aboutsummaryrefslogtreecommitdiff
path: root/gmp-6.3.0/mpn/powerpc64/mode32
diff options
context:
space:
mode:
Diffstat (limited to 'gmp-6.3.0/mpn/powerpc64/mode32')
-rw-r--r--gmp-6.3.0/mpn/powerpc64/mode32/add_n.asm86
-rw-r--r--gmp-6.3.0/mpn/powerpc64/mode32/addmul_1.asm79
-rw-r--r--gmp-6.3.0/mpn/powerpc64/mode32/mul_1.asm73
-rw-r--r--gmp-6.3.0/mpn/powerpc64/mode32/p4/gmp-mparam.h182
-rw-r--r--gmp-6.3.0/mpn/powerpc64/mode32/sqr_diagonal.asm117
-rw-r--r--gmp-6.3.0/mpn/powerpc64/mode32/sub_n.asm88
-rw-r--r--gmp-6.3.0/mpn/powerpc64/mode32/submul_1.asm81
7 files changed, 706 insertions, 0 deletions
diff --git a/gmp-6.3.0/mpn/powerpc64/mode32/add_n.asm b/gmp-6.3.0/mpn/powerpc64/mode32/add_n.asm
new file mode 100644
index 0000000..1da8087
--- /dev/null
+++ b/gmp-6.3.0/mpn/powerpc64/mode32/add_n.asm
@@ -0,0 +1,86 @@
+dnl PowerPC-64/mode32 mpn_add_n -- Add two limb vectors of the same length > 0
+dnl and store sum in a third limb vector.
+
+dnl Copyright 1999-2001, 2003, 2005 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 POWER3/PPC630: ?
+C POWER4/PPC970: 4.25
+
+C INPUT PARAMETERS
+C rp r3
+C up r4
+C vp r5
+C n r6
+
+ASM_START()
+PROLOGUE(mpn_add_n)
+ mtctr r6 C copy size into CTR
+ addic r0, r0, 0 C clear cy
+ ld r8, 0(r4) C load least significant s1 limb
+ ld r0, 0(r5) C load least significant s2 limb
+ addi r3, r3, -8 C offset res_ptr, it's updated before it's used
+ bdz L(end) C If done, skip loop
+
+L(oop): ld r9, 8(r4) C load s1 limb
+ ld r10, 8(r5) C load s2 limb
+ adde r7, r0, r8 C add limbs with cy, set cy
+ srdi r6, r0, 32
+ srdi r11, r8, 32
+ adde r6, r6, r11 C add high limb parts, set cy
+ std r7, 8(r3) C store result limb
+ bdz L(exit) C decrement CTR and exit if done
+ ldu r8, 16(r4) C load s1 limb and update s1_ptr
+ ldu r0, 16(r5) C load s2 limb and update s2_ptr
+ adde r7, r10, r9 C add limbs with cy, set cy
+ srdi r6, r10, 32
+ srdi r11, r9, 32
+ adde r6, r6, r11 C add high limb parts, set cy
+ stdu r7, 16(r3) C store result limb and update res_ptr
+ bdnz L(oop) C decrement CTR and loop back
+
+L(end): adde r7, r0, r8
+ srdi r6, r0, 32
+ srdi r11, r8, 32
+ adde r6, r6, r11 C add limbs with cy, set cy
+ std r7, 8(r3) C store ultimate result limb
+ li r3, 0 C load cy into ...
+ addze r4, r3 C ... return value register
+ blr
+L(exit): adde r7, r10, r9
+ srdi r6, r10, 32
+ srdi r11, r9, 32
+ adde r6, r6, r11 C add limbs with cy, set cy
+ std r7, 16(r3)
+ li r3, 0 C load cy into ...
+ addze r4, r3 C ... return value register
+ blr
+EPILOGUE()
diff --git a/gmp-6.3.0/mpn/powerpc64/mode32/addmul_1.asm b/gmp-6.3.0/mpn/powerpc64/mode32/addmul_1.asm
new file mode 100644
index 0000000..bdc3951
--- /dev/null
+++ b/gmp-6.3.0/mpn/powerpc64/mode32/addmul_1.asm
@@ -0,0 +1,79 @@
+dnl PowerPC-64 mpn_addmul_1 -- Multiply a limb vector with a limb and add
+dnl the result to a second limb vector.
+
+dnl Copyright 1999-2001, 2003, 2005 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 POWER3/PPC630: ?
+C POWER4/PPC970: 12.5
+
+C INPUT PARAMETERS
+C rp r3
+C up r4
+C n r5
+C v r6,r7 or r7,r8
+
+ASM_START()
+PROLOGUE(mpn_addmul_1)
+
+ifdef(`BROKEN_LONGLONG_PARAM',
+` rldimi r8, r7, 32,0 C assemble vlimb from separate 32-bit arguments
+ mr r6, r8
+',`
+ rldimi r7, r6, 32,0 C assemble vlimb from separate 32-bit arguments
+ mr r6, r7
+')
+ li r7, 0 C cy_limb = 0
+ mtctr r5
+ addic r0, r0, 0
+ addi r3, r3, -8
+ addi r4, r4, -8
+
+L(oop): ldu r0, 8(r4)
+ mulld r9, r0, r6
+ adde r12, r9, r7 C add old high limb and new low limb
+ srdi r5, r9, 32
+ srdi r11, r7, 32
+ adde r5, r5, r11 C add high limb parts, set cy
+ mulhdu r7, r0, r6
+ addze r7, r7
+ ld r10, 8(r3)
+ addc r9, r12, r10
+ srdi r5, r12, 32
+ srdi r11, r10, 32
+ adde r5, r5, r11 C add high limb parts, set cy
+ stdu r9, 8(r3)
+ bdnz L(oop)
+
+ addze r4, r7
+ srdi r3, r4, 32
+ blr
+EPILOGUE()
diff --git a/gmp-6.3.0/mpn/powerpc64/mode32/mul_1.asm b/gmp-6.3.0/mpn/powerpc64/mode32/mul_1.asm
new file mode 100644
index 0000000..3a17e98
--- /dev/null
+++ b/gmp-6.3.0/mpn/powerpc64/mode32/mul_1.asm
@@ -0,0 +1,73 @@
+dnl PowerPC-64 mpn_mul_1 -- Multiply a limb vector with a limb and add
+dnl the result to a second limb vector.
+
+dnl Copyright 1999-2001, 2003, 2005 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 POWER3/PPC630: ?
+C POWER4/PPC970: 10
+
+C INPUT PARAMETERS
+C rp r3
+C up r4
+C n r5
+C v r6,r7 or r7,r8
+
+ASM_START()
+PROLOGUE(mpn_mul_1)
+
+ifdef(`BROKEN_LONGLONG_PARAM',
+` rldimi r8, r7, 32,0 C assemble vlimb from separate 32-bit arguments
+ mr r6, r8
+',`
+ rldimi r7, r6, 32,0 C assemble vlimb from separate 32-bit arguments
+ mr r6, r7
+')
+ li r7, 0 C cy_limb = 0
+ mtctr r5
+ addic r0, r0, 0
+ addi r3, r3, -8
+ addi r4, r4, -8
+
+L(oop): ldu r0, 8(r4)
+ mulld r9, r0, r6
+ adde r12, r9, r7 C add old high limb and new low limb
+ srdi r5, r9, 32
+ srdi r11, r7, 32
+ adde r5, r5, r11 C add high limb parts, set cy
+ mulhdu r7, r0, r6
+ stdu r12, 8(r3)
+ bdnz L(oop)
+
+ addze r4, r7
+ srdi r3, r4, 32
+ blr
+EPILOGUE()
diff --git a/gmp-6.3.0/mpn/powerpc64/mode32/p4/gmp-mparam.h b/gmp-6.3.0/mpn/powerpc64/mode32/p4/gmp-mparam.h
new file mode 100644
index 0000000..4e805a0
--- /dev/null
+++ b/gmp-6.3.0/mpn/powerpc64/mode32/p4/gmp-mparam.h
@@ -0,0 +1,182 @@
+/* PowerPC-64 gmp-mparam.h -- Compiler/machine parameter header file.
+
+Copyright 2008, 2009, 2011, 2017 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/. */
+
+/* 1800 MHz PPC970 */
+/* FFT tuning limit = 0.5 M */
+/* Generated by tuneup.c, 2017-01-01, gcc 4.0 */
+
+#define DIVREM_1_NORM_THRESHOLD 0 /* always */
+#define DIVREM_1_UNNORM_THRESHOLD 0 /* always */
+#define MOD_1_1P_METHOD 1
+#define MOD_1_NORM_THRESHOLD 0 /* always */
+#define MOD_1_UNNORM_THRESHOLD 0 /* always */
+#define MOD_1N_TO_MOD_1_1_THRESHOLD 7
+#define MOD_1U_TO_MOD_1_1_THRESHOLD 5
+#define MOD_1_1_TO_MOD_1_2_THRESHOLD 6
+#define MOD_1_2_TO_MOD_1_4_THRESHOLD 46
+#define PREINV_MOD_1_TO_MOD_1_THRESHOLD 15
+#define USE_PREINV_DIVREM_1 1
+#define DIV_QR_1N_PI1_METHOD 1
+#define DIV_QR_1_NORM_THRESHOLD 2
+#define DIV_QR_1_UNNORM_THRESHOLD 2
+#define DIV_QR_2_PI2_THRESHOLD 15
+#define DIVEXACT_1_THRESHOLD 0 /* always */
+#define BMOD_1_TO_MOD_1_THRESHOLD 88
+
+#define DIV_1_VS_MUL_1_PERCENT 269
+
+#define MUL_TOOM22_THRESHOLD 18
+#define MUL_TOOM33_THRESHOLD 60
+#define MUL_TOOM44_THRESHOLD 88
+#define MUL_TOOM6H_THRESHOLD 124
+#define MUL_TOOM8H_THRESHOLD 187
+
+#define MUL_TOOM32_TO_TOOM43_THRESHOLD 61
+#define MUL_TOOM32_TO_TOOM53_THRESHOLD 91
+#define MUL_TOOM42_TO_TOOM53_THRESHOLD 61
+#define MUL_TOOM42_TO_TOOM63_THRESHOLD 60
+#define MUL_TOOM43_TO_TOOM54_THRESHOLD 74
+
+#define SQR_BASECASE_THRESHOLD 4
+#define SQR_TOOM2_THRESHOLD 28
+#define SQR_TOOM3_THRESHOLD 90
+#define SQR_TOOM4_THRESHOLD 143
+#define SQR_TOOM6_THRESHOLD 181
+#define SQR_TOOM8_THRESHOLD 272
+
+#define MULMID_TOOM42_THRESHOLD 34
+
+#define MULMOD_BNM1_THRESHOLD 10
+#define SQRMOD_BNM1_THRESHOLD 15
+
+#define MUL_FFT_MODF_THRESHOLD 252 /* k = 5 */
+#define MUL_FFT_TABLE3 \
+ { { 252, 5}, { 11, 6}, { 6, 5}, { 13, 6}, \
+ { 7, 5}, { 15, 6}, { 13, 5}, { 27, 6}, \
+ { 15, 7}, { 8, 6}, { 17, 7}, { 9, 6}, \
+ { 19, 7}, { 17, 8}, { 9, 7}, { 20, 8}, \
+ { 11, 7}, { 23, 8}, { 13, 9}, { 7, 8}, \
+ { 21, 9}, { 11, 8}, { 27,10}, { 7, 9}, \
+ { 15, 8}, { 33, 9}, { 19, 8}, { 39, 9}, \
+ { 23, 8}, { 47, 9}, { 27,10}, { 15, 9}, \
+ { 39,10}, { 23, 9}, { 47,11}, { 15,10}, \
+ { 31, 9}, { 67,10}, { 39, 9}, { 83,10}, \
+ { 47, 9}, { 95, 8}, { 191,10}, { 55,11}, \
+ { 31,10}, { 63, 9}, { 127, 8}, { 255,10}, \
+ { 71, 9}, { 143, 8}, { 287,10}, { 79, 9}, \
+ { 159, 8}, { 319,11}, { 47,10}, { 95, 9}, \
+ { 191, 8}, { 383,10}, { 103,12}, { 31,11}, \
+ { 63,10}, { 127, 9}, { 255, 8}, { 511,10}, \
+ { 143, 9}, { 287,11}, { 79,10}, { 159, 9}, \
+ { 319, 8}, { 639,10}, { 175, 9}, { 351, 8}, \
+ { 703,11}, { 95,10}, { 191, 9}, { 383, 8}, \
+ { 767,10}, { 207, 9}, { 415,10}, { 223, 9}, \
+ { 447,12}, { 63,11}, { 127,10}, { 255, 9}, \
+ { 511,11}, { 143,10}, { 287, 9}, { 575,11}, \
+ { 159,10}, { 319, 9}, { 639,11}, { 175,10}, \
+ { 351, 9}, { 703,12}, { 95,11}, { 191,10}, \
+ { 383, 9}, { 767,11}, { 207,10}, { 415,11}, \
+ { 223,10}, { 447,13}, { 8192,14}, { 16384,15}, \
+ { 32768,16} }
+#define MUL_FFT_TABLE3_SIZE 105
+#define MUL_FFT_THRESHOLD 5248
+
+#define SQR_FFT_MODF_THRESHOLD 236 /* k = 5 */
+#define SQR_FFT_TABLE3 \
+ { { 236, 5}, { 13, 6}, { 15, 7}, { 8, 6}, \
+ { 17, 7}, { 9, 6}, { 19, 7}, { 17, 8}, \
+ { 9, 7}, { 20, 8}, { 11, 7}, { 24, 8}, \
+ { 13, 9}, { 7, 8}, { 19, 9}, { 11, 8}, \
+ { 25,10}, { 7, 9}, { 15, 8}, { 33, 9}, \
+ { 19, 8}, { 39, 9}, { 23, 8}, { 47, 9}, \
+ { 27,10}, { 15, 9}, { 39,10}, { 23, 9}, \
+ { 47,11}, { 15,10}, { 31, 9}, { 67,10}, \
+ { 39, 9}, { 79, 8}, { 159,10}, { 47, 9}, \
+ { 95, 8}, { 191,11}, { 31,10}, { 63, 9}, \
+ { 127, 8}, { 255,10}, { 71, 9}, { 143, 8}, \
+ { 287,10}, { 79, 9}, { 159, 8}, { 319,11}, \
+ { 47,10}, { 95, 9}, { 191, 8}, { 383,12}, \
+ { 31,11}, { 63,10}, { 127, 9}, { 255, 8}, \
+ { 511,10}, { 143, 9}, { 287, 8}, { 575,11}, \
+ { 79,10}, { 159, 9}, { 319, 8}, { 639,10}, \
+ { 175, 9}, { 351, 8}, { 703,11}, { 95,10}, \
+ { 191, 9}, { 383, 8}, { 767,10}, { 207, 9}, \
+ { 415,10}, { 223,12}, { 63,11}, { 127,10}, \
+ { 255, 9}, { 511,11}, { 143,10}, { 287, 9}, \
+ { 575,11}, { 159,10}, { 319, 9}, { 639,11}, \
+ { 175,10}, { 351, 9}, { 703,11}, { 191,10}, \
+ { 383, 9}, { 767,11}, { 207,10}, { 415,11}, \
+ { 223,10}, { 447,13}, { 8192,14}, { 16384,15}, \
+ { 32768,16} }
+#define SQR_FFT_TABLE3_SIZE 97
+#define SQR_FFT_THRESHOLD 3200
+
+#define MULLO_BASECASE_THRESHOLD 0 /* always */
+#define MULLO_DC_THRESHOLD 56
+#define MULLO_MUL_N_THRESHOLD 8648
+#define SQRLO_BASECASE_THRESHOLD 2
+#define SQRLO_DC_THRESHOLD 106
+#define SQRLO_SQR_THRESHOLD 6293
+
+#define DC_DIV_QR_THRESHOLD 28
+#define DC_DIVAPPR_Q_THRESHOLD 102
+#define DC_BDIV_QR_THRESHOLD 51
+#define DC_BDIV_Q_THRESHOLD 124
+
+#define INV_MULMOD_BNM1_THRESHOLD 34
+#define INV_NEWTON_THRESHOLD 123
+#define INV_APPR_THRESHOLD 109
+
+#define BINV_NEWTON_THRESHOLD 206
+#define REDC_1_TO_REDC_N_THRESHOLD 51
+
+#define MU_DIV_QR_THRESHOLD 807
+#define MU_DIVAPPR_Q_THRESHOLD 807
+#define MUPI_DIV_QR_THRESHOLD 53
+#define MU_BDIV_QR_THRESHOLD 748
+#define MU_BDIV_Q_THRESHOLD 872
+
+#define POWM_SEC_TABLE 2,23,66,440,1555
+
+#define GET_STR_DC_THRESHOLD 7
+#define GET_STR_PRECOMPUTE_THRESHOLD 17
+#define SET_STR_DC_THRESHOLD 1035
+#define SET_STR_PRECOMPUTE_THRESHOLD 2170
+
+#define FAC_DSC_THRESHOLD 542
+#define FAC_ODD_THRESHOLD 24
+
+#define MATRIX22_STRASSEN_THRESHOLD 10
+#define HGCD_THRESHOLD 108
+#define HGCD_APPR_THRESHOLD 116
+#define HGCD_REDUCE_THRESHOLD 1437
+#define GCD_DC_THRESHOLD 268
+#define GCDEXT_DC_THRESHOLD 241
+#define JACOBI_BASE_METHOD 4
diff --git a/gmp-6.3.0/mpn/powerpc64/mode32/sqr_diagonal.asm b/gmp-6.3.0/mpn/powerpc64/mode32/sqr_diagonal.asm
new file mode 100644
index 0000000..ff5f4b3
--- /dev/null
+++ b/gmp-6.3.0/mpn/powerpc64/mode32/sqr_diagonal.asm
@@ -0,0 +1,117 @@
+dnl PowerPC-64 mpn_sqr_diagonal.
+
+dnl Copyright 2001-2003, 2005, 2006, 20010 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 POWER3/PPC630 18
+C POWER4/PPC970 ?
+C POWER5 7.25
+C POWER6 9.5
+
+C INPUT PARAMETERS
+define(`rp', r3)
+define(`up', r4)
+define(`n', r5)
+
+ASM_START()
+PROLOGUE(mpn_sqr_diagonal)
+ifdef(`HAVE_ABI_mode32',
+` rldicl n, n, 0, 32') C zero extend n
+
+ rldicl. r0, n, 0,62 C r0 = n & 3, set cr0
+ addi n, n, 3 C compute count...
+ cmpdi cr6, r0, 2
+ srdi n, n, 2 C ...for ctr
+ mtctr n C copy count into ctr
+ beq cr0, L(b00)
+ blt cr6, L(b01)
+ beq cr6, L(b10)
+
+L(b11): ld r0, 0(up)
+ ld r10, 8(up)
+ ld r12, 16(up)
+ addi rp, rp, -16
+ mulld r7, r0, r0
+ mulhdu r8, r0, r0
+ mulld r9, r10, r10
+ mulhdu r10, r10, r10
+ mulld r11, r12, r12
+ mulhdu r12, r12, r12
+ addi up, up, 24
+ b L(11)
+
+ ALIGN(16)
+L(b01): ld r0, 0(up)
+ addi rp, rp, -48
+ addi up, up, 8
+ mulld r11, r0, r0
+ mulhdu r12, r0, r0
+ b L(01)
+
+ ALIGN(16)
+L(b10): ld r0, 0(up)
+ ld r12, 8(up)
+ addi rp, rp, -32
+ addi up, up, 16
+ mulld r9, r0, r0
+ mulhdu r10, r0, r0
+ mulld r11, r12, r12
+ mulhdu r12, r12, r12
+ b L(10)
+
+ ALIGN(32)
+L(b00):
+L(top): ld r0, 0(up)
+ ld r8, 8(up)
+ ld r10, 16(up)
+ ld r12, 24(up)
+ mulld r5, r0, r0
+ mulhdu r6, r0, r0
+ mulld r7, r8, r8
+ mulhdu r8, r8, r8
+ mulld r9, r10, r10
+ mulhdu r10, r10, r10
+ mulld r11, r12, r12
+ mulhdu r12, r12, r12
+ addi up, up, 32
+ std r5, 0(rp)
+ std r6, 8(rp)
+L(11): std r7, 16(rp)
+ std r8, 24(rp)
+L(10): std r9, 32(rp)
+ std r10, 40(rp)
+L(01): std r11, 48(rp)
+ std r12, 56(rp)
+ addi rp, rp, 64
+ bdnz L(top)
+
+ blr
+EPILOGUE()
diff --git a/gmp-6.3.0/mpn/powerpc64/mode32/sub_n.asm b/gmp-6.3.0/mpn/powerpc64/mode32/sub_n.asm
new file mode 100644
index 0000000..6fdc1d4
--- /dev/null
+++ b/gmp-6.3.0/mpn/powerpc64/mode32/sub_n.asm
@@ -0,0 +1,88 @@
+dnl PowerPC-64/mode32 mpn_sub_n -- Subtract two limb vectors of the same
+dnl length and store difference in a third limb vector.
+
+dnl Copyright 1999-2001, 2003, 2005 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 POWER3/PPC630: ?
+C POWER4/PPC970: 4.25
+
+C INPUT PARAMETERS
+C rp r3
+C up r4
+C vp r5
+C n r6
+
+ASM_START()
+PROLOGUE(mpn_sub_n)
+ mtctr r6 C copy size into CTR
+ addic r0, r6, -1 C set cy
+ ld r8, 0(r4) C load least significant s1 limb
+ ld r0, 0(r5) C load least significant s2 limb
+ addi r3, r3, -8 C offset res_ptr, it's updated before it's used
+ bdz L(end) C If done, skip loop
+
+L(oop): ld r9, 8(r4) C load s1 limb
+ ld r10, 8(r5) C load s2 limb
+ subfe r7, r0, r8 C subtract limbs with cy, set cy
+ srdi r6, r0, 32
+ srdi r11, r8, 32
+ subfe r6, r6, r11
+ std r7, 8(r3) C store result limb
+ bdz L(exit) C decrement CTR and exit if done
+ ldu r8, 16(r4) C load s1 limb and update s1_ptr
+ ldu r0, 16(r5) C load s2 limb and update s2_ptr
+ subfe r7, r10, r9 C subtract limbs with cy, set cy
+ srdi r6, r10, 32
+ srdi r11, r9, 32
+ subfe r6, r6, r11
+ stdu r7, 16(r3) C store result limb and update res_ptr
+ bdnz L(oop) C decrement CTR and loop back
+
+L(end): subfe r7, r0, r8
+ srdi r6, r0, 32
+ srdi r11, r8, 32
+ subfe r6, r6, r11
+ std r7, 8(r3) C store ultimate result limb
+ subfe r3, r0, r0 C load !cy into ...
+ subfic r4, r3, 0 C ... return value register
+ li r3, 0 C zero extend return value
+ blr
+L(exit): subfe r7, r10, r9
+ srdi r6, r10, 32
+ srdi r11, r9, 32
+ subfe r6, r6, r11
+ std r7, 16(r3)
+ subfe r3, r0, r0 C load !cy into ...
+ subfic r4, r3, 0 C ... return value register
+ li r3, 0 C zero extend return value
+ blr
+EPILOGUE()
diff --git a/gmp-6.3.0/mpn/powerpc64/mode32/submul_1.asm b/gmp-6.3.0/mpn/powerpc64/mode32/submul_1.asm
new file mode 100644
index 0000000..996eda2
--- /dev/null
+++ b/gmp-6.3.0/mpn/powerpc64/mode32/submul_1.asm
@@ -0,0 +1,81 @@
+dnl PowerPC-64 mpn_submul_1 -- Multiply a limb vector with a limb and subtract
+dnl the result from a second limb vector.
+
+dnl Copyright 1999-2001, 2003, 2005 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 POWER3/PPC630: ?
+C POWER4/PPC970: 16
+
+C INPUT PARAMETERS
+C rp r3
+C up r4
+C n r5
+C v r6,r7 or r7,r8
+
+ASM_START()
+PROLOGUE(mpn_submul_1)
+
+ifdef(`BROKEN_LONGLONG_PARAM',
+` rldimi r8, r7, 32,0 C assemble vlimb from separate 32-bit arguments
+ mr r6, r8
+',`
+ rldimi r7, r6, 32,0 C assemble vlimb from separate 32-bit arguments
+ mr r6, r7
+')
+ li r7, 0 C cy_limb = 0
+ mtctr r5
+ addic r0, r0, 0
+ addi r3, r3, -8
+ addi r4, r4, -8
+
+L(oop): ldu r0, 8(r4)
+ mulld r9, r0, r6
+ adde r12, r9, r7 C add old high limb and new low limb
+ srdi r5, r9, 32
+ srdi r11, r7, 32
+ adde r5, r5, r11 C add high limb parts, set cy
+ mulhdu r7, r0, r6
+ addze r7, r7
+ ld r10, 8(r3)
+ subfc r9, r12, r10
+ srdi r5, r12, 32
+ srdi r11, r10, 32
+ subfe r5, r5, r11 C subtract high limb parts, set cy
+ stdu r9, 8(r3)
+ subfe r11, r11, r11 C invert ...
+ addic r11, r11, 1 C ... carry
+ bdnz L(oop)
+
+ addze r4, r7
+ srdi r3, r4, 32
+ blr
+EPILOGUE()
generated by cgit v1.2.3 (git 2.25.1) at 2024-09-19 21:44:17 +0000