| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Merge branch 'ppc-r64-44' into 'master' | Niels Möller | 2022-08-06 | 2 | -0/+277 |
| |\ | | | | | | | | | [PowerPC] Implement Poly1305 single block update based on radix 2^64 See merge request nettle/nettle!47 | ||||
| | * | [PowerPC] Use defined structure constants of P1305 in asm.m4 | Maamoun TK | 2022-08-06 | 1 | -20/+20 |
| | | | |||||
| | * | [PowerPC] Implement Poly1305 single block update based on radix 2^64 | Maamoun TK | 2022-05-29 | 2 | -0/+277 |
| | | | |||||
| * | | Fix a POSIX violation of m4 argument expansion | Maamoun TK | 2022-06-13 | 1 | -53/+60 |
| |/ | |||||
| * | Fix comment typo. | Niels Möller | 2022-03-17 | 1 | -1/+1 |
| | | |||||
| * | ppc: Update fat setup for new ghash organization. | Niels Möller | 2022-02-22 | 2 | -5/+40 |
| | | |||||
| * | ppc: Update vpmsumd ghash to new organization. | Niels Möller | 2022-02-22 | 3 | -499/+519 |
| | | |||||
| * | ecc: Add powerpc64 assembly for ecc_448_modp | Martin Schwenke | 2022-01-24 | 1 | -0/+174 |
| | | | | | | Signed-off-by: Martin Schwenke <martin@meltin.net> Signed-off-by: Amitay Isaacs <amitay@gmail.com> | ||||
| * | Move a comment. | Niels Möller | 2022-01-24 | 1 | -2/+2 |
| | | |||||
| * | ecc: Add powerpc64 assembly for ecc_25519_modp | Martin Schwenke | 2022-01-24 | 1 | -0/+101 |
| | | | | | | Signed-off-by: Martin Schwenke <martin@meltin.net> Signed-off-by: Alastair D'Silva <alastair@d-silva.org> | ||||
| * | ecc: Add powerpc64 assembly for ecc_224_modp | Amitay Isaacs | 2022-01-24 | 1 | -0/+123 |
| | | | | | Signed-off-by: Amitay Isaacs <amitay@ozlabs.org> | ||||
| * | ecc: Add powerpc64 assembly for ecc_521_modp | Martin Schwenke | 2022-01-21 | 1 | -0/+166 |
| | | | | | | Signed-off-by: Martin Schwenke <martin@meltin.net> Signed-off-by: Alastair D'Silva <alastair@d-silva.org> | ||||
| * | ecc: Add powerpc64 assembly for ecc_384_modp | Martin Schwenke | 2022-01-21 | 1 | -0/+227 |
| | | | | | | | Signed-off-by: Martin Schwenke <martin@meltin.net> Signed-off-by: Amitay Isaacs <amitay@ozlabs.org> Signed-off-by: Alastair D'Silva <alastair@d-silva.org> | ||||
| * | ecc: Add powerpc64 assembly for ecc_192_modp | Amitay Isaacs | 2022-01-21 | 1 | -0/+87 |
| | | | | | Signed-off-by: Amitay Isaacs <amitay@ozlabs.org> | ||||
| * | ppc: Reduce number of registers used for ecc_secp256r1_redc. | Niels Möller | 2022-01-10 | 1 | -42/+26 |
| | | |||||
| * | ppc: New configure test for ELFV2_ABI | Niels Möller | 2022-01-04 | 1 | -2/+2 |
| | | |||||
| * | ppc: Add powerpc64 assembly for ecc_256_redc | Amitay Isaacs | 2021-12-09 | 1 | -0/+144 |
| | | |||||
| * | ppc: Fix macro name SWAP_MASK to use all uppercase. | Niels Möller | 2021-04-13 | 2 | -88/+88 |
| | | |||||
| * | [PowerPC64] Use 32-bit offset to load data | mamonet | 2020-12-18 | 3 | -6/+10 |
| | | |||||
| * | ppc: More interleaving of chacha_4core. | Niels Möller | 2020-12-12 | 1 | -16/+16 |
| | | |||||
| * | Merge branch 'ppc-chacha-4core' | Niels Möller | 2020-12-08 | 2 | -0/+314 |
| |\ | |||||
| | * | ppc: Save registers below stack pointer, without modifying it.ppc-chacha-4core | Niels Möller | 2020-12-01 | 1 | -10/+11 |
| | | | |||||
| | * | ppc: Optimize chacha_4core main loop | Niels Möller | 2020-12-01 | 1 | -9/+42 |
| | | | | | | | | | | | * powerpc64/p7/chacha-4core.asm (QR): Instruction level interleaving in the main loop, written by Torbjörn Granlund. | ||||
| | * | ppc: Workaround using m4_unquote. | Niels Möller | 2020-11-30 | 1 | -1/+1 |
| | | | |||||
| | * | ppc: Add byte-swapping to chacha_4core, for big-endian builds. | Niels Möller | 2020-11-30 | 1 | -0/+13 |
| | | | |||||
| | * | ppc: New assembly for chacha_core4, doing four blocks in parallel. | Niels Möller | 2020-11-30 | 2 | -0/+267 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | * chacha-crypt.c: (_nettle_chacha_crypt_4core) (_nettle_chacha_crypt32_4core): New functions. * chacha-internal.h: Add prototypes for _nettle_chacha_4core and related functions. * configure.ac (asm_nettle_optional_list): Add chacha-4core.asm. * powerpc64/fat/chacha-4core.asm: New file. * powerpc64/p7/chacha-4core.asm: New file. * fat-ppc.c (fat_init): When altivec is available, use _nettle_chacha_crypt_4core and _nettle_chacha_crypt32_4core instead of _2core variants. | ||||
| * | | Fix comment type | Niels Möller | 2020-12-01 | 1 | -1/+1 |
| |/ | |||||
| * | Merge branch 'ppc-gcm' into master-updates | Niels Möller | 2020-11-28 | 2 | -0/+538 |
| |\ | |||||
| | * | ppc: Enable gcm code in fat builds. Based on patch by Mamone Tarsha. | Niels Möller | 2020-11-26 | 1 | -0/+39 |
| | | | |||||
| | * | [PowerPC64] modify register defines in gcm-hash.asm | mamonet | 2020-11-25 | 1 | -20/+20 |
| | | | |||||
| | * | ppc: Fix table offsets in gcm_hash. | Maamoun TK | 2020-11-14 | 1 | -37/+34 |
| | | | |||||
| | * | ppc: Assembly implementation of gcm_hash. | Maamoun TK | 2020-11-12 | 1 | -0/+502 |
| | | | |||||
| * | | ppc: Use vaddcuw instruction. | Niels Möller | 2020-11-28 | 1 | -3/+1 |
| | | | |||||
| * | | ppc: Support big-endian for _chacha_2core.ppc-chacha-2core | Niels Möller | 2020-11-25 | 1 | -0/+17 |
| | | | |||||
| * | | ppc: Enable _chacha_2core in fat builds. | Niels Möller | 2020-11-24 | 1 | -0/+36 |
| | | | |||||
| * | | ppc: Implement _chacha_2core. | Niels Möller | 2020-11-23 | 1 | -0/+249 |
| |/ | | | | * powerpc64/p7/chacha-2core.asm: New file. | ||||
| * | ppc: Comment instructions for chacha byte swapping.ppc-chacha-core | Niels Möller | 2020-11-07 | 1 | -3/+3 |
| | | |||||
| * | ppc: Add altivec detection to fat builds | Niels Möller | 2020-11-07 | 1 | -0/+37 |
| | | |||||
| * | ppc: chacha-core big-endian support | Maamoun TK | 2020-09-28 | 1 | -2/+22 |
| | | |||||
| * | ppc: Assembly implementation of _chacha_core. | Niels Möller | 2020-09-25 | 1 | -0/+140 |
| | | |||||
| * | "PowerPC64" Use same register convention in VSR macro | Maamoun TK | 2020-09-23 | 1 | -4/+3 |
| | | |||||
| * | "PowerPC64" Use explicit register names | Maamoun TK | 2020-09-23 | 3 | -197/+200 |
| | | | | | | This patch is built upon ppc-m4-macrology.patch. Using explicit register names is working as expected now. | ||||
| * | ppc: Add configure test and macros to replace register names. | Niels Möller | 2020-09-21 | 1 | -0/+14 |
| | | | | | | | | | | | | | | * aclocal.m4 (GMP_ASM_POWERPC_R_REGISTERS): New configure test, adapted from corresponding test in GMP's acinlude.m4. * configure.ac (ASM_PPC_WANT_R_REGISTERS): New substituted variable. Set using GMP_ASM_POWERPC_R_REGISTERS, when powerpc64 assembly code is enabled. * config.m4.in: Substituted here. * powerpc64/machine.m4: Check ASM_PPC_WANT_R_REGISTERS, and if needed, replace register names like r0, r1, ... with integers. * Makefile.in (%.asm): Include m4-utils.m4 for preprocessing of .asm files, and include config.m4 before machine.m4. | ||||
| * | Use default m4 quote character in asm files, part 5default-m4-quote-char | Niels Möller | 2020-09-14 | 5 | -98/+98 |
| | | | | | Update powerpc64 files. | ||||
| * | "PowerPC64" AES improve syntax | Maamoun TK | 2020-09-04 | 4 | -110/+90 |
| | | | | | | | | | | | This patch adds "VSR" macro to improve the syntax of assembly code, I will create a separate patch for gcm-hash since it hasn't merged yet to the master. I also removed the TODO from README because I tried to use "lxv/stxv" in POWER9 instead of "lxvd2x/stxvd2x" but gcc produced "lxvd2x/stxvd2x" in the binary. I'm not sure if it's variant issue of gcc but this will be problematic since "lxvd2x/stxvd2x" need permuting in little-endian mode while "lxv/stxv" is endianness aware. | ||||
| * | Add support for powerpc64 fat build | Niels Möller | 2020-08-26 | 2 | -0/+74 |
| | | | | | Based on patch by Mamone Tarsha | ||||
| * | Rename powerpc64/P8 to powerpc64/p8 | Niels Möller | 2020-08-26 | 2 | -0/+0 |
| | | |||||
| * | "PowerPC64" Add README (Reformatted) | Maamoun TK | 2020-08-26 | 1 | -0/+73 |
| | | |||||
| * | "PowerPC64" Add optimized AES [Enc|Dec] | Maamoun TK | 2020-08-26 | 2 | -0/+711 |
| | | | | | | | | | | | | | | I measured the latency and throughput of vcipher/vncipher/vxor instructions for POWER8 vcipher/vncipher throughput 6 instructions per cycle latency 0.91 clock cycles vxor throughput 6 instructions per cycle latency 0.32 clock cycles So the ideal option for POWER8 is processing 8 blocks, it has +12% performance over processing 4 blocks. | ||||
| * | "PowerPC64" Add machine.m4 | Maamoun TK | 2020-08-26 | 1 | -0/+32 |
 |
index : delta/nettle.git | |
| git.lysator.liu.se: nettle/nettle.git |
| summaryrefslogtreecommitdiff |