Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add hardcoded flint_mpn_aors_n for ARM and x86 #2118

Open
wants to merge 13 commits into
base: main
Choose a base branch
from
Open

Add hardcoded flint_mpn_aors_n for ARM and x86 #2118

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
d09c98e
Add hardcoded flint_mpn_aors_n for ARM and x86
Nov 27, 2024
00ecdcb
Start on aorsrsh for x86
Nov 30, 2024
9ce9168
Add generation for hardcoded flint_mpn_addrsh
Dec 2, 2024
c806930
Also subrsh
Dec 2, 2024
62a6c20
Fixup
Dec 2, 2024
e63d4f7
fixup
Dec 2, 2024
2daf43a
Add corresponding C sources for aorsrsh
Dec 2, 2024
96786cd
Add tests for aorsrsh
Dec 2, 2024
65fadb4
blabla
Dec 2, 2024
877ec63
bla
Dec 2, 2024
a537b89
fixup
Dec 2, 2024
55dd138
fixup
Dec 2, 2024
9e7f462
Stash for aorsrsh for ARM64
Dec 9, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
bla
  • Loading branch information
Albin Ahlbäck committed Dec 2, 2024
commit 877ec63b6988c3685ffbe7edd66c0d46862f5a2b
2 changes: 1 addition & 1 deletion dev/gen_x86_aorsrsh.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,7 +119,7 @@ function aorsrsh(n::Int; is_add::Bool = true)
mov( s3, rp(ix))
elseif ix == n - 1
mov( ap(ix), s0)
sub( s1, s0)
sbb( s1, s0)
mov( s0, rp(ix))
else
mov( ap(ix), s3)
Expand Down
2 changes: 1 addition & 1 deletion src/mpn_extras/test/t-aorsrsh_n.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,7 +102,7 @@ TEST_FUNCTION_START(flint_mpn_aorsrsh_n, state)
result = (cf == cg && mpn_cmp(fp, gp, n) == 0);
if (!result)
TEST_FUNCTION_FAIL(
"%s:\n"
"function: %s\n"
"aliasing: %s\n"
"ix = %wd\n"
"n = %wd\n"
Expand Down
30 changes: 15 additions & 15 deletions src/mpn_extras/x86_64/broadwell/aorsrsh_hard.asm
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1066,7 +1066,7 @@ PROLOGUE(flint_mpn_subrsh_2)
sub s2, tnc
mov tnc, 0*8(rp)
mov 1*8(ap), s0
sub s1, s0
sbb s1, s0
mov s0, 1*8(rp)
setc R8(sx)
ret
Expand Down Expand Up @@ -1094,7 +1094,7 @@ PROLOGUE(flint_mpn_subrsh_3)
sbb s2, s3
mov s3, 1*8(rp)
mov 2*8(ap), s0
sub s1, s0
sbb s1, s0
mov s0, 2*8(rp)
pop s3
setc R8(sx)
Expand Down Expand Up @@ -1130,7 +1130,7 @@ PROLOGUE(flint_mpn_subrsh_4)
sbb s2, s3
mov s3, 2*8(rp)
mov 3*8(ap), s0
sub s1, s0
sbb s1, s0
mov s0, 3*8(rp)
pop s3
setc R8(sx)
Expand Down Expand Up @@ -1173,7 +1173,7 @@ PROLOGUE(flint_mpn_subrsh_5)
sbb s2, s3
mov s3, 3*8(rp)
mov 4*8(ap), s0
sub s1, s0
sbb s1, s0
mov s0, 4*8(rp)
pop s3
setc R8(sx)
Expand Down Expand Up @@ -1223,7 +1223,7 @@ PROLOGUE(flint_mpn_subrsh_6)
sbb s2, s3
mov s3, 4*8(rp)
mov 5*8(ap), s0
sub s1, s0
sbb s1, s0
mov s0, 5*8(rp)
pop s3
setc R8(sx)
Expand Down Expand Up @@ -1280,7 +1280,7 @@ PROLOGUE(flint_mpn_subrsh_7)
sbb s2, s3
mov s3, 5*8(rp)
mov 6*8(ap), s0
sub s1, s0
sbb s1, s0
mov s0, 6*8(rp)
pop s3
setc R8(sx)
Expand Down Expand Up @@ -1344,7 +1344,7 @@ PROLOGUE(flint_mpn_subrsh_8)
sbb s2, s3
mov s3, 6*8(rp)
mov 7*8(ap), s0
sub s1, s0
sbb s1, s0
mov s0, 7*8(rp)
pop s3
setc R8(sx)
Expand Down Expand Up @@ -1415,7 +1415,7 @@ PROLOGUE(flint_mpn_subrsh_9)
sbb s2, s3
mov s3, 7*8(rp)
mov 8*8(ap), s0
sub s1, s0
sbb s1, s0
mov s0, 8*8(rp)
pop s3
setc R8(sx)
Expand Down Expand Up @@ -1493,7 +1493,7 @@ PROLOGUE(flint_mpn_subrsh_10)
sbb s2, s3
mov s3, 8*8(rp)
mov 9*8(ap), s0
sub s1, s0
sbb s1, s0
mov s0, 9*8(rp)
pop s3
setc R8(sx)
Expand Down Expand Up @@ -1578,7 +1578,7 @@ PROLOGUE(flint_mpn_subrsh_11)
sbb s2, s3
mov s3, 9*8(rp)
mov 10*8(ap), s0
sub s1, s0
sbb s1, s0
mov s0, 10*8(rp)
pop s3
setc R8(sx)
Expand Down Expand Up @@ -1670,7 +1670,7 @@ PROLOGUE(flint_mpn_subrsh_12)
sbb s2, s3
mov s3, 10*8(rp)
mov 11*8(ap), s0
sub s1, s0
sbb s1, s0
mov s0, 11*8(rp)
pop s3
setc R8(sx)
Expand Down Expand Up @@ -1769,7 +1769,7 @@ PROLOGUE(flint_mpn_subrsh_13)
sbb s2, s3
mov s3, 11*8(rp)
mov 12*8(ap), s0
sub s1, s0
sbb s1, s0
mov s0, 12*8(rp)
pop s3
setc R8(sx)
Expand Down Expand Up @@ -1875,7 +1875,7 @@ PROLOGUE(flint_mpn_subrsh_14)
sbb s2, s3
mov s3, 12*8(rp)
mov 13*8(ap), s0
sub s1, s0
sbb s1, s0
mov s0, 13*8(rp)
pop s3
setc R8(sx)
Expand Down Expand Up @@ -1988,7 +1988,7 @@ PROLOGUE(flint_mpn_subrsh_15)
sbb s2, s3
mov s3, 13*8(rp)
mov 14*8(ap), s0
sub s1, s0
sbb s1, s0
mov s0, 14*8(rp)
pop s3
setc R8(sx)
Expand Down Expand Up @@ -2108,7 +2108,7 @@ PROLOGUE(flint_mpn_subrsh_16)
sbb s2, s3
mov s3, 14*8(rp)
mov 15*8(ap), s0
sub s1, s0
sbb s1, s0
mov s0, 15*8(rp)
pop s3
setc R8(sx)
Expand Down
Loading