0x00000000595f9282}, + /* x^119808 mod p(x)` << 1, x^119872 mod p(x)` << 1 */ + {0x000000013a0f1c52, 0x0000000164b1c25a}, + /* x^118784 mod p(x)` << 1, x^118848 mod p(x)` << 1 */ + {0x000000010c2c40c0, 0x00000000fbd67c50}, + /* x^117760 mod p(x)` << 1, x^117824 mod p(x)` << 1 */ + {0x00000000ff6fac3e, 0x0000000096076268}, + /* x^116736 mod p(x)` << 1, x^116800 mod p(x)` << 1 */ + {0x000000017b3609c0, 0x00000001d288e4cc}, + /* x^115712 mod p(x)` << 1, x^115776 mod p(x)` << 1 */ + {0x0000000088c8c922, 0x00000001eaac1bdc}, + /* x^114688 mod p(x)` << 1, x^114752 mod p(x)` << 1 */ + {0x00000001751baae6, 0x00000001f1ea39e2}, + /* x^113664 mod p(x)` << 1, x^113728 mod p(x)` << 1 */ + {0x0000000107952972, 0x00000001eb6506fc}, + /* x^112640 mod p(x)` << 1, x^112704 mod p(x)` << 1 */ + {0x0000000162b00abe, 0x000000010f806ffe}, + /* x^111616 mod p(x)` << 1, x^111680 mod p(x)` << 1 */ + {0x000000000d7b404c, 0x000000010408481e}, + /* x^110592 mod p(x)` << 1, x^110656 mod p(x)` << 1 */ + {0x00000000763b13d4, 0x0000000188260534}, + /* x^109568 mod p(x)` << 1, x^109632 mod p(x)` << 1 */ + {0x00000000f6dc22d8, 0x0000000058fc73e0}, + /* x^108544 mod p(x)` << 1, x^108608 mod p(x)` << 1 */ + {0x000000007daae060, 0x00000000391c59b8}, + /* x^107520 mod p(x)` << 1, x^107584 mod p(x)` << 1 */ + {0x000000013359ab7c, 0x000000018b638400}, + /* x^106496 mod p(x)` << 1, x^106560 mod p(x)` << 1 */ + {0x000000008add438a, 0x000000011738f5c4}, + /* x^105472 mod p(x)` << 1, x^105536 mod p(x)` << 1 */ + {0x00000001edbefdea, 0x000000008cf7c6da}, + /* x^104448 mod p(x)` << 1, x^104512 mod p(x)` << 1 */ + {0x000000004104e0f8, 0x00000001ef97fb16}, + /* x^103424 mod p(x)` << 1, x^103488 mod p(x)` << 1 */ + {0x00000000b48a8222, 0x0000000102130e20}, + /* x^102400 mod p(x)` << 1, x^102464 mod p(x)` << 1 */ + {0x00000001bcb46844, 0x00000000db968898}, + /* x^101376 mod p(x)` << 1, x^101440 mod p(x)` << 1 */ + {0x000000013293ce0a, 0x00000000b5047b5e}, + /* x^100352 mod p(x)` << 1, x^100416 mod p(x)` << 1 */ + {0x00000001710d0844, 0x000000010b90fdb2}, + /* x^99328 mod p(x)` << 1, x^99392 mod p(x)` << 1 */ + {0x0000000117907f6e, 0x000000004834a32e}, + /* x^98304 mod p(x)` << 1, x^98368 mod p(x)` << 1 */ + {0x0000000087ddf93e, 0x0000000059c8f2b0}, + /* x^97280 mod p(x)` << 1, x^97344 mod p(x)` << 1 */ + {0x000000005970e9b0, 0x0000000122cec508}, + /* x^96256 mod p(x)` << 1, x^96320 mod p(x)` << 1 */ + {0x0000000185b2b7d0, 0x000000000a330cda}, + /* x^95232 mod p(x)` << 1, x^95296 mod p(x)` << 1 */ + {0x00000001dcee0efc, 0x000000014a47148c}, + /* x^94208 mod p(x)` << 1, x^94272 mod p(x)` << 1 */ + {0x0000000030da2722, 0x0000000042c61cb8}, + /* x^93184 mod p(x)` << 1, x^93248 mod p(x)` << 1 */ + {0x000000012f925a18, 0x0000000012fe6960}, + /* x^92160 mod p(x)` << 1, x^92224 mod p(x)` << 1 */ + {0x00000000dd2e357c, 0x00000000dbda2c20}, + /* x^91136 mod p(x)` << 1, x^91200 mod p(x)` << 1 */ + {0x00000000071c80de, 0x000000011122410c}, + /* x^90112 mod p(x)` << 1, x^90176 mod p(x)` << 1 */ + {0x000000011513140a, 0x00000000977b2070}, + /* x^89088 mod p(x)` << 1, x^89152 mod p(x)` << 1 */ + {0x00000001df876e8e, 0x000000014050438e}, + /* x^88064 mod p(x)` << 1, x^88128 mod p(x)` << 1 */ + {0x000000015f81d6ce, 0x0000000147c840e8}, + /* x^87040 mod p(x)` << 1, x^87104 mod p(x)` << 1 */ + {0x000000019dd94dbe, 0x00000001cc7c88ce}, + /* x^86016 mod p(x)` << 1, x^86080 mod p(x)` << 1 */ + {0x00000001373d206e, 0x00000001476b35a4}, + /* x^84992 mod p(x)` << 1, x^85056 mod p(x)` << 1 */ + {0x00000000668ccade, 0x000000013d52d508}, + /* x^83968 mod p(x)` << 1, x^84032 mod p(x)` << 1 */ + {0x00000001b192d268, 0x000000008e4be32e}, + /* x^82944 mod p(x)` << 1, x^83008 mod p(x)` << 1 */ + {0x00000000e30f3a78, 0x00000000024120fe}, + /* x^81920 mod p(x)` << 1, x^81984 mod p(x)` << 1 */ + {0x000000010ef1f7bc, 0x00000000ddecddb4}, + /* x^80896 mod p(x)` << 1, x^80960 mod p(x)` << 1 */ + {0x00000001f5ac7380, 0x00000000d4d403bc}, + /* x^79872 mod p(x)` << 1, x^79936 mod p(x)` << 1 */ + {0x000000011822ea70, 0x00000001734b89aa}, + /* x^78848 mod p(x)` << 1, x^78912 mod p(x)` << 1 */ + {0x00000000c3a33848, 0x000000010e7a58d6}, + /* x^77824 mod p(x)` << 1, x^77888 mod p(x)` << 1 */ + {0x00000001bd151c24, 0x00000001f9f04e9c}, + /* x^76800 mod p(x)` << 1, x^76864 mod p(x)` << 1 */ + {0x0000000056002d76, 0x00000000b692225e}, + /* x^75776 mod p(x)` << 1, x^75840 mod p(x)` << 1 */ + {0x000000014657c4f4, 0x000000019b8d3f3e}, + /* x^74752 mod p(x)` << 1, x^74816 mod p(x)` << 1 */ + {0x0000000113742d7c, 0x00000001a874f11e}, + /* x^73728 mod p(x)` << 1, x^73792 mod p(x)` << 1 */ + {0x000000019c5920ba, 0x000000010d5a4254}, + /* x^72704 mod p(x)` << 1, x^72768 mod p(x)` << 1 */ + {0x000000005216d2d6, 0x00000000bbb2f5d6}, + /* x^71680 mod p(x)` << 1, x^71744 mod p(x)` << 1 */ + {0x0000000136f5ad8a, 0x0000000179cc0e36}, + /* x^70656 mod p(x)` << 1, x^70720 mod p(x)` << 1 */ + {0x000000018b07beb6, 0x00000001dca1da4a}, + /* x^69632 mod p(x)` << 1, x^69696 mod p(x)` << 1 */ + {0x00000000db1e93b0, 0x00000000feb1a192}, + /* x^68608 mod p(x)` << 1, x^68672 mod p(x)` << 1 */ + {0x000000000b96fa3a, 0x00000000d1eeedd6}, + /* x^67584 mod p(x)` << 1, x^67648 mod p(x)` << 1 */ + {0x00000001d9968af0, 0x000000008fad9bb4}, + /* x^66560 mod p(x)` << 1, x^66624 mod p(x)` << 1 */ + {0x000000000e4a77a2, 0x00000001884938e4}, + /* x^65536 mod p(x)` << 1, x^65600 mod p(x)` << 1 */ + {0x00000000508c2ac8, 0x00000001bc2e9bc0}, + /* x^64512 mod p(x)` << 1, x^64576 mod p(x)` << 1 */ + {0x0000000021572a80, 0x00000001f9658a68}, + /* x^63488 mod p(x)` << 1, x^63552 mod p(x)` << 1 */ + {0x00000001b859daf2, 0x000000001b9224fc}, + /* x^62464 mod p(x)` << 1, x^62528 mod p(x)` << 1 */ + {0x000000016f788474, 0x0000000055b2fb84}, + /* x^61440 mod p(x)` << 1, x^61504 mod p(x)` << 1 */ + {0x00000001b438810e, 0x000000018b090348}, + /* x^60416 mod p(x)` << 1, x^60480 mod p(x)` << 1 */ + {0x0000000095ddc6f2, 0x000000011ccbd5ea}, + /* x^59392 mod p(x)` << 1, x^59456 mod p(x)` << 1 */ + {0x00000001d977c20c, 0x0000000007ae47f8}, + /* x^58368 mod p(x)` << 1, x^58432 mod p(x)` << 1 */ + {0x00000000ebedb99a, 0x0000000172acbec0}, + /* x^57344 mod p(x)` << 1, x^57408 mod p(x)` << 1 */ + {0x00000001df9e9e92, 0x00000001c6e3ff20}, + /* x^56320 mod p(x)` << 1, x^56384 mod p(x)` << 1 */ + {0x00000001a4a3f952, 0x00000000e1b38744}, + /* x^55296 mod p(x)` << 1, x^55360 mod p(x)` << 1 */ + {0x00000000e2f51220, 0x00000000791585b2}, + /* x^54272 mod p(x)` << 1, x^54336 mod p(x)` << 1 */ + {0x000000004aa01f3e, 0x00000000ac53b894}, + /* x^53248 mod p(x)` << 1, x^53312 mod p(x)` << 1 */ + {0x00000000b3e90a58, 0x00000001ed5f2cf4}, + /* x^52224 mod p(x)` << 1, x^52288 mod p(x)` << 1 */ + {0x000000000c9ca2aa, 0x00000001df48b2e0}, + /* x^51200 mod p(x)` << 1, x^51264 mod p(x)` << 1 */ + {0x0000000151682316, 0x00000000049c1c62}, + /* x^50176 mod p(x)` << 1, x^50240 mod p(x)` << 1 */ + {0x0000000036fce78c, 0x000000017c460c12}, + /* x^49152 mod p(x)` << 1, x^49216 mod p(x)` << 1 */ + {0x000000009037dc10, 0x000000015be4da7e}, + /* x^48128 mod p(x)` << 1, x^48192 mod p(x)` << 1 */ + {0x00000000d3298582, 0x000000010f38f668}, + /* x^47104 mod p(x)` << 1, x^47168 mod p(x)` << 1 */ + {0x00000001b42e8ad6, 0x0000000039f40a00}, + /* x^46080 mod p(x)` << 1, x^46144 mod p(x)` << 1 */ + {0x00000000142a9838, 0x00000000bd4c10c4}, + /* x^45056 mod p(x)` << 1, x^45120 mod p(x)` << 1 */ + {0x0000000109c7f190, 0x0000000042db1d98}, + /* x^44032 mod p(x)` << 1, x^44096 mod p(x)` << 1 */ + {0x0000000056ff9310, 0x00000001c905bae6}, + /* x^43008 mod p(x)` << 1, x^43072 mod p(x)` << 1 */ + {0x00000001594513aa, 0x00000000069d40ea}, + /* x^41984 mod p(x)` << 1, x^42048 mod p(x)` << 1 */ + {0x00000001e3b5b1e8, 0x000000008e4fbad0}, + /* x^40960 mod p(x)` << 1, x^41024 mod p(x)` << 1 */ + {0x000000011dd5fc08, 0x0000000047bedd46}, + /* x^39936 mod p(x)` << 1, x^40000 mod p(x)` << 1 */ + {0x00000001675f0cc2, 0x0000000026396bf8}, + /* x^38912 mod p(x)` << 1, x^38976 mod p(x)` << 1 */ + {0x00000000d1c8dd44, 0x00000000379beb92}, + /* x^37888 mod p(x)` << 1, x^37952 mod p(x)` << 1 */ + {0x0000000115ebd3d8, 0x000000000abae54a}, + /* x^36864 mod p(x)` << 1, x^36928 mod p(x)` << 1 */ + {0x00000001ecbd0dac, 0x0000000007e6a128}, + /* x^35840 mod p(x)` << 1, x^35904 mod p(x)` << 1 */ + {0x00000000cdf67af2, 0x000000000ade29d2}, + /* x^34816 mod p(x)` << 1, x^34880 mod p(x)` << 1 */ + {0x000000004c01ff4c, 0x00000000f974c45c}, + /* x^33792 mod p(x)` << 1, x^33856 mod p(x)` << 1 */ + {0x00000000f2d8657e, 0x00000000e77ac60a}, + /* x^32768 mod p(x)` << 1, x^32832 mod p(x)` << 1 */ + {0x000000006bae74c4, 0x0000000145895816}, + /* x^31744 mod p(x)` << 1, x^31808 mod p(x)` << 1 */ + {0x0000000152af8aa0, 0x0000000038e362be}, + /* x^30720 mod p(x)` << 1, x^30784 mod p(x)` << 1 */ + {0x0000000004663802, 0x000000007f991a64}, + /* x^29696 mod p(x)` << 1, x^29760 mod p(x)` << 1 */ + {0x00000001ab2f5afc, 0x00000000fa366d3a}, + /* x^28672 mod p(x)` << 1, x^28736 mod p(x)` << 1 */ + {0x0000000074a4ebd4, 0x00000001a2bb34f0}, + /* x^27648 mod p(x)` << 1, x^27712 mod p(x)` << 1 */ + {0x00000001d7ab3a4c, 0x0000000028a9981e}, + /* x^26624 mod p(x)` << 1, x^26688 mod p(x)` << 1 */ + {0x00000001a8da60c6, 0x00000001dbc672be}, + /* x^25600 mod p(x)` << 1, x^25664 mod p(x)` << 1 */ + {0x000000013cf63820, 0x00000000b04d77f6}, + /* x^24576 mod p(x)` << 1, x^24640 mod p(x)` << 1 */ + {0x00000000bec12e1e, 0x0000000124400d96}, + /* x^23552 mod p(x)` << 1, x^23616 mod p(x)` << 1 */ + {0x00000001c6368010, 0x000000014ca4b414}, + /* x^22528 mod p(x)` << 1, x^22592 mod p(x)` << 1 */ + {0x00000001e6e78758, 0x000000012fe2c938}, + /* x^21504 mod p(x)` << 1, x^21568 mod p(x)` << 1 */ + {0x000000008d7f2b3c, 0x00000001faed01e6}, + /* x^20480 mod p(x)` << 1, x^20544 mod p(x)` << 1 */ + {0x000000016b4a156e, 0x000000007e80ecfe}, + /* x^19456 mod p(x)` << 1, x^19520 mod p(x)` << 1 */ + {0x00000001c63cfeb6, 0x0000000098daee94}, + /* x^18432 mod p(x)` << 1, x^18496 mod p(x)` << 1 */ + {0x000000015f902670, 0x000000010a04edea}, + /* x^17408 mod p(x)` << 1, x^17472 mod p(x)` << 1 */ + {0x00000001cd5de11e, 0x00000001c00b4524}, + /* x^16384 mod p(x)` << 1, x^16448 mod p(x)` << 1 */ + {0x000000001acaec54, 0x0000000170296550}, + /* x^15360 mod p(x)` << 1, x^15424 mod p(x)` << 1 */ + {0x000000002bd0ca78, 0x0000000181afaa48}, + /* x^14336 mod p(x)` << 1, x^14400 mod p(x)` << 1 */ + {0x0000000032d63d5c, 0x0000000185a31ffa}, + /* x^13312 mod p(x)` << 1, x^13376 mod p(x)` << 1 */ + {0x000000001c6d4e4c, 0x000000002469f608}, + /* x^12288 mod p(x)` << 1, x^12352 mod p(x)` << 1 */ + {0x0000000106a60b92, 0x000000006980102a}, + /* x^11264 mod p(x)` << 1, x^11328 mod p(x)` << 1 */ + {0x00000000d3855e12, 0x0000000111ea9ca8}, + /* x^10240 mod p(x)` << 1, x^10304 mod p(x)` << 1 */ + {0x00000000e3125636, 0x00000001bd1d29ce}, + /* x^9216 mod p(x)` << 1, x^9280 mod p(x)` << 1 */ + {0x000000009e8f7ea4, 0x00000001b34b9580}, + /* x^8192 mod p(x)` << 1, x^8256 mod p(x)` << 1 */ + {0x00000001c82e562c, 0x000000003076054e}, + /* x^7168 mod p(x)` << 1, x^7232 mod p(x)` << 1 */ + {0x00000000ca9f09ce, 0x000000012a608ea4}, + /* x^6144 mod p(x)` << 1, x^6208 mod p(x)` << 1 */ + {0x00000000c63764e6, 0x00000000784d05fe}, + /* x^5120 mod p(x)` << 1, x^5184 mod p(x)` << 1 */ + {0x0000000168d2e49e, 0x000000016ef0d82a}, + /* x^4096 mod p(x)` << 1, x^4160 mod p(x)` << 1 */ + {0x00000000e986c148, 0x0000000075bda454}, + /* x^3072 mod p(x)` << 1, x^3136 mod p(x)` << 1 */ + {0x00000000cfb65894, 0x000000003dc0a1c4}, + /* x^2048 mod p(x)` << 1, x^2112 mod p(x)` << 1 */ + {0x0000000111cadee4, 0x00000000e9a5d8be}, + /* x^1024 mod p(x)` << 1, x^1088 mod p(x)` << 1 */ + {0x0000000171fb63ce, 0x00000001609bc4b4} +#endif /* __LITTLE_ENDIAN__ */ +}; - /* x^288 mod p(x)`, x^320 mod p(x)`, x^352 mod p(x)`, x^384 mod p(x)` */ - .octa 0x9c25531d19e65ddeec1631edb2dea967 +/* Reduce final 1024-2048 bits to 64 bits, shifting 32 bits to include the trailing 32 bits of zeros + */ + +static const __vector unsigned long long vcrc_short_const[16] __attribute__((aligned(16))) = { +#ifdef __LITTLE_ENDIAN__ + /* x^1952 mod p(x) , x^1984 mod p(x) , x^2016 mod p(x) , x^2048 mod p(x) */ + {0x5cf015c388e56f72, 0x7fec2963e5bf8048}, + /* x^1824 mod p(x) , x^1856 mod p(x) , x^1888 mod p(x) , x^1920 mod p(x) */ + {0x963a18920246e2e6, 0x38e888d4844752a9}, + /* x^1696 mod p(x) , x^1728 mod p(x) , x^1760 mod p(x) , x^1792 mod p(x) */ + {0x419a441956993a31, 0x42316c00730206ad}, + /* x^1568 mod p(x) , x^1600 mod p(x) , x^1632 mod p(x) , x^1664 mod p(x) */ + {0x924752ba2b830011, 0x543d5c543e65ddf9}, + /* x^1440 mod p(x) , x^1472 mod p(x) , x^1504 mod p(x) , x^1536 mod p(x) */ + {0x55bd7f9518e4a304, 0x78e87aaf56767c92}, + /* x^1312 mod p(x) , x^1344 mod p(x) , x^1376 mod p(x) , x^1408 mod p(x) */ + {0x6d76739fe0553f1e, 0x8f68fcec1903da7f}, + /* x^1184 mod p(x) , x^1216 mod p(x) , x^1248 mod p(x) , x^1280 mod p(x) */ + {0xc133722b1fe0b5c3, 0x3f4840246791d588}, + /* x^1056 mod p(x) , x^1088 mod p(x) , x^1120 mod p(x) , x^1152 mod p(x) */ + {0x64b67ee0e55ef1f3, 0x34c96751b04de25a}, + /* x^928 mod p(x) , x^960 mod p(x) , x^992 mod p(x) , x^1024 mod p(x) */ + {0x069db049b8fdb1e7, 0x156c8e180b4a395b}, + /* x^800 mod p(x) , x^832 mod p(x) , x^864 mod p(x) , x^896 mod p(x) */ + {0xa11bfaf3c9e90b9e, 0xe0b99ccbe661f7be}, + /* x^672 mod p(x) , x^704 mod p(x) , x^736 mod p(x) , x^768 mod p(x) */ + {0x817cdc5119b29a35, 0x041d37768cd75659}, + /* x^544 mod p(x) , x^576 mod p(x) , x^608 mod p(x) , x^640 mod p(x) */ + {0x1ce9d94b36c41f1c, 0x3a0777818cfaa965}, + /* x^416 mod p(x) , x^448 mod p(x) , x^480 mod p(x) , x^512 mod p(x) */ + {0x4f256efcb82be955, 0x0e148e8252377a55}, + /* x^288 mod p(x) , x^320 mod p(x) , x^352 mod p(x) , x^384 mod p(x) */ + {0xec1631edb2dea967, 0x9c25531d19e65dde}, + /* x^160 mod p(x) , x^192 mod p(x) , x^224 mod p(x) , x^256 mod p(x) */ + {0x5d27e147510ac59a, 0x790606ff9957c0a6}, + /* x^32 mod p(x) , x^64 mod p(x) , x^96 mod p(x) , x^128 mod p(x) */ + {0xa66805eb18b8ea18, 0x82f63b786ea2d55c} +#else /* __LITTLE_ENDIAN__ */ + /* x^1952 mod p(x) , x^1984 mod p(x) , x^2016 mod p(x) , x^2048 mod p(x) */ + {0x7fec2963e5bf8048, 0x5cf015c388e56f72}, + /* x^1824 mod p(x) , x^1856 mod p(x) , x^1888 mod p(x) , x^1920 mod p(x) */ + {0x38e888d4844752a9, 0x963a18920246e2e6}, + /* x^1696 mod p(x) , x^1728 mod p(x) , x^1760 mod p(x) , x^1792 mod p(x) */ + {0x42316c00730206ad, 0x419a441956993a31}, + /* x^1568 mod p(x) , x^1600 mod p(x) , x^1632 mod p(x) , x^1664 mod p(x) */ + {0x543d5c543e65ddf9, 0x924752ba2b830011}, + /* x^1440 mod p(x) , x^1472 mod p(x) , x^1504 mod p(x) , x^1536 mod p(x) */ + {0x78e87aaf56767c92, 0x55bd7f9518e4a304}, + /* x^1312 mod p(x) , x^1344 mod p(x) , x^1376 mod p(x) , x^1408 mod p(x) */ + {0x8f68fcec1903da7f, 0x6d76739fe0553f1e}, + /* x^1184 mod p(x) , x^1216 mod p(x) , x^1248 mod p(x) , x^1280 mod p(x) */ + {0x3f4840246791d588, 0xc133722b1fe0b5c3}, + /* x^1056 mod p(x) , x^1088 mod p(x) , x^1120 mod p(x) , x^1152 mod p(x) */ + {0x34c96751b04de25a, 0x64b67ee0e55ef1f3}, + /* x^928 mod p(x) , x^960 mod p(x) , x^992 mod p(x) , x^1024 mod p(x) */ + {0x156c8e180b4a395b, 0x069db049b8fdb1e7}, + /* x^800 mod p(x) , x^832 mod p(x) , x^864 mod p(x) , x^896 mod p(x) */ + {0xe0b99ccbe661f7be, 0xa11bfaf3c9e90b9e}, + /* x^672 mod p(x) , x^704 mod p(x) , x^736 mod p(x) , x^768 mod p(x) */ + {0x041d37768cd75659, 0x817cdc5119b29a35}, + /* x^544 mod p(x) , x^576 mod p(x) , x^608 mod p(x) , x^640 mod p(x) */ + {0x3a0777818cfaa965, 0x1ce9d94b36c41f1c}, + /* x^416 mod p(x) , x^448 mod p(x) , x^480 mod p(x) , x^512 mod p(x) */ + {0x0e148e8252377a55, 0x4f256efcb82be955}, + /* x^288 mod p(x) , x^320 mod p(x) , x^352 mod p(x) , x^384 mod p(x) */ + {0x9c25531d19e65dde, 0xec1631edb2dea967}, + /* x^160 mod p(x) , x^192 mod p(x) , x^224 mod p(x) , x^256 mod p(x) */ + {0x790606ff9957c0a6, 0x5d27e147510ac59a}, + /* x^32 mod p(x) , x^64 mod p(x) , x^96 mod p(x) , x^128 mod p(x) */ + {0x82f63b786ea2d55c, 0xa66805eb18b8ea18} +#endif /* __LITTLE_ENDIAN__ */ +}; - /* x^160 mod p(x)`, x^192 mod p(x)`, x^224 mod p(x)`, x^256 mod p(x)` */ - .octa 0x790606ff9957c0a65d27e147510ac59a +/* Barrett constants */ +/* 33 bit reflected Barrett constant m - (4^32)/n */ - /* x^32 mod p(x)`, x^64 mod p(x)`, x^96 mod p(x)`, x^128 mod p(x)` */ - .octa 0x82f63b786ea2d55ca66805eb18b8ea18 +static const __vector unsigned long long v_Barrett_const[2] __attribute__((aligned(16))) = { +/* x^64 div p(x) */ +#ifdef __LITTLE_ENDIAN__ + {0x00000000dea713f1, 0x0000000000000000}, {0x0000000105ec76f1, 0x0000000000000000} +#else /* __LITTLE_ENDIAN__ */ + {0x0000000000000000, 0x00000000dea713f1}, {0x0000000000000000, 0x0000000105ec76f1} +#endif /* __LITTLE_ENDIAN__ */ +}; +#endif /* POWER8_INTRINSICS */ - .barrett_constants : - /* 33 bit reflected Barrett constant m - (4^32)/n */ - .octa 0x000000000000000000000000dea713f1 /* x^64 div p(x)` */ - /* 33 bit reflected Barrett constant n */ - .octa 0x00000000000000000000000105ec76f1 -#endif +#endif /* __ASSEMBLER__ */ diff --git a/src/third_party/wiredtiger/src/checksum/power8/crc32_wrapper.c b/src/third_party/wiredtiger/src/checksum/power8/crc32_wrapper.c index c8fbaba0886..60537c735d7 100644 --- a/src/third_party/wiredtiger/src/checksum/power8/crc32_wrapper.c +++ b/src/third_party/wiredtiger/src/checksum/power8/crc32_wrapper.c @@ -3,78 +3,10 @@ #include <stddef.h> #if defined(__powerpc64__) && !defined(HAVE_NO_CRC32_HARDWARE) -#define CRC_TABLE -#include "crc32_constants.h" -#define VMX_ALIGN 16U -#define VMX_ALIGN_MASK (VMX_ALIGN - 1) - -/* - * crc32_align -- - * Align helper for CRC32 functions. - */ -static unsigned int -crc32_align(unsigned int crc, const unsigned char *p, unsigned long len) -{ -#ifdef REFLECT - while (len--) - crc = crc_table[(crc ^ *p++) & 0xff] ^ (crc >> 8); - return crc; -#else - while (len--) - crc = crc_table[((crc >> 24) ^ *p++) & 0xff] ^ (crc << 8); - return crc; -#endif -} - -unsigned int __crc32_vpmsum(unsigned int crc, const unsigned char *p, unsigned long len); - -/* -Werror=missing-prototypes */ unsigned int crc32_vpmsum(unsigned int crc, const unsigned char *p, unsigned long len); /* - * crc32_vpmsum -- - * VPM sum helper for CRC32 functions. - */ -unsigned int -crc32_vpmsum(unsigned int crc, const unsigned char *p, unsigned long len) -{ - unsigned int prealign; - unsigned int tail; - -#ifdef CRC_XOR - crc ^= 0xffffffff; -#endif - - if (len < VMX_ALIGN + VMX_ALIGN_MASK) { - crc = crc32_align(crc, p, len); - goto out; - } - - if ((unsigned long)p & VMX_ALIGN_MASK) { - prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK); - crc = crc32_align(crc, p, prealign); - len -= prealign; - p += prealign; - } - - crc = __crc32_vpmsum(crc, p, len & ~VMX_ALIGN_MASK); - - tail = len & VMX_ALIGN_MASK; - if (tail) { - p += len & ~VMX_ALIGN_MASK; - crc = crc32_align(crc, p, tail); - } - -out: -#ifdef CRC_XOR - crc ^= 0xffffffff; -#endif - - return crc; -} - -/* * __wt_checksum_hw -- * WiredTiger: return a checksum for a chunk of memory. */ diff --git a/src/third_party/wiredtiger/src/checksum/power8/ppc-opcode.h b/src/third_party/wiredtiger/src/checksum/power8/ppc-opcode.h deleted file mode 100644 index 0e5a189dc9d..00000000000 --- a/src/third_party/wiredtiger/src/checksum/power8/ppc-opcode.h +++ /dev/null @@ -1,23 +0,0 @@ -#ifndef __OPCODES_H -#define __OPCODES_H - -#define __PPC_RA(a) (((a)&0x1f) << 16) -#define __PPC_RB(b) (((b)&0x1f) << 11) -#define __PPC_XA(a) ((((a)&0x1f) << 16) | (((a)&0x20) >> 3)) -#define __PPC_XB(b) ((((b)&0x1f) << 11) | (((b)&0x20) >> 4)) -#define __PPC_XS(s) ((((s)&0x1f) << 21) | (((s)&0x20) >> 5)) -#define __PPC_XT(s) __PPC_XS(s) -#define VSX_XX3(t, a, b) (__PPC_XT(t) | __PPC_XA(a) | __PPC_XB(b)) -#define VSX_XX1(s, a, b) (__PPC_XS(s) | __PPC_RA(a) | __PPC_RB(b)) - -#define PPC_INST_VPMSUMW 0x10000488 -#define PPC_INST_VPMSUMD 0x100004c8 -#define PPC_INST_MFVSRD 0x7c000066 -#define PPC_INST_MTVSRD 0x7c000166 - -#define VPMSUMW(t, a, b) .long PPC_INST_VPMSUMW | VSX_XX3((t), a, b) -#define VPMSUMD(t, a, b) .long PPC_INST_VPMSUMD | VSX_XX3((t), a, b) -#define MFVRD(a, t) .long PPC_INST_MFVSRD | VSX_XX1((t) + 32, a, 0) -#define MTVRD(t, a) .long PPC_INST_MTVSRD | VSX_XX1((t) + 32, a, 0) - -#endif diff --git a/src/third_party/wiredtiger/src/checksum/power8/vec_crc32.c b/src/third_party/wiredtiger/src/checksum/power8/vec_crc32.c new file mode 100644 index 00000000000..4356d505007 --- /dev/null +++ b/src/third_party/wiredtiger/src/checksum/power8/vec_crc32.c @@ -0,0 +1,672 @@ +#include <wiredtiger_config.h> +#if defined(__powerpc64__) && !defined(HAVE_NO_CRC32_HARDWARE) +/* + * Calculate the checksum of data that is 16 byte aligned and a multiple of + * 16 bytes. + * + * The first step is to reduce it to 1024 bits. We do this in 8 parallel + * chunks in order to mask the latency of the vpmsum instructions. If we + * have more than 32 kB of data to checksum we repeat this step multiple + * times, passing in the previous 1024 bits. + * + * The next step is to reduce the 1024 bits to 64 bits. This step adds + * 32 bits of 0s to the end - this matches what a CRC does. We just + * calculate constants that land the data in this 32 bits. + * + * We then use fixed point Barrett reduction to compute a mod n over GF(2) + * for n = CRC using POWER8 instructions. We use x = 32. + * + * http://en.wikipedia.org/wiki/Barrett_reduction + * + * This code uses gcc vector builtins instead using assembly directly. + * + * Copyright (C) 2017 Rogerio Alves <rogealve@br.ibm.com>, IBM + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of either: + * + * a) the GNU General Public License as published by the Free Software + * Foundation; either version 2 of the License, or (at your option) + * any later version, or + * b) the Apache License, Version 2.0 + */ + +#include <altivec.h> + +#define POWER8_INTRINSICS +#define CRC_TABLE + +#include "crc32_constants.h" + +#define VMX_ALIGN 16UL +#define VMX_ALIGN_MASK (VMX_ALIGN - 1) + +#ifdef REFLECT +/* + * crc32_align -- + * Align helper for CRC32 functions. + */ +static unsigned int +crc32_align(unsigned int crc, const unsigned char *p, unsigned long len) +{ + while (len--) + crc = crc_table[(crc ^ *p++) & 0xff] ^ (crc >> 8); + return crc; +} +#else +/* + * crc32_align -- + * Align helper for CRC32 functions. + */ +static unsigned int +crc32_align(unsigned int crc, const unsigned char *p, unsigned long len) +{ + while (len--) + crc = crc_table[((crc >> 24) ^ *p++) & 0xff] ^ (crc << 8); + return crc; +} +#endif + +static unsigned int __attribute__((aligned(32))) +__crc32_vpmsum(unsigned int crc, const void *p, unsigned long len); + +/* -Werror=missing-prototypes */ +unsigned int crc32_vpmsum(unsigned int crc, const unsigned char *p, unsigned long len); + +/* + * crc32_vpmsum -- + * VPM sum helper for CRC32 functions. + */ +unsigned int +crc32_vpmsum(unsigned int crc, const unsigned char *p, unsigned long len) +{ + unsigned int prealign; + unsigned int tail; + +#ifdef CRC_XOR + crc ^= 0xffffffff; +#endif + + if (len < VMX_ALIGN + VMX_ALIGN_MASK) { + crc = crc32_align(crc, p, len); + goto out; + } + + if ((unsigned long)p & VMX_ALIGN_MASK) { + prealign = VMX_ALIGN - ((unsigned long)p & VMX_ALIGN_MASK); + crc = crc32_align(crc, p, prealign); + len -= prealign; + p += prealign; + } + + crc = __crc32_vpmsum(crc, p, len & ~VMX_ALIGN_MASK); + + tail = len & VMX_ALIGN_MASK; + if (tail) { + p += len & ~VMX_ALIGN_MASK; + crc = crc32_align(crc, p, tail); + } + +out: +#ifdef CRC_XOR + crc ^= 0xffffffff; +#endif + + return crc; +} + +#if defined(__clang__) +#include "clang_workaround.h" +#else +#define __builtin_pack_vector(a, b) __builtin_pack_vector_int128((a), (b)) +#define __builtin_unpack_vector_0(a) __builtin_unpack_vector_int128((vector __int128_t)(a), 0) +#ifndef REFLECT +#define __builtin_unpack_vector_1(a) __builtin_unpack_vector_int128((vector __int128_t)(a), 1) +#endif +#endif + +/* When we have a load-store in a single-dispatch group and address overlap + * such that foward is not allowed (load-hit-store) the group must be flushed. + * A group ending NOP prevents the flush. + */ +#define GROUP_ENDING_NOP __asm__("ori 2,2,0" ::: "memory") + +#if defined(__BIG_ENDIAN__) && defined(REFLECT) +#define BYTESWAP_DATA +#elif defined(__LITTLE_ENDIAN__) && !defined(REFLECT) +#define BYTESWAP_DATA +#endif + +#ifdef BYTESWAP_DATA +#define VEC_PERM(vr, va, vb, vc) vr = vec_perm(va, vb, (__vector unsigned char)vc) +#if defined(__LITTLE_ENDIAN__) +/* Byte reverse permute constant LE. */ +static const __vector unsigned long long vperm_const + __attribute__((aligned(16))) = {0x08090A0B0C0D0E0FUL, 0x0001020304050607UL}; +#else +static const __vector unsigned long long vperm_const + __attribute__((aligned(16))) = {0x0F0E0D0C0B0A0908UL, 0X0706050403020100UL}; +#endif +#else +#define VEC_PERM(vr, va, vb, vc) +#endif + +static unsigned int __attribute__((aligned(32))) +__crc32_vpmsum(unsigned int crc, const void *p, unsigned long len) +{ + + const __vector unsigned long long vzero = {0, 0}; + const __vector unsigned long long vones = {0xffffffffffffffffUL, 0xffffffffffffffffUL}; + +#ifdef REFLECT + const __vector unsigned long long vmask_32bit = (__vector unsigned long long)vec_sld( + (__vector unsigned char)vzero, (__vector unsigned char)vones, 4); +#endif + + const __vector unsigned long long vmask_64bit = (__vector unsigned long long)vec_sld( + (__vector unsigned char)vzero, (__vector unsigned char)vones, 8); + + __vector unsigned long long vcrc; + + __vector unsigned long long vconst1, vconst2; + + /* vdata0-vdata7 will contain our data (p). */ + __vector unsigned long long vdata0, vdata1, vdata2, vdata3, vdata4, vdata5, vdata6, vdata7; + + /* v0-v7 will contain our checksums */ + __vector unsigned long long v0 = {0, 0}; + __vector unsigned long long v1 = {0, 0}; + __vector unsigned long long v2 = {0, 0}; + __vector unsigned long long v3 = {0, 0}; + __vector unsigned long long v4 = {0, 0}; + __vector unsigned long long v5 = {0, 0}; + __vector unsigned long long v6 = {0, 0}; + __vector unsigned long long v7 = {0, 0}; + + /* Vector auxiliary variables. */ + __vector unsigned long long va0, va1, va2, va3, va4, va5, va6, va7; + + unsigned int result = 0; + unsigned int offset; /* Constant table offset. */ + + unsigned long i; /* Counter. */ + unsigned long chunks; + + unsigned long block_size; + int next_block = 0; + + /* Align by 128 bits. The last 128 bit block will be processed at end. */ + unsigned long length = len & 0xFFFFFFFFFFFFFF80UL; +#ifdef REFLECT + __vector unsigned char vsht_splat; +#endif + +#ifdef REFLECT + vcrc = (__vector unsigned long long)__builtin_pack_vector(0UL, crc); +#else + vcrc = (__vector unsigned long long)__builtin_pack_vector(crc, 0UL); + + /* Shift into top 32 bits */ + vcrc = (__vector unsigned long long)vec_sld( + (__vector unsigned char)vcrc, (__vector unsigned char)vzero, 4); +#endif + + /* Short version. */ + if (len < 256) { + /* Calculate where in the constant table we need to start. */ + offset = 256 - len; + + vconst1 = vec_ld(offset, vcrc_short_const); + vdata0 = vec_ld(0, (__vector unsigned long long *)p); + VEC_PERM(vdata0, vdata0, vconst1, vperm_const); + + /* xor initial value*/ + vdata0 = vec_xor(vdata0, vcrc); + + vdata0 = (__vector unsigned long long)__builtin_crypto_vpmsumw( + (__vector unsigned int)vdata0, (__vector unsigned int)vconst1); + v0 = vec_xor(v0, vdata0); + + for (i = 16; i < len; i += 16) { + vconst1 = vec_ld(offset + i, vcrc_short_const); + vdata0 = vec_ld(i, (__vector unsigned long long *)p); + VEC_PERM(vdata0, vdata0, vconst1, vperm_const); + vdata0 = (__vector unsigned long long)__builtin_crypto_vpmsumw( + (__vector unsigned int)vdata0, (__vector unsigned int)vconst1); + v0 = vec_xor(v0, vdata0); + } + } else { + + /* Load initial values. */ + vdata0 = vec_ld(0, (__vector unsigned long long *)p); + vdata1 = vec_ld(16, (__vector unsigned long long *)p); + + VEC_PERM(vdata0, vdata0, vdata0, vperm_const); + VEC_PERM(vdata1, vdata1, vdata1, vperm_const); + + vdata2 = vec_ld(32, (__vector unsigned long long *)p); + vdata3 = vec_ld(48, (__vector unsigned long long *)p); + + VEC_PERM(vdata2, vdata2, vdata2, vperm_const); + VEC_PERM(vdata3, vdata3, vdata3, vperm_const); + + vdata4 = vec_ld(64, (__vector unsigned long long *)p); + vdata5 = vec_ld(80, (__vector unsigned long long *)p); + + VEC_PERM(vdata4, vdata4, vdata4, vperm_const); + VEC_PERM(vdata5, vdata5, vdata5, vperm_const); + + vdata6 = vec_ld(96, (__vector unsigned long long *)p); + vdata7 = vec_ld(112, (__vector unsigned long long *)p); + + VEC_PERM(vdata6, vdata6, vdata6, vperm_const); + VEC_PERM(vdata7, vdata7, vdata7, vperm_const); + + /* xor in initial value */ + vdata0 = vec_xor(vdata0, vcrc); + + p = (char *)p + 128; + + do { + /* Checksum in blocks of MAX_SIZE. */ + block_size = length; + if (block_size > MAX_SIZE) { + block_size = MAX_SIZE; + } + + length = length - block_size; + + /* + * Work out the offset into the constants table to start at. Each constant is 16 bytes, + * and it is used against 128 bytes of input data - 128 / 16 = 8 + */ + offset = (MAX_SIZE / 8) - (block_size / 8); + /* We reduce our final 128 bytes in a separate step */ + chunks = (block_size / 128) - 1; + + vconst1 = vec_ld(offset, vcrc_const); + + va0 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata0, (__vector unsigned long long)vconst1); + va1 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata1, (__vector unsigned long long)vconst1); + va2 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata2, (__vector unsigned long long)vconst1); + va3 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata3, (__vector unsigned long long)vconst1); + va4 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata4, (__vector unsigned long long)vconst1); + va5 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata5, (__vector unsigned long long)vconst1); + va6 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata6, (__vector unsigned long long)vconst1); + va7 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata7, (__vector unsigned long long)vconst1); + + if (chunks > 1) { + offset += 16; + vconst2 = vec_ld(offset, vcrc_const); + GROUP_ENDING_NOP; + + vdata0 = vec_ld(0, (__vector unsigned long long *)p); + VEC_PERM(vdata0, vdata0, vdata0, vperm_const); + + vdata1 = vec_ld(16, (__vector unsigned long long *)p); + VEC_PERM(vdata1, vdata1, vdata1, vperm_const); + + vdata2 = vec_ld(32, (__vector unsigned long long *)p); + VEC_PERM(vdata2, vdata2, vdata2, vperm_const); + + vdata3 = vec_ld(48, (__vector unsigned long long *)p); + VEC_PERM(vdata3, vdata3, vdata3, vperm_const); + + vdata4 = vec_ld(64, (__vector unsigned long long *)p); + VEC_PERM(vdata4, vdata4, vdata4, vperm_const); + + vdata5 = vec_ld(80, (__vector unsigned long long *)p); + VEC_PERM(vdata5, vdata5, vdata5, vperm_const); + + vdata6 = vec_ld(96, (__vector unsigned long long *)p); + VEC_PERM(vdata6, vdata6, vdata6, vperm_const); + + vdata7 = vec_ld(112, (__vector unsigned long long *)p); + VEC_PERM(vdata7, vdata7, vdata7, vperm_const); + + p = (char *)p + 128; + + /* + * main loop. We modulo schedule it such that it takes three iterations to complete + * - first iteration load, second iteration vpmsum, third iteration xor. + */ + for (i = 0; i < chunks - 2; i++) { + vconst1 = vec_ld(offset, vcrc_const); + offset += 16; + GROUP_ENDING_NOP; + + v0 = vec_xor(v0, va0); + va0 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata0, (__vector unsigned long long)vconst2); + vdata0 = vec_ld(0, (__vector unsigned long long *)p); + VEC_PERM(vdata0, vdata0, vdata0, vperm_const); + GROUP_ENDING_NOP; + + v1 = vec_xor(v1, va1); + va1 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata1, (__vector unsigned long long)vconst2); + vdata1 = vec_ld(16, (__vector unsigned long long *)p); + VEC_PERM(vdata1, vdata1, vdata1, vperm_const); + GROUP_ENDING_NOP; + + v2 = vec_xor(v2, va2); + va2 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata2, (__vector unsigned long long)vconst2); + vdata2 = vec_ld(32, (__vector unsigned long long *)p); + VEC_PERM(vdata2, vdata2, vdata2, vperm_const); + GROUP_ENDING_NOP; + + v3 = vec_xor(v3, va3); + va3 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata3, (__vector unsigned long long)vconst2); + vdata3 = vec_ld(48, (__vector unsigned long long *)p); + VEC_PERM(vdata3, vdata3, vdata3, vperm_const); + + vconst2 = vec_ld(offset, vcrc_const); + GROUP_ENDING_NOP; + + v4 = vec_xor(v4, va4); + va4 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata4, (__vector unsigned long long)vconst1); + vdata4 = vec_ld(64, (__vector unsigned long long *)p); + VEC_PERM(vdata4, vdata4, vdata4, vperm_const); + GROUP_ENDING_NOP; + + v5 = vec_xor(v5, va5); + va5 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata5, (__vector unsigned long long)vconst1); + vdata5 = vec_ld(80, (__vector unsigned long long *)p); + VEC_PERM(vdata5, vdata5, vdata5, vperm_const); + GROUP_ENDING_NOP; + + v6 = vec_xor(v6, va6); + va6 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata6, (__vector unsigned long long)vconst1); + vdata6 = vec_ld(96, (__vector unsigned long long *)p); + VEC_PERM(vdata6, vdata6, vdata6, vperm_const); + GROUP_ENDING_NOP; + + v7 = vec_xor(v7, va7); + va7 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata7, (__vector unsigned long long)vconst1); + vdata7 = vec_ld(112, (__vector unsigned long long *)p); + VEC_PERM(vdata7, vdata7, vdata7, vperm_const); + + p = (char *)p + 128; + } + + /* First cool down*/ + vconst1 = vec_ld(offset, vcrc_const); + offset += 16; + + v0 = vec_xor(v0, va0); + va0 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata0, (__vector unsigned long long)vconst1); + GROUP_ENDING_NOP; + + v1 = vec_xor(v1, va1); + va1 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata1, (__vector unsigned long long)vconst1); + GROUP_ENDING_NOP; + + v2 = vec_xor(v2, va2); + va2 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata2, (__vector unsigned long long)vconst1); + GROUP_ENDING_NOP; + + v3 = vec_xor(v3, va3); + va3 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata3, (__vector unsigned long long)vconst1); + GROUP_ENDING_NOP; + + v4 = vec_xor(v4, va4); + va4 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata4, (__vector unsigned long long)vconst1); + GROUP_ENDING_NOP; + + v5 = vec_xor(v5, va5); + va5 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata5, (__vector unsigned long long)vconst1); + GROUP_ENDING_NOP; + + v6 = vec_xor(v6, va6); + va6 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata6, (__vector unsigned long long)vconst1); + GROUP_ENDING_NOP; + + v7 = vec_xor(v7, va7); + va7 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)vdata7, (__vector unsigned long long)vconst1); + } /* else */ + + /* Second cool down. */ + v0 = vec_xor(v0, va0); + v1 = vec_xor(v1, va1); + v2 = vec_xor(v2, va2); + v3 = vec_xor(v3, va3); + v4 = vec_xor(v4, va4); + v5 = vec_xor(v5, va5); + v6 = vec_xor(v6, va6); + v7 = vec_xor(v7, va7); + +#ifdef REFLECT + /* + * vpmsumd produces a 96 bit result in the least significant bits of the register. Since + * we are bit reflected we have to shift it left 32 bits so it occupies the least + * significant bits in the bit reflected domain. + */ + v0 = (__vector unsigned long long)vec_sld( + (__vector unsigned char)v0, (__vector unsigned char)vzero, 4); + v1 = (__vector unsigned long long)vec_sld( + (__vector unsigned char)v1, (__vector unsigned char)vzero, 4); + v2 = (__vector unsigned long long)vec_sld( + (__vector unsigned char)v2, (__vector unsigned char)vzero, 4); + v3 = (__vector unsigned long long)vec_sld( + (__vector unsigned char)v3, (__vector unsigned char)vzero, 4); + v4 = (__vector unsigned long long)vec_sld( + (__vector unsigned char)v4, (__vector unsigned char)vzero, 4); + v5 = (__vector unsigned long long)vec_sld( + (__vector unsigned char)v5, (__vector unsigned char)vzero, 4); + v6 = (__vector unsigned long long)vec_sld( + (__vector unsigned char)v6, (__vector unsigned char)vzero, 4); + v7 = (__vector unsigned long long)vec_sld( + (__vector unsigned char)v7, (__vector unsigned char)vzero, 4); +#endif + + /* xor with the last 1024 bits. */ + va0 = vec_ld(0, (__vector unsigned long long *)p); + VEC_PERM(va0, va0, va0, vperm_const); + + va1 = vec_ld(16, (__vector unsigned long long *)p); + VEC_PERM(va1, va1, va1, vperm_const); + + va2 = vec_ld(32, (__vector unsigned long long *)p); + VEC_PERM(va2, va2, va2, vperm_const); + + va3 = vec_ld(48, (__vector unsigned long long *)p); + VEC_PERM(va3, va3, va3, vperm_const); + + va4 = vec_ld(64, (__vector unsigned long long *)p); + VEC_PERM(va4, va4, va4, vperm_const); + + va5 = vec_ld(80, (__vector unsigned long long *)p); + VEC_PERM(va5, va5, va5, vperm_const); + + va6 = vec_ld(96, (__vector unsigned long long *)p); + VEC_PERM(va6, va6, va6, vperm_const); + + va7 = vec_ld(112, (__vector unsigned long long *)p); + VEC_PERM(va7, va7, va7, vperm_const); + + p = (char *)p + 128; + + vdata0 = vec_xor(v0, va0); + vdata1 = vec_xor(v1, va1); + vdata2 = vec_xor(v2, va2); + vdata3 = vec_xor(v3, va3); + vdata4 = vec_xor(v4, va4); + vdata5 = vec_xor(v5, va5); + vdata6 = vec_xor(v6, va6); + vdata7 = vec_xor(v7, va7); + + /* Check if we have more blocks to process */ + next_block = 0; + if (length != 0) { + next_block = 1; + + /* zero v0-v7 */ + v0 = vec_xor(v0, v0); + v1 = vec_xor(v1, v1); + v2 = vec_xor(v2, v2); + v3 = vec_xor(v3, v3); + v4 = vec_xor(v4, v4); + v5 = vec_xor(v5, v5); + v6 = vec_xor(v6, v6); + v7 = vec_xor(v7, v7); + } + length = length + 128; + + } while (next_block); + + /* Calculate how many bytes we have left. */ + length = (len & 127); + + /* Calculate where in (short) constant table we need to start. */ + offset = 128 - length; + + v0 = vec_ld(offset, vcrc_short_const); + v1 = vec_ld(offset + 16, vcrc_short_const); + v2 = vec_ld(offset + 32, vcrc_short_const); + v3 = vec_ld(offset + 48, vcrc_short_const); + v4 = vec_ld(offset + 64, vcrc_short_const); + v5 = vec_ld(offset + 80, vcrc_short_const); + v6 = vec_ld(offset + 96, vcrc_short_const); + v7 = vec_ld(offset + 112, vcrc_short_const); + + offset += 128; + + v0 = (__vector unsigned long long)__builtin_crypto_vpmsumw( + (__vector unsigned int)vdata0, (__vector unsigned int)v0); + v1 = (__vector unsigned long long)__builtin_crypto_vpmsumw( + (__vector unsigned int)vdata1, (__vector unsigned int)v1); + v2 = (__vector unsigned long long)__builtin_crypto_vpmsumw( + (__vector unsigned int)vdata2, (__vector unsigned int)v2); + v3 = (__vector unsigned long long)__builtin_crypto_vpmsumw( + (__vector unsigned int)vdata3, (__vector unsigned int)v3); + v4 = (__vector unsigned long long)__builtin_crypto_vpmsumw( + (__vector unsigned int)vdata4, (__vector unsigned int)v4); + v5 = (__vector unsigned long long)__builtin_crypto_vpmsumw( + (__vector unsigned int)vdata5, (__vector unsigned int)v5); + v6 = (__vector unsigned long long)__builtin_crypto_vpmsumw( + (__vector unsigned int)vdata6, (__vector unsigned int)v6); + v7 = (__vector unsigned long long)__builtin_crypto_vpmsumw( + (__vector unsigned int)vdata7, (__vector unsigned int)v7); + + /* Now reduce the tail (0-112 bytes). */ + for (i = 0; i < length; i += 16) { + vdata0 = vec_ld(i, (__vector unsigned long long *)p); + VEC_PERM(vdata0, vdata0, vdata0, vperm_const); + va0 = vec_ld(offset + i, vcrc_short_const); + va0 = (__vector unsigned long long)__builtin_crypto_vpmsumw( + (__vector unsigned int)vdata0, (__vector unsigned int)va0); + v0 = vec_xor(v0, va0); + } + + /* xor all parallel chunks together. */ + v0 = vec_xor(v0, v1); + v2 = vec_xor(v2, v3); + v4 = vec_xor(v4, v5); + v6 = vec_xor(v6, v7); + + v0 = vec_xor(v0, v2); + v4 = vec_xor(v4, v6); + + v0 = vec_xor(v0, v4); + } + + /* Barrett Reduction */ + vconst1 = vec_ld(0, v_Barrett_const); + vconst2 = vec_ld(16, v_Barrett_const); + + v1 = (__vector unsigned long long)vec_sld( + (__vector unsigned char)v0, (__vector unsigned char)v0, 8); + v0 = vec_xor(v1, v0); + +#ifdef REFLECT + /* shift left one bit */ + vsht_splat = vec_splat_u8(1); + v0 = (__vector unsigned long long)vec_sll((__vector unsigned char)v0, vsht_splat); +#endif + + v0 = vec_and(v0, vmask_64bit); + +#ifndef REFLECT + + /* + * Now for the actual algorithm. The idea is to calculate q, the multiple of our polynomial that + * we need to subtract. By doing the computation 2x bits higher (ie 64 bits) and shifting the + * result back down 2x bits, we round down to the nearest multiple. + */ + + /* ma */ + v1 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)v0, (__vector unsigned long long)vconst1); + /* q = floor(ma/(2^64)) */ + v1 = (__vector unsigned long long)vec_sld( + (__vector unsigned char)vzero, (__vector unsigned char)v1, 8); + /* qn */ + v1 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)v1, (__vector unsigned long long)vconst2); + /* a - qn, subtraction is xor in GF(2) */ + v0 = vec_xor(v0, v1); + /* + * Get the result into r3. We need to shift it left 8 bytes: V0 [ 0 1 2 X ] V0 [ 0 X 2 3 ] + */ + result = __builtin_unpack_vector_1(v0); +#else + + /* + * The reflected version of Barrett reduction. Instead of bit reflecting our data (which is + * expensive to do), we bit reflect our constants and our algorithm, which means the + * intermediate data in our vector registers goes from 0-63 instead of 63-0. We can reflect the + * algorithm because we don't carry in mod 2 arithmetic. + */ + + /* bottom 32 bits of a */ + v1 = vec_and(v0, vmask_32bit); + + /* ma */ + v1 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)v1, (__vector unsigned long long)vconst1); + + /* bottom 32bits of ma */ + v1 = vec_and(v1, vmask_32bit); + /* qn */ + v1 = __builtin_crypto_vpmsumd( + (__vector unsigned long long)v1, (__vector unsigned long long)vconst2); + /* a - qn, subtraction is xor in GF(2) */ + v0 = vec_xor(v0, v1); + + /* + * Since we are bit reflected, the result (ie the low 32 bits) is in the high 32 bits. We just + * need to shift it left 4 bytes V0 [ 0 1 X 3 ] V0 [ 0 X 2 3 ] + */ + + /* shift result into top 64 bits of */ + v0 = (__vector unsigned long long)vec_sld( + (__vector unsigned char)v0, (__vector unsigned char)vzero, 4); + + result = __builtin_unpack_vector_0(v0); +#endif + + return result; +} +#endif |