Provide some arm a12/a17 optimised files.

5 files changed, 398 insertions, 0 deletions

diff --git a/mpn/arm/v7a/cora17/addmul_1.asm b/mpn/arm/v7a/cora17/addmul_1.asm
new file mode 100644
index 000000000..c11ed47f7
--- /dev/null
+++ b/mpn/arm/v7a/cora17/addmul_1.asm
@@ -0,0 +1,34 @@
+dnl  ARM mpn_addmul_1
+
+dnl  Copyright 2018 Free Software Foundation, Inc.
+
+dnl  This file is part of the GNU MP Library.
+dnl
+dnl  The GNU MP Library is free software; you can redistribute it and/or modify
+dnl  it under the terms of either:
+dnl
+dnl    * the GNU Lesser General Public License as published by the Free
+dnl      Software Foundation; either version 3 of the License, or (at your
+dnl      option) any later version.
+dnl
+dnl  or
+dnl
+dnl    * the GNU General Public License as published by the Free Software
+dnl      Foundation; either version 2 of the License, or (at your option) any
+dnl      later version.
+dnl
+dnl  or both in parallel, as here.
+dnl
+dnl  The GNU MP Library is distributed in the hope that it will be useful, but
+dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+dnl  for more details.
+dnl
+dnl  You should have received copies of the GNU General Public License and the
+dnl  GNU Lesser General Public License along with the GNU MP Library.  If not,
+dnl  see https://www.gnu.org/licenses/.
+
+include(`../config.m4')
+
+MULFUNC_PROLOGUE(mpn_addmul_1)
+include_mpn(`arm/v6/addmul_1.asm')
diff --git a/mpn/arm/v7a/cora17/gmp-mparam.h b/mpn/arm/v7a/cora17/gmp-mparam.h
new file mode 100644
index 000000000..152b403ff
--- /dev/null
+++ b/mpn/arm/v7a/cora17/gmp-mparam.h
@@ -0,0 +1,175 @@
+/* gmp-mparam.h -- Compiler/machine parameter header file.
+
+Copyright 2018 Free Software Foundation, Inc.
+
+This file is part of the GNU MP Library.
+
+The GNU MP Library is free software; you can redistribute it and/or modify
+it under the terms of either:
+
+  * the GNU Lesser General Public License as published by the Free
+    Software Foundation; either version 3 of the License, or (at your
+    option) any later version.
+
+or
+
+  * 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 both in parallel, as here.
+
+The GNU MP Library is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+for more details.
+
+You should have received copies of the GNU General Public License and the
+GNU Lesser General Public License along with the GNU MP Library.  If not,
+see https://www.gnu.org/licenses/.  */
+
+#define GMP_LIMB_BITS 32
+#define GMP_LIMB_BYTES 4
+
+/* 1800 MHz Cortex-A17 with Neon (in spite of file position) */
+/* FFT tuning limit = 0.5 M */
+/* Generated by tuneup.c, 2018-10-27, gcc 6.3 */
+
+#define MOD_1_NORM_THRESHOLD                 0  /* always */
+#define MOD_1_UNNORM_THRESHOLD               0  /* always */
+#define MOD_1N_TO_MOD_1_1_THRESHOLD          5
+#define MOD_1U_TO_MOD_1_1_THRESHOLD          4
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD         8
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD     MP_SIZE_T_MAX
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD     12
+#define USE_PREINV_DIVREM_1                  1  /* native */
+#define DIV_QR_1N_PI1_METHOD                 1
+#define DIV_QR_1_NORM_THRESHOLD          MP_SIZE_T_MAX  /* never */
+#define DIV_QR_1_UNNORM_THRESHOLD        MP_SIZE_T_MAX  /* never */
+#define DIV_QR_2_PI2_THRESHOLD           MP_SIZE_T_MAX  /* never */
+#define DIVEXACT_1_THRESHOLD                 0  /* always (native) */
+#define BMOD_1_TO_MOD_1_THRESHOLD           42
+
+#define DIV_1_VS_MUL_1_PERCENT             208
+
+#define MUL_TOOM22_THRESHOLD                38
+#define MUL_TOOM33_THRESHOLD               131
+#define MUL_TOOM44_THRESHOLD               208
+#define MUL_TOOM6H_THRESHOLD               303
+#define MUL_TOOM8H_THRESHOLD               454
+
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD     141
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD     176
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD     130
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD     145
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD     178
+
+#define SQR_BASECASE_THRESHOLD               0  /* always (native) */
+#define SQR_TOOM2_THRESHOLD                 58
+#define SQR_TOOM3_THRESHOLD                189
+#define SQR_TOOM4_THRESHOLD                348
+#define SQR_TOOM6_THRESHOLD                426
+#define SQR_TOOM8_THRESHOLD                608
+
+#define MULMID_TOOM42_THRESHOLD             62
+
+#define MULMOD_BNM1_THRESHOLD               22
+#define SQRMOD_BNM1_THRESHOLD               30
+
+#define MUL_FFT_MODF_THRESHOLD             565  /* k = 5 */
+#define MUL_FFT_TABLE3                                      \
+  { {    565, 5}, {     29, 6}, {     15, 5}, {     31, 6}, \
+    {     16, 5}, {     33, 6}, {     17, 5}, {     35, 6}, \
+    {     29, 7}, {     15, 6}, {     33, 7}, {     17, 6}, \
+    {     36, 7}, {     19, 6}, {     39, 7}, {     29, 8}, \
+    {     15, 7}, {     35, 8}, {     19, 7}, {     43, 8}, \
+    {     23, 7}, {     49, 8}, {     27, 7}, {     55, 9}, \
+    {     15, 8}, {     31, 7}, {     63, 8}, {     43, 9}, \
+    {     23, 8}, {     55, 9}, {     31, 8}, {     67, 9}, \
+    {     39, 8}, {     83, 9}, {     47, 8}, {     95, 9}, \
+    {     55,10}, {     31, 9}, {     79,10}, {     47, 9}, \
+    {     95,11}, {     31,10}, {     63, 9}, {    135,10}, \
+    {     79, 9}, {    159,10}, {     95, 9}, {    191,10}, \
+    {    111,11}, {     63,10}, {    143, 9}, {    287, 8}, \
+    {    575,10}, {    159,11}, {     95,10}, {    191, 9}, \
+    {    383, 8}, {    767, 9}, {    399,12}, {     63,11}, \
+    {    127,10}, {    255, 9}, {    511, 8}, {   1023, 9}, \
+    {    543,10}, {    287, 9}, {    575,10}, {    303,11}, \
+    {    159,10}, {    319, 9}, {    639,10}, {    335, 9}, \
+    {    671,10}, {    351, 9}, {    703,10}, {    367, 9}, \
+    {    735,11}, {    191,10}, {    383, 9}, {    767,10}, \
+    {    399, 9}, {    799,10}, {    415, 9}, {    831,10}, \
+    {    431, 9}, {    863,11}, {    223,10}, {    447,12}, \
+    {   4096,13}, {   8192,14}, {  16384,15}, {  32768,16} }
+#define MUL_FFT_TABLE3_SIZE 92
+#define MUL_FFT_THRESHOLD                 5760
+
+#define SQR_FFT_MODF_THRESHOLD             525  /* k = 5 */
+#define SQR_FFT_TABLE3                                      \
+  { {    525, 5}, {     29, 6}, {     15, 5}, {     33, 6}, \
+    {     29, 7}, {     15, 6}, {     33, 7}, {     17, 6}, \
+    {     36, 7}, {     19, 6}, {     39, 7}, {     29, 8}, \
+    {     15, 7}, {     35, 8}, {     19, 7}, {     41, 8}, \
+    {     23, 7}, {     49, 8}, {     27, 9}, {     15, 8}, \
+    {     43, 9}, {     23, 8}, {     55,10}, {     15, 9}, \
+    {     31, 8}, {     67, 9}, {     39, 8}, {     79, 9}, \
+    {     47, 8}, {     95, 9}, {     55,10}, {     31, 9}, \
+    {     79,10}, {     47, 9}, {     95,11}, {     31,10}, \
+    {     63, 9}, {    135,10}, {     79, 9}, {    159,10}, \
+    {     95, 9}, {    191,10}, {    111,11}, {     63,10}, \
+    {    143, 9}, {    287,10}, {    159, 9}, {    319,11}, \
+    {     95,10}, {    191, 9}, {    383, 8}, {    767, 9}, \
+    {    399,12}, {     63,11}, {    127, 9}, {    511,10}, \
+    {    271, 9}, {    543,10}, {    287, 9}, {    575,10}, \
+    {    303,11}, {    159,10}, {    319, 9}, {    639,10}, \
+    {    335, 9}, {    671,10}, {    351, 9}, {    703,10}, \
+    {    367,11}, {    191,10}, {    383, 9}, {    767,10}, \
+    {    399, 9}, {    799,10}, {    415, 9}, {    831,10}, \
+    {    431, 9}, {    863,10}, {    447,12}, {   4096,13}, \
+    {   8192,14}, {  16384,15}, {  32768,16} }
+#define SQR_FFT_TABLE3_SIZE 83
+#define SQR_FFT_THRESHOLD                 4736
+
+#define MULLO_BASECASE_THRESHOLD             0  /* always */
+#define MULLO_DC_THRESHOLD                  25
+#define MULLO_MUL_N_THRESHOLD            13463
+#define SQRLO_BASECASE_THRESHOLD             0  /* always */
+#define SQRLO_DC_THRESHOLD                  26
+#define SQRLO_SQR_THRESHOLD               8907
+
+#define DC_DIV_QR_THRESHOLD                 35
+#define DC_DIVAPPR_Q_THRESHOLD             111
+#define DC_BDIV_QR_THRESHOLD                32
+#define DC_BDIV_Q_THRESHOLD                108
+
+#define INV_MULMOD_BNM1_THRESHOLD           74
+#define INV_NEWTON_THRESHOLD               173
+#define INV_APPR_THRESHOLD                 123
+
+#define BINV_NEWTON_THRESHOLD              303
+#define REDC_1_TO_REDC_2_THRESHOLD           2
+#define REDC_2_TO_REDC_N_THRESHOLD         159
+
+#define MU_DIV_QR_THRESHOLD               1895
+#define MU_DIVAPPR_Q_THRESHOLD            1895
+#define MUPI_DIV_QR_THRESHOLD               73
+#define MU_BDIV_QR_THRESHOLD              1685
+#define MU_BDIV_Q_THRESHOLD               2089
+
+#define POWM_SEC_TABLE  5,19,122,480,1486
+
+#define GET_STR_DC_THRESHOLD                14
+#define GET_STR_PRECOMPUTE_THRESHOLD        28
+#define SET_STR_DC_THRESHOLD               108
+#define SET_STR_PRECOMPUTE_THRESHOLD       630
+
+#define FAC_DSC_THRESHOLD                  282
+#define FAC_ODD_THRESHOLD                   55
+
+#define MATRIX22_STRASSEN_THRESHOLD         28
+#define HGCD_THRESHOLD                      58
+#define HGCD_APPR_THRESHOLD                 52
+#define HGCD_REDUCE_THRESHOLD             3524
+#define GCD_DC_THRESHOLD                   358
+#define GCDEXT_DC_THRESHOLD                249
+#define JACOBI_BASE_METHOD                   4
diff --git a/mpn/arm/v7a/cora17/mod_34lsub1.asm b/mpn/arm/v7a/cora17/mod_34lsub1.asm
new file mode 100644
index 000000000..39e5a15fb
--- /dev/null
+++ b/mpn/arm/v7a/cora17/mod_34lsub1.asm
@@ -0,0 +1,121 @@
+dnl  ARM mpn_mod_34lsub1 -- remainder modulo 2^24-1.
+
+dnl  Copyright 2012, 2013, 2018 Free Software Foundation, Inc.
+
+dnl  This file is part of the GNU MP Library.
+dnl
+dnl  The GNU MP Library is free software; you can redistribute it and/or modify
+dnl  it under the terms of either:
+dnl
+dnl    * the GNU Lesser General Public License as published by the Free
+dnl      Software Foundation; either version 3 of the License, or (at your
+dnl      option) any later version.
+dnl
+dnl  or
+dnl
+dnl    * the GNU General Public License as published by the Free Software
+dnl      Foundation; either version 2 of the License, or (at your option) any
+dnl      later version.
+dnl
+dnl  or both in parallel, as here.
+dnl
+dnl  The GNU MP Library is distributed in the hope that it will be useful, but
+dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+dnl  for more details.
+dnl
+dnl  You should have received copies of the GNU General Public License and the
+dnl  GNU Lesser General Public License along with the GNU MP Library.  If not,
+dnl  see https://www.gnu.org/licenses/.
+
+include(`../config.m4')
+
+C	     cycles/limb
+C StrongARM	 ?
+C XScale	 ?
+C Cortex-A5	 2.67
+C Cortex-A7	 2.37
+C Cortex-A8	 2.34
+C Cortex-A9	 ?
+C Cortex-A15	 1.39
+C Cortex-A17	 1.60
+C Cortex-A53	 2.51
+
+define(`ap',	r0)
+define(`n',	r1)
+
+C mp_limb_t mpn_mod_34lsub1 (mp_srcptr up, mp_size_t n)
+
+C TODO
+C  * Write cleverer summation code.
+C  * Consider loading 6 64-bit aligned registers at a time, to approach 1 c/l.
+
+ASM_START()
+	TEXT
+	ALIGN(32)
+PROLOGUE(mpn_mod_34lsub1)
+	push	{ r4, r5, r6, r7 }
+
+	subs	n, n, #3
+	mov	r7, #0
+	blt	L(le2)			C n <= 2
+
+	ldmia	ap!, { r2, r3, r12 }
+	subs	n, n, #3
+	blt	L(sum)			C n <= 5
+	mov	r7, #0
+	b	L(mid)
+
+L(top):	adds	r2, r2, r4
+	adcs	r3, r3, r5
+	adcs	r12, r12, r6
+	adc	r7, r7, #0
+L(mid):	ldmia	ap!, { r4, r5, r6 }
+	subs	n, n, #3
+	bpl	L(top)
+
+	adds	r2, r2, r4
+	adcs	r3, r3, r5
+	adcs	r12, r12, r6
+	adc	r7, r7, #0		C r7 <= 1
+
+L(sum):	cmn	n, #2
+	movlo	r4, #0
+	ldrhs	r4, [ap], #4
+	movls	r5, #0
+	ldrhi	r5, [ap], #4
+
+	adds	r2, r2, r4
+	adcs	r3, r3, r5
+	adcs	r12, r12, #0
+	adc	r7, r7, #0		C r7 <= 2
+
+L(sum2):
+	bic	r0, r2, #0xff000000
+	add	r0, r0, r2, lsr #24
+	add	r0, r0, r7
+
+	mov	r7, r3, lsl #8
+	bic	r2, r7, #0xff000000
+	add	r0, r0, r2
+	add	r0, r0, r3, lsr #16
+
+	mov	r2, r12, lsl #16
+	bic	r1, r2, #0xff000000
+	add	r0, r0, r1
+	add	r0, r0, r12, lsr #8
+
+	pop	{ r4, r5, r6, r7 }
+	return	lr
+
+L(le2):	cmn	n, #1
+	bne	L(1)
+	ldmia	ap!, { r2, r3 }
+	mov	r12, #0
+	b	L(sum2)
+L(1):	ldr	r2, [ap]
+	bic	r0, r2, #0xff000000
+	add	r0, r0, r2, lsr #24
+	pop	{ r4, r5, r6, r7 }
+	return	lr
+EPILOGUE()
diff --git a/mpn/arm/v7a/cora17/mul_1.asm b/mpn/arm/v7a/cora17/mul_1.asm
new file mode 100644
index 000000000..d9b6042c3
--- /dev/null
+++ b/mpn/arm/v7a/cora17/mul_1.asm
@@ -0,0 +1,34 @@
+dnl  ARM mpn_mul_1
+
+dnl  Copyright 2018 Free Software Foundation, Inc.
+
+dnl  This file is part of the GNU MP Library.
+dnl
+dnl  The GNU MP Library is free software; you can redistribute it and/or modify
+dnl  it under the terms of either:
+dnl
+dnl    * the GNU Lesser General Public License as published by the Free
+dnl      Software Foundation; either version 3 of the License, or (at your
+dnl      option) any later version.
+dnl
+dnl  or
+dnl
+dnl    * the GNU General Public License as published by the Free Software
+dnl      Foundation; either version 2 of the License, or (at your option) any
+dnl      later version.
+dnl
+dnl  or both in parallel, as here.
+dnl
+dnl  The GNU MP Library is distributed in the hope that it will be useful, but
+dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+dnl  for more details.
+dnl
+dnl  You should have received copies of the GNU General Public License and the
+dnl  GNU Lesser General Public License along with the GNU MP Library.  If not,
+dnl  see https://www.gnu.org/licenses/.
+
+include(`../config.m4')
+
+MULFUNC_PROLOGUE(mpn_mul_1)
+include_mpn(`arm/v6/mul_1.asm')
diff --git a/mpn/arm/v7a/cora17/submul_1.asm b/mpn/arm/v7a/cora17/submul_1.asm
new file mode 100644
index 000000000..f3e8139ec
--- /dev/null
+++ b/mpn/arm/v7a/cora17/submul_1.asm
@@ -0,0 +1,34 @@
+dnl  ARM mpn_submul_1
+
+dnl  Copyright 2018 Free Software Foundation, Inc.
+
+dnl  This file is part of the GNU MP Library.
+dnl
+dnl  The GNU MP Library is free software; you can redistribute it and/or modify
+dnl  it under the terms of either:
+dnl
+dnl    * the GNU Lesser General Public License as published by the Free
+dnl      Software Foundation; either version 3 of the License, or (at your
+dnl      option) any later version.
+dnl
+dnl  or
+dnl
+dnl    * the GNU General Public License as published by the Free Software
+dnl      Foundation; either version 2 of the License, or (at your option) any
+dnl      later version.
+dnl
+dnl  or both in parallel, as here.
+dnl
+dnl  The GNU MP Library is distributed in the hope that it will be useful, but
+dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+dnl  for more details.
+dnl
+dnl  You should have received copies of the GNU General Public License and the
+dnl  GNU Lesser General Public License along with the GNU MP Library.  If not,
+dnl  see https://www.gnu.org/licenses/.
+
+include(`../config.m4')
+
+MULFUNC_PROLOGUE(mpn_submul_1)
+include_mpn(`arm/v6/submul_1.asm')