On Tue, 2015-02-03 at 10:57 +0100, Torbjörn Granlund wrote:
> Marc Glisse <marc.gli...@inria.fr> writes:
>
> Apparently not, the motivation for the patch is that multu has
> disappeared...
>
> Then I see no other robust approach than making mpn/mipsnomultu_64 (or
> somesuch).
>
> Well, an analogous robust approach would be moving the dmultu code into
> mpn/mips64/dmultu and put the r6 code into mpn/mips64/nodmultu.
>
> (As a side note, I have been planning to move things around a bit,
> creating mpn/x86/32 and mpn/x86/64 with the contents of mpn/x86 and
> mpn/x86_64, respectively. SImilarly for powerpc32 and powerpc64,
> sparc32 and sparc64, etc. Common code between 32-bit and 64-bit limbs
> will live in the shared directory (mpn/x86, mpn/powerpc, mpn/sparc,
> etc). There is a good amount of such common code already, which is
> shared in an ugly manner.)
OK, so what I did was to create a mips32r6 directory under mips32 and a
mips64r6 directory under mips64 and put copies of the routines that had
to be changed for r6 in those directories. I have done test builds for
various MIPS targets and verified that the non-r6 code has not changed.
For the new r6 stuff I have verified that it all builds but I haven't
tested the changes with 'make check'.
Is there a way to do 'make check' with a simulator or a remote system?
I usually build MIPS code using a cross compiler on an x86 Linux box and
that is what I did to build GMP (using --build=x86_64-unknown-linux-gnu
--host=mips-img-linux-gnu or some other host depending on what flavor of
MIPS I wanted to build). I was hoping I could run 'make check' on the
x86 box and have it run tests via a simulator. That makes it easier to
build and test multiple MIPS architectures.
I tweaked the GMP configure script to recognize mips*-mti-* and
mips*-img-* targets, these hosts/targets exist in GCC and binutils as
names to use for cross compilers targeting MIPS (mti for pre-r6, img for
r6).
I have attached the patch as it currently exists to this email so people
could look it over.
Steve Ellcey
sell...@imgtec.com
diff -r 2ff56d3c5dfe configure.ac
--- a/configure.ac Wed Aug 27 11:24:26 2014 +0200
+++ b/configure.ac Thu Feb 05 14:27:13 2015 -0800
@@ -907,27 +907,41 @@
gcc_cflags_optlist="abi"
gcc_cflags_abi="-mabi=32"
gcc_testlist="gcc-mips-o32"
- path="mips32"
+ case $host in
+ mips32r6 | mips*-img-*)
+ path="mips32/mips32r6 mips32" ;;
+ *)
+ path="mips32" ;;
+ esac
cc_cflags="-O2 -o32" # no -g, it disables all optimizations
# this suits both mips32 and mips64
GMP_INCLUDE_MPN(mips32/mips-defs.m4)
case $host in
- [mips64*-*-* | mips*-*-irix[6789]*])
+ [mips64*-*-* | mips*-mti-* | mips*-img-* | mips*-*-irix[6789]*])
abilist="n32 64 o32"
cclist_n32="gcc cc"
gcc_n32_cflags="$gcc_cflags -mabi=n32"
cc_n32_cflags="-O2 -n32" # no -g, it disables all optimizations
limb_n32=longlong
- path_n32="mips64"
cclist_64="gcc cc"
gcc_64_cflags="$gcc_cflags -mabi=64"
gcc_64_ldflags="-Wc,-mabi=64"
cc_64_cflags="-O2 -64" # no -g, it disables all optimizations
cc_64_ldflags="-Wc,-64"
- path_64="mips64"
+
+ case $host in
+ mips64r6 | mips*-img-*)
+ path_n32="mips64/mips64r6 mips64"
+ path_64="mips64/mips64r6 mips64"
+ ;;
+ *)
+ path_n32="mips64"
+ path_64="mips64"
+ ;;
+ esac
;;
esac
;;
diff -r 2ff56d3c5dfe mpn/mips32/mips32r6/addmul_1.asm
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/mips32/mips32r6/addmul_1.asm Thu Feb 05 14:27:13 2015 -0800
@@ -0,0 +1,104 @@
+dnl MIPS32 mpn_addmul_1 -- Multiply a limb vector with a single limb and add
+dnl the product to a second limb vector.
+
+dnl Copyright 1992, 1994, 1996, 2000, 2002 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 INPUT PARAMETERS
+C res_ptr $4
+C s1_ptr $5
+C size $6
+C s2_limb $7
+
+ASM_START()
+PROLOGUE(mpn_addmul_1)
+
+C feed-in phase 0
+ lw $8,0($5)
+
+C feed-in phase 1
+ addiu $5,$5,4
+ mulu $11,$8,$7
+ muhu $12,$8,$7
+
+ addiu $6,$6,-1
+ beq $6,$0,$LC0
+ move $2,$0 C zero cy2
+
+ addiu $6,$6,-1
+ beq $6,$0,$LC1
+ lw $8,0($5) C load new s1 limb as early as possible
+
+Loop: lw $10,0($4)
+ move $3,$11
+ move $9,$12
+ addiu $5,$5,4
+ addu $3,$3,$2 C add old carry limb to low product limb
+ mulu $11,$8,$7
+ muhu $12,$8,$7
+ lw $8,0($5) C load new s1 limb as early as possible
+ addiu $6,$6,-1 C decrement loop counter
+ sltu $2,$3,$2 C carry from previous addition -> $2
+ addu $3,$10,$3
+ sltu $10,$3,$10
+ addu $2,$2,$10
+ sw $3,0($4)
+ addiu $4,$4,4
+ bne $6,$0,Loop
+ addu $2,$9,$2 C add high product limb and carry from addition
+
+C wind-down phase 1
+$LC1: lw $10,0($4)
+ move $3,$11
+ move $9,$12
+ addu $3,$3,$2
+ sltu $2,$3,$2
+ mulu $11,$8,$7
+ muhu $12,$8,$7
+ addu $3,$10,$3
+ sltu $10,$3,$10
+ addu $2,$2,$10
+ sw $3,0($4)
+ addiu $4,$4,4
+ addu $2,$9,$2 C add high product limb and carry from addition
+
+C wind-down phase 0
+$LC0: lw $10,0($4)
+ move $3,$11
+ move $9,$12
+ addu $3,$3,$2
+ sltu $2,$3,$2
+ addu $3,$10,$3
+ sltu $10,$3,$10
+ addu $2,$2,$10
+ sw $3,0($4)
+ j $31
+ addu $2,$9,$2 C add high product limb and carry from addition
+EPILOGUE(mpn_addmul_1)
diff -r 2ff56d3c5dfe mpn/mips32/mips32r6/mul_1.asm
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/mips32/mips32r6/mul_1.asm Thu Feb 05 14:27:13 2015 -0800
@@ -0,0 +1,92 @@
+dnl MIPS32 mpn_mul_1 -- Multiply a limb vector with a single limb and store
+dnl the product in a second limb vector.
+
+dnl Copyright 1992, 1994, 1996, 2000, 2002 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 INPUT PARAMETERS
+C res_ptr $4
+C s1_ptr $5
+C size $6
+C s2_limb $7
+
+ASM_START()
+PROLOGUE(mpn_mul_1)
+
+C feed-in phase 0
+ lw $8,0($5)
+
+C feed-in phase 1
+ addiu $5,$5,4
+ mulu $11,$8,$7
+ muhu $12,$8,$7
+
+ addiu $6,$6,-1
+ beq $6,$0,$LC0
+ move $2,$0 C zero cy2
+
+ addiu $6,$6,-1
+ beq $6,$0,$LC1
+ lw $8,0($5) C load new s1 limb as early as possible
+
+Loop: move $10,$11
+ move $9,$12
+ addiu $5,$5,4
+ addu $10,$10,$2 C add old carry limb to low product limb
+ mulu $11,$8,$7
+ muhu $12,$8,$7
+ lw $8,0($5) C load new s1 limb as early as possible
+ addiu $6,$6,-1 C decrement loop counter
+ sltu $2,$10,$2 C carry from previous addition -> $2
+ sw $10,0($4)
+ addiu $4,$4,4
+ bne $6,$0,Loop
+ addu $2,$9,$2 C add high product limb and carry from addition
+
+C wind-down phase 1
+$LC1: move $10,$11
+ move $9,$12
+ addu $10,$10,$2
+ sltu $2,$10,$2
+ mulu $11,$8,$7
+ muhu $12,$8,$7
+ sw $10,0($4)
+ addiu $4,$4,4
+ addu $2,$9,$2 C add high product limb and carry from addition
+
+C wind-down phase 0
+$LC0: move $10,$11
+ move $9,$12
+ addu $10,$10,$2
+ sltu $2,$10,$2
+ sw $10,0($4)
+ j $31
+ addu $2,$9,$2 C add high product limb and carry from addition
+EPILOGUE(mpn_mul_1)
diff -r 2ff56d3c5dfe mpn/mips32/mips32r6/submul_1.asm
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/mips32/mips32r6/submul_1.asm Thu Feb 05 14:27:13 2015 -0800
@@ -0,0 +1,104 @@
+dnl MIPS32 mpn_submul_1 -- Multiply a limb vector with a single limb and
+dnl subtract the product from a second limb vector.
+
+dnl Copyright 1992, 1994, 1996, 2000, 2002 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 INPUT PARAMETERS
+C res_ptr $4
+C s1_ptr $5
+C size $6
+C s2_limb $7
+
+ASM_START()
+PROLOGUE(mpn_submul_1)
+
+C feed-in phase 0
+ lw $8,0($5)
+
+C feed-in phase 1
+ addiu $5,$5,4
+ mulu $11,$8,$7
+ muhu $12,$8,$7
+
+ addiu $6,$6,-1
+ beq $6,$0,$LC0
+ move $2,$0 C zero cy2
+
+ addiu $6,$6,-1
+ beq $6,$0,$LC1
+ lw $8,0($5) C load new s1 limb as early as possible
+
+Loop: lw $10,0($4)
+ move $3,$11
+ move $9,$12
+ addiu $5,$5,4
+ addu $3,$3,$2 C add old carry limb to low product limb
+ mulu $11,$8,$7
+ muhu $12,$8,$7
+ lw $8,0($5) C load new s1 limb as early as possible
+ addiu $6,$6,-1 C decrement loop counter
+ sltu $2,$3,$2 C carry from previous addition -> $2
+ subu $3,$10,$3
+ sgtu $10,$3,$10
+ addu $2,$2,$10
+ sw $3,0($4)
+ addiu $4,$4,4
+ bne $6,$0,Loop
+ addu $2,$9,$2 C add high product limb and carry from addition
+
+C wind-down phase 1
+$LC1: lw $10,0($4)
+ move $3,$11
+ move $9,$12
+ addu $3,$3,$2
+ sltu $2,$3,$2
+ mulu $11,$8,$7
+ muhu $12,$8,$7
+ subu $3,$10,$3
+ sgtu $10,$3,$10
+ addu $2,$2,$10
+ sw $3,0($4)
+ addiu $4,$4,4
+ addu $2,$9,$2 C add high product limb and carry from addition
+
+C wind-down phase 0
+$LC0: lw $10,0($4)
+ move $3,$11
+ move $9,$12
+ addu $3,$3,$2
+ sltu $2,$3,$2
+ subu $3,$10,$3
+ sgtu $10,$3,$10
+ addu $2,$2,$10
+ sw $3,0($4)
+ j $31
+ addu $2,$9,$2 C add high product limb and carry from addition
+EPILOGUE(mpn_submul_1)
diff -r 2ff56d3c5dfe mpn/mips32/mips32r6/umul.asm
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/mips32/mips32r6/umul.asm Thu Feb 05 14:27:13 2015 -0800
@@ -0,0 +1,44 @@
+dnl MIPS32 umul_ppmm -- longlong.h support.
+
+dnl Copyright 1999, 2002 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 INPUT PARAMETERS
+C plp $4
+C u $5
+C v $6
+
+ASM_START()
+PROLOGUE(mpn_umul_ppmm)
+ mulu $3,$5,$6
+ muhu $2,$5,$6
+ j $31
+ sw $3,0($4)
+EPILOGUE(mpn_umul_ppmm)
diff -r 2ff56d3c5dfe mpn/mips64/mips64r6/addmul_1.asm
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/mips64/mips64r6/addmul_1.asm Thu Feb 05 14:27:13 2015 -0800
@@ -0,0 +1,104 @@
+dnl MIPS64 mpn_addmul_1 -- Multiply a limb vector with a single limb and add
+dnl the product to a second limb vector.
+
+dnl Copyright 1992, 1994, 1995, 2000-2002 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 INPUT PARAMETERS
+C res_ptr $4
+C s1_ptr $5
+C size $6
+C s2_limb $7
+
+ASM_START()
+PROLOGUE(mpn_addmul_1)
+
+C feed-in phase 0
+ ld $8,0($5)
+
+C feed-in phase 1
+ daddiu $5,$5,8
+ dmulu $11,$8,$7
+ dmuhu $12,$8,$7
+
+ daddiu $6,$6,-1
+ beq $6,$0,$LC0
+ move $2,$0 C zero cy2
+
+ daddiu $6,$6,-1
+ beq $6,$0,$LC1
+ ld $8,0($5) C load new s1 limb as early as possible
+
+Loop: ld $10,0($4)
+ move $3,$11
+ move $9,$12
+ daddiu $5,$5,8
+ daddu $3,$3,$2 C add old carry limb to low product limb
+ dmulu $11,$8,$7
+ dmuhu $12,$8,$7
+ ld $8,0($5) C load new s1 limb as early as possible
+ daddiu $6,$6,-1 C decrement loop counter
+ sltu $2,$3,$2 C carry from previous addition -> $2
+ daddu $3,$10,$3
+ sltu $10,$3,$10
+ daddu $2,$2,$10
+ sd $3,0($4)
+ daddiu $4,$4,8
+ bne $6,$0,Loop
+ daddu $2,$9,$2 C add high product limb and carry from addition
+
+C wind-down phase 1
+$LC1: ld $10,0($4)
+ move $3,$11
+ move $9,$12
+ daddu $3,$3,$2
+ sltu $2,$3,$2
+ dmulu $11,$8,$7
+ dmuhu $12,$8,$7
+ daddu $3,$10,$3
+ sltu $10,$3,$10
+ daddu $2,$2,$10
+ sd $3,0($4)
+ daddiu $4,$4,8
+ daddu $2,$9,$2 C add high product limb and carry from addition
+
+C wind-down phase 0
+$LC0: ld $10,0($4)
+ move $3,$11
+ move $9,$12
+ daddu $3,$3,$2
+ sltu $2,$3,$2
+ daddu $3,$10,$3
+ sltu $10,$3,$10
+ daddu $2,$2,$10
+ sd $3,0($4)
+ j $31
+ daddu $2,$9,$2 C add high product limb and carry from addition
+EPILOGUE(mpn_addmul_1)
diff -r 2ff56d3c5dfe mpn/mips64/mips64r6/mul_1.asm
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/mips64/mips64r6/mul_1.asm Thu Feb 05 14:27:13 2015 -0800
@@ -0,0 +1,95 @@
+dnl MIPS64 mpn_mul_1 -- Multiply a limb vector with a single limb and store
+dnl the product in a second limb vector.
+
+dnl Copyright 1992, 1994, 1995, 2000-2002 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 INPUT PARAMETERS
+C res_ptr $4
+C s1_ptr $5
+C size $6
+C s2_limb $7
+
+ASM_START()
+PROLOGUE(mpn_mul_1)
+
+C feed-in phase 0
+ ld $8,0($5)
+
+C feed-in phase 1
+ daddiu $5,$5,8
+ dmulu $11,$8,$7
+ dmuhu $12,$8,$7
+
+ daddiu $6,$6,-1
+ beq $6,$0,$LC0
+ move $2,$0 C zero cy2
+
+ daddiu $6,$6,-1
+ beq $6,$0,$LC1
+ ld $8,0($5) C load new s1 limb as early as possible
+
+Loop: nop
+ move $10,$11
+ move $9,$12
+ daddiu $5,$5,8
+ daddu $10,$10,$2 C add old carry limb to low product limb
+ dmulu $11,$8,$7
+ dmuhu $12,$8,$7
+ ld $8,0($5) C load new s1 limb as early as possible
+ daddiu $6,$6,-1 C decrement loop counter
+ sltu $2,$10,$2 C carry from previous addition -> $2
+ nop
+ nop
+ sd $10,0($4)
+ daddiu $4,$4,8
+ bne $6,$0,Loop
+ daddu $2,$9,$2 C add high product limb and carry from addition
+
+C wind-down phase 1
+$LC1: move $10,$11
+ move $9,$12
+ daddu $10,$10,$2
+ sltu $2,$10,$2
+ dmulu $11,$8,$7
+ dmuhu $12,$8,$7
+ sd $10,0($4)
+ daddiu $4,$4,8
+ daddu $2,$9,$2 C add high product limb and carry from addition
+
+C wind-down phase 0
+$LC0: move $10,$11
+ move $9,$12
+ daddu $10,$10,$2
+ sltu $2,$10,$2
+ sd $10,0($4)
+ j $31
+ daddu $2,$9,$2 C add high product limb and carry from addition
+EPILOGUE(mpn_mul_1)
diff -r 2ff56d3c5dfe mpn/mips64/mips64r6/sqr_diagonal.asm
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/mips64/mips64r6/sqr_diagonal.asm Thu Feb 05 14:27:13 2015 -0800
@@ -0,0 +1,80 @@
+dnl MIPS64 mpn_sqr_diagonal.
+
+dnl Copyright 2001, 2002 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/.
+
+
+dnl INPUT PARAMETERS
+dnl rp $4
+dnl up $5
+dnl n $6
+
+include(`../config.m4')
+
+ASM_START()
+PROLOGUE(mpn_sqr_diagonal)
+ ld r8,0(r5)
+ daddiu r6,r6,-2
+ dmulu r11,r8,r8
+ dmuhu r12,r8,r8
+ bltz r6,$Lend1
+ nop
+ ld r8,8(r5)
+ beq r6,r0,$Lend2
+ nop
+
+$Loop: move r10,r11
+ move r9,r12
+ daddiu r6,r6,-1
+ sd r10,0(r4)
+ sd r9,8(r4)
+ dmulu r11,r8,r8
+ dmuhu r12,r8,r8
+ ld r8,16(r5)
+ daddiu r5,r5,8
+ bne r6,r0,$Loop
+ daddiu r4,r4,16
+
+$Lend2: move r10,r11
+ move r9,r12
+ sd r10,0(r4)
+ sd r9,8(r4)
+ dmulu r11,r8,r8
+ dmuhu r12,r8,r8
+ move r10,r11
+ move r9,r12
+ sd r10,16(r4)
+ j r31
+ sd r9,24(r4)
+
+$Lend1: move r10,r11
+ move r9,r12
+ sd r10,0(r4)
+ j r31
+ sd r9,8(r4)
+EPILOGUE(mpn_sqr_diagonal)
diff -r 2ff56d3c5dfe mpn/mips64/mips64r6/submul_1.asm
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/mips64/mips64r6/submul_1.asm Thu Feb 05 14:27:13 2015 -0800
@@ -0,0 +1,104 @@
+dnl MIPS64 mpn_submul_1 -- Multiply a limb vector with a single limb and
+dnl subtract the product from a second limb vector.
+
+dnl Copyright 1992, 1994, 1995, 2000-2002 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 INPUT PARAMETERS
+C res_ptr $4
+C s1_ptr $5
+C size $6
+C s2_limb $7
+
+ASM_START()
+PROLOGUE(mpn_submul_1)
+
+C feed-in phase 0
+ ld $8,0($5)
+
+C feed-in phase 1
+ daddiu $5,$5,8
+ dmulu $11,$8,$7
+ dmuhu $12,$8,$7
+
+ daddiu $6,$6,-1
+ beq $6,$0,$LC0
+ move $2,$0 C zero cy2
+
+ daddiu $6,$6,-1
+ beq $6,$0,$LC1
+ ld $8,0($5) C load new s1 limb as early as possible
+
+Loop: ld $10,0($4)
+ move $3,$11
+ move $9,$12
+ daddiu $5,$5,8
+ daddu $3,$3,$2 C add old carry limb to low product limb
+ dmulu $11,$8,$7
+ dmuhu $12,$8,$7
+ ld $8,0($5) C load new s1 limb as early as possible
+ daddiu $6,$6,-1 C decrement loop counter
+ sltu $2,$3,$2 C carry from previous addition -> $2
+ dsubu $3,$10,$3
+ sgtu $10,$3,$10
+ daddu $2,$2,$10
+ sd $3,0($4)
+ daddiu $4,$4,8
+ bne $6,$0,Loop
+ daddu $2,$9,$2 C add high product limb and carry from addition
+
+C wind-down phase 1
+$LC1: ld $10,0($4)
+ move $3,$11
+ move $9,$12
+ daddu $3,$3,$2
+ sltu $2,$3,$2
+ dmulu $11,$8,$7
+ dmuhu $12,$8,$7
+ dsubu $3,$10,$3
+ sgtu $10,$3,$10
+ daddu $2,$2,$10
+ sd $3,0($4)
+ daddiu $4,$4,8
+ daddu $2,$9,$2 C add high product limb and carry from addition
+
+C wind-down phase 0
+$LC0: ld $10,0($4)
+ move $3,$11
+ move $9,$12
+ daddu $3,$3,$2
+ sltu $2,$3,$2
+ dsubu $3,$10,$3
+ sgtu $10,$3,$10
+ daddu $2,$2,$10
+ sd $3,0($4)
+ j $31
+ daddu $2,$9,$2 C add high product limb and carry from addition
+EPILOGUE(mpn_submul_1)
diff -r 2ff56d3c5dfe mpn/mips64/mips64r6/umul.asm
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mpn/mips64/mips64r6/umul.asm Thu Feb 05 14:27:13 2015 -0800
@@ -0,0 +1,44 @@
+dnl MIPS64 umul_ppmm -- longlong.h support.
+
+dnl Copyright 2002 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 INPUT PARAMETERS
+C plp $4
+C u $5
+C v $6
+
+ASM_START()
+PROLOGUE(mpn_umul_ppmm)
+ dmulu $3,$5,$6
+ dmuhu $2,$5,$6
+ j $31
+ sd $3,0($4)
+EPILOGUE(mpn_umul_ppmm)
_______________________________________________
gmp-devel mailing list
gmp-devel@gmplib.org
https://gmplib.org/mailman/listinfo/gmp-devel
