2019-03-22 23:33:59 +08:00
|
|
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
2013-05-30 23:39:35 +08:00
|
|
|
; RUN: llc < %s -mtriple=x86_64-linux-gnu -mcpu=atom | FileCheck %s
|
2010-06-10 04:30:22 +08:00
|
|
|
; <rdar://problem/8006248>
|
|
|
|
|
|
2013-05-30 21:19:42 +08:00
|
|
|
; This randomly started passing after an unrelated change, if it fails again it
|
|
|
|
|
; might be worth looking at PR12324: misched bringup.
|
|
|
|
|
|
2010-06-10 04:30:22 +08:00
|
|
|
@llvm.used = appending global [1 x i8*] [i8* bitcast (void ([40 x i16]*, i32*, i16**, i64*)* @func to i8*)], section "llvm.metadata"
|
|
|
|
|
|
|
|
|
|
define void @func([40 x i16]* %a, i32* %b, i16** %c, i64* %d) nounwind {
|
2019-03-22 23:33:59 +08:00
|
|
|
; CHECK-LABEL: func:
|
|
|
|
|
; CHECK: # %bb.0: # %entry
|
|
|
|
|
; CHECK-NEXT: movslq (%rsi), %rax
|
|
|
|
|
; CHECK-NEXT: movl $4, %esi
|
|
|
|
|
; CHECK-NEXT: subq %rax, %rsi
|
|
|
|
|
; CHECK-NEXT: movq (%rdx), %rax
|
|
|
|
|
; CHECK-NEXT: movswl 8(%rdi), %edx
|
|
|
|
|
; CHECK-NEXT: movswl (%rax,%rsi,2), %eax
|
|
|
|
|
; CHECK-NEXT: movl $1, %esi
|
|
|
|
|
; CHECK-NEXT: imull %edx, %eax
|
|
|
|
|
; CHECK-NEXT: xorl %edx, %edx
|
|
|
|
|
; CHECK-NEXT: addl $2138875574, %eax # imm = 0x7F7CA6B6
|
|
|
|
|
; CHECK-NEXT: cmpl $-8608074, %eax # imm = 0xFF7CA6B6
|
[DAGCombiner][X86][AArch64][AMDGPU] (x + C) - y -> (x - y) + C fold. Try 3
Summary:
The main motivation is shown by all these `neg` instructions that are now created.
In particular, the `@reg32_lshr_by_negated_unfolded_sub_b` test.
AArch64 test changes all look good (`neg` created), or neutral.
X86 changes look neutral (vectors), or good (`neg` / `xor eax, eax` created).
I'm not sure about `X86/ragreedy-hoist-spill.ll`, it looks like the spill
is now hoisted into preheader (which should still be good?),
2 4-byte reloads become 1 8-byte reload, and are elsewhere,
but i'm not sure how that affects that loop.
I'm unable to interpret AMDGPU change, looks neutral-ish?
This is hopefully a step towards solving [[ https://bugs.llvm.org/show_bug.cgi?id=41952 | PR41952 ]].
https://rise4fun.com/Alive/pkdq (we are missing more patterns, i'll submit them later)
This is a recommit, originally committed in rL361852, but reverted
to investigate test-suite compile-time hangs, and then reverted in
rL362109 to fix missing constant folds that were causing
endless combine loops.
Reviewers: craig.topper, RKSimon, spatel, arsenm
Reviewed By: RKSimon
Subscribers: bjope, qcolombet, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, javed.absar, dstuttard, tpr, t-tye, kristof.beyls, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D62223
llvm-svn: 362142
2019-05-31 04:36:54 +08:00
|
|
|
; CHECK-NEXT: movslq %eax, %rdi
|
2019-03-22 23:33:59 +08:00
|
|
|
; CHECK-NEXT: setl %dl
|
|
|
|
|
; CHECK-NEXT: cmpl $2138875573, %eax # imm = 0x7F7CA6B5
|
[DAGCombiner][X86][AArch64][AMDGPU] (x + C) - y -> (x - y) + C fold. Try 3
Summary:
The main motivation is shown by all these `neg` instructions that are now created.
In particular, the `@reg32_lshr_by_negated_unfolded_sub_b` test.
AArch64 test changes all look good (`neg` created), or neutral.
X86 changes look neutral (vectors), or good (`neg` / `xor eax, eax` created).
I'm not sure about `X86/ragreedy-hoist-spill.ll`, it looks like the spill
is now hoisted into preheader (which should still be good?),
2 4-byte reloads become 1 8-byte reload, and are elsewhere,
but i'm not sure how that affects that loop.
I'm unable to interpret AMDGPU change, looks neutral-ish?
This is hopefully a step towards solving [[ https://bugs.llvm.org/show_bug.cgi?id=41952 | PR41952 ]].
https://rise4fun.com/Alive/pkdq (we are missing more patterns, i'll submit them later)
This is a recommit, originally committed in rL361852, but reverted
to investigate test-suite compile-time hangs, and then reverted in
rL362109 to fix missing constant folds that were causing
endless combine loops.
Reviewers: craig.topper, RKSimon, spatel, arsenm
Reviewed By: RKSimon
Subscribers: bjope, qcolombet, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, javed.absar, dstuttard, tpr, t-tye, kristof.beyls, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D62223
llvm-svn: 362142
2019-05-31 04:36:54 +08:00
|
|
|
; CHECK-NEXT: movq %rdi, %r8
|
2019-03-22 23:33:59 +08:00
|
|
|
; CHECK-NEXT: leal -1(%rdx,%rdx), %edx
|
|
|
|
|
; CHECK-NEXT: cmovlel %edx, %esi
|
[DAGCombiner][X86][AArch64][AMDGPU] (x + C) - y -> (x - y) + C fold. Try 3
Summary:
The main motivation is shown by all these `neg` instructions that are now created.
In particular, the `@reg32_lshr_by_negated_unfolded_sub_b` test.
AArch64 test changes all look good (`neg` created), or neutral.
X86 changes look neutral (vectors), or good (`neg` / `xor eax, eax` created).
I'm not sure about `X86/ragreedy-hoist-spill.ll`, it looks like the spill
is now hoisted into preheader (which should still be good?),
2 4-byte reloads become 1 8-byte reload, and are elsewhere,
but i'm not sure how that affects that loop.
I'm unable to interpret AMDGPU change, looks neutral-ish?
This is hopefully a step towards solving [[ https://bugs.llvm.org/show_bug.cgi?id=41952 | PR41952 ]].
https://rise4fun.com/Alive/pkdq (we are missing more patterns, i'll submit them later)
This is a recommit, originally committed in rL361852, but reverted
to investigate test-suite compile-time hangs, and then reverted in
rL362109 to fix missing constant folds that were causing
endless combine loops.
Reviewers: craig.topper, RKSimon, spatel, arsenm
Reviewed By: RKSimon
Subscribers: bjope, qcolombet, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, javed.absar, dstuttard, tpr, t-tye, kristof.beyls, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D62223
llvm-svn: 362142
2019-05-31 04:36:54 +08:00
|
|
|
; CHECK-NEXT: subq %rax, %r8
|
2019-03-22 23:33:59 +08:00
|
|
|
; CHECK-NEXT: xorl %eax, %eax
|
|
|
|
|
; CHECK-NEXT: cmpl $1, %esi
|
[DAGCombiner][X86][AArch64][AMDGPU] (x + C) - y -> (x - y) + C fold. Try 3
Summary:
The main motivation is shown by all these `neg` instructions that are now created.
In particular, the `@reg32_lshr_by_negated_unfolded_sub_b` test.
AArch64 test changes all look good (`neg` created), or neutral.
X86 changes look neutral (vectors), or good (`neg` / `xor eax, eax` created).
I'm not sure about `X86/ragreedy-hoist-spill.ll`, it looks like the spill
is now hoisted into preheader (which should still be good?),
2 4-byte reloads become 1 8-byte reload, and are elsewhere,
but i'm not sure how that affects that loop.
I'm unable to interpret AMDGPU change, looks neutral-ish?
This is hopefully a step towards solving [[ https://bugs.llvm.org/show_bug.cgi?id=41952 | PR41952 ]].
https://rise4fun.com/Alive/pkdq (we are missing more patterns, i'll submit them later)
This is a recommit, originally committed in rL361852, but reverted
to investigate test-suite compile-time hangs, and then reverted in
rL362109 to fix missing constant folds that were causing
endless combine loops.
Reviewers: craig.topper, RKSimon, spatel, arsenm
Reviewed By: RKSimon
Subscribers: bjope, qcolombet, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, javed.absar, dstuttard, tpr, t-tye, kristof.beyls, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D62223
llvm-svn: 362142
2019-05-31 04:36:54 +08:00
|
|
|
; CHECK-NEXT: cmovneq %rax, %r8
|
|
|
|
|
; CHECK-NEXT: testl %edi, %edi
|
|
|
|
|
; CHECK-NEXT: cmovnsq %rax, %r8
|
|
|
|
|
; CHECK-NEXT: movq (%rcx), %rax
|
|
|
|
|
; CHECK-NEXT: subq %r8, %rdi
|
|
|
|
|
; CHECK-NEXT: leaq -2138875574(%rax,%rdi), %rax
|
2019-03-22 23:33:59 +08:00
|
|
|
; CHECK-NEXT: movq %rax, (%rcx)
|
|
|
|
|
; CHECK-NEXT: retq
|
2010-06-10 04:30:22 +08:00
|
|
|
entry:
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%tmp103 = getelementptr inbounds [40 x i16], [40 x i16]* %a, i64 0, i64 4
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp104 = load i16, i16* %tmp103, align 2
|
2010-06-10 04:30:22 +08:00
|
|
|
%tmp105 = sext i16 %tmp104 to i32
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp106 = load i32, i32* %b, align 4
|
2010-06-10 04:30:22 +08:00
|
|
|
%tmp107 = sub nsw i32 4, %tmp106
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp108 = load i16*, i16** %c, align 8
|
2010-06-10 04:30:22 +08:00
|
|
|
%tmp109 = sext i32 %tmp107 to i64
|
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction
One of several parallel first steps to remove the target type of pointers,
replacing them with a single opaque pointer type.
This adds an explicit type parameter to the gep instruction so that when the
first parameter becomes an opaque pointer type, the type to gep through is
still available to the instructions.
* This doesn't modify gep operators, only instructions (operators will be
handled separately)
* Textual IR changes only. Bitcode (including upgrade) and changing the
in-memory representation will be in separate changes.
* geps of vectors are transformed as:
getelementptr <4 x float*> %x, ...
->getelementptr float, <4 x float*> %x, ...
Then, once the opaque pointer type is introduced, this will ultimately look
like:
getelementptr float, <4 x ptr> %x
with the unambiguous interpretation that it is a vector of pointers to float.
* address spaces remain on the pointer, not the type:
getelementptr float addrspace(1)* %x
->getelementptr float, float addrspace(1)* %x
Then, eventually:
getelementptr float, ptr addrspace(1) %x
Importantly, the massive amount of test case churn has been automated by
same crappy python code. I had to manually update a few test cases that
wouldn't fit the script's model (r228970,r229196,r229197,r229198). The
python script just massages stdin and writes the result to stdout, I
then wrapped that in a shell script to handle replacing files, then
using the usual find+xargs to migrate all the files.
update.py:
import fileinput
import sys
import re
ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))")
def conv(match, line):
if not match:
return line
line = match.groups()[0]
if len(match.groups()[5]) == 0:
line += match.groups()[2]
line += match.groups()[3]
line += ", "
line += match.groups()[1]
line += "\n"
return line
for line in sys.stdin:
if line.find("getelementptr ") == line.find("getelementptr inbounds"):
if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("):
line = conv(re.match(ibrep, line), line)
elif line.find("getelementptr ") != line.find("getelementptr ("):
line = conv(re.match(normrep, line), line)
sys.stdout.write(line)
apply.sh:
for name in "$@"
do
python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name"
rm -f "$name.tmp"
done
The actual commands:
From llvm/src:
find test/ -name *.ll | xargs ./apply.sh
From llvm/src/tools/clang:
find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}"
From llvm/src/tools/polly:
find test/ -name *.ll | xargs ./apply.sh
After that, check-all (with llvm, clang, clang-tools-extra, lld,
compiler-rt, and polly all checked out).
The extra 'rm' in the apply.sh script is due to a few files in clang's test
suite using interesting unicode stuff that my python script was throwing
exceptions on. None of those files needed to be migrated, so it seemed
sufficient to ignore those cases.
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7636
llvm-svn: 230786
2015-02-28 03:29:02 +08:00
|
|
|
%tmp110 = getelementptr inbounds i16, i16* %tmp108, i64 %tmp109
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp111 = load i16, i16* %tmp110, align 1
|
2010-06-10 04:30:22 +08:00
|
|
|
%tmp112 = sext i16 %tmp111 to i32
|
|
|
|
|
%tmp = mul i32 355244649, %tmp112
|
|
|
|
|
%tmp1 = mul i32 %tmp, %tmp105
|
|
|
|
|
%tmp2 = add i32 %tmp1, 2138875574
|
|
|
|
|
%tmp3 = add i32 %tmp2, 1546991088
|
|
|
|
|
%tmp4 = mul i32 %tmp3, 2122487257
|
|
|
|
|
%tmp5 = icmp sge i32 %tmp4, 2138875574
|
|
|
|
|
%tmp6 = icmp slt i32 %tmp4, -8608074
|
|
|
|
|
%tmp7 = or i1 %tmp5, %tmp6
|
|
|
|
|
%outSign = select i1 %tmp7, i32 1, i32 -1
|
|
|
|
|
%tmp8 = icmp slt i32 %tmp4, 0
|
|
|
|
|
%tmp9 = icmp eq i32 %outSign, 1
|
|
|
|
|
%tmp10 = and i1 %tmp8, %tmp9
|
|
|
|
|
%tmp11 = sext i32 %tmp4 to i64
|
|
|
|
|
%tmp12 = add i64 %tmp11, 5089792279245435153
|
|
|
|
|
%tmp13 = sub i64 %tmp12, 2138875574
|
|
|
|
|
%tmp14 = zext i32 %tmp4 to i64
|
|
|
|
|
%tmp15 = sub i64 %tmp11, %tmp14
|
|
|
|
|
%tmp16 = select i1 %tmp10, i64 %tmp15, i64 0
|
|
|
|
|
%tmp17 = sub i64 %tmp13, %tmp16
|
|
|
|
|
%tmp18 = mul i64 %tmp17, 4540133155013554595
|
|
|
|
|
%tmp19 = sub i64 %tmp18, 5386586244038704851
|
|
|
|
|
%tmp20 = add i64 %tmp19, -1368057358110947217
|
|
|
|
|
%tmp21 = mul i64 %tmp20, -422037402840850817
|
2015-02-28 05:17:42 +08:00
|
|
|
%tmp115 = load i64, i64* %d, align 8
|
2010-06-10 04:30:22 +08:00
|
|
|
%alphaX = mul i64 468858157810230901, %tmp21
|
|
|
|
|
%alphaXbetaY = add i64 %alphaX, %tmp115
|
|
|
|
|
%transformed = add i64 %alphaXbetaY, 9040145182981852475
|
|
|
|
|
store i64 %transformed, i64* %d, align 8
|
|
|
|
|
ret void
|
|
|
|
|
}
|