maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/select.ll

404 lines
9.3 KiB
LLVM
Raw Normal View History

Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; RUN: llc < %s -mtriple=x86_64-apple-darwin10 -mcpu=generic | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-apple-darwin10 -mcpu=atom | FileCheck -check-prefix=ATOM %s
Change this to the correct PR number. llvm-svn: 91148
2009-12-12 04:09:21 +08:00
; PR5757
Fix the result type of SELECT nodes lowered from Select instructions with aggregate return values. This fixes PR5754. llvm-svn: 91145
2009-12-12 03:50:50 +08:00
%0 = type { i64, i32 }
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
define i32 @test1(%0* %p, %0* %q, i1 %r) nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%t0 = load %0, %0* %p
%t1 = load %0, %0* %q
Fix the result type of SELECT nodes lowered from Select instructions with aggregate return values. This fixes PR5754. llvm-svn: 91145
2009-12-12 03:50:50 +08:00
%t4 = select i1 %r, %0 %t0, %0 %t1
%t5 = extractvalue %0 %t4, 1
ret i32 %t5
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test1:
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
; CHECK: cmovneq %rdi, %rsi
; CHECK: movl (%rsi), %eax
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test1:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: cmovneq %rdi, %rsi
; ATOM: movl (%rsi), %eax
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
}
; PR2139
define i32 @test2() nounwind {
entry:
%tmp73 = tail call i1 @return_false() ; <i8> [#uses=1]
%g.0 = select i1 %tmp73, i16 0, i16 -480 ; <i16> [#uses=2]
%tmp7778 = sext i16 %g.0 to i32 ; <i32> [#uses=1]
%tmp80 = shl i32 %tmp7778, 3 ; <i32> [#uses=2]
%tmp87 = icmp sgt i32 %tmp80, 32767 ; <i1> [#uses=1]
br i1 %tmp87, label %bb90, label %bb91
bb90: ; preds = %bb84, %bb72
unreachable
bb91: ; preds = %bb84
ret i32 0
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test2:
Enable MI Sched for x86. This changes the SelectionDAG scheduling preference to source order. Soon, the SelectionDAG scheduler can be bypassed saving a nice chunk of compile time. Performance differences that result from this change are often a consequence of register coalescing. The register coalescer is far from perfect. Bugs can be filed for deficiencies. On x86 SandyBridge/Haswell, the source order schedule is often preserved, particularly for small blocks. Register pressure is generally improved over the SD scheduler's ILP mode. However, we are still able to handle large blocks that require latency hiding, unlike the SD scheduler's BURR mode. MI scheduler also attempts to discover the critical path in single-block loops and adjust heuristics accordingly. The MI scheduler relies on the new machine model. This is currently unimplemented for AVX, so we may not be generating the best code yet. Unit tests are updated so they don't depend on SD scheduling heuristics. llvm-svn: 192750
2013-10-16 07:33:07 +08:00
; CHECK: cmovnew
; CHECK: cwtl
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test2:
Enable MI Sched for x86. This changes the SelectionDAG scheduling preference to source order. Soon, the SelectionDAG scheduler can be bypassed saving a nice chunk of compile time. Performance differences that result from this change are often a consequence of register coalescing. The register coalescer is far from perfect. Bugs can be filed for deficiencies. On x86 SandyBridge/Haswell, the source order schedule is often preserved, particularly for small blocks. Register pressure is generally improved over the SD scheduler's ILP mode. However, we are still able to handle large blocks that require latency hiding, unlike the SD scheduler's BURR mode. MI scheduler also attempts to discover the critical path in single-block loops and adjust heuristics accordingly. The MI scheduler relies on the new machine model. This is currently unimplemented for AVX, so we may not be generating the best code yet. Unit tests are updated so they don't depend on SD scheduling heuristics. llvm-svn: 192750
2013-10-16 07:33:07 +08:00
; ATOM: cmovnew
; ATOM: cwtl
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
}
declare i1 @return_false()
;; Select between two floating point constants.
define float @test3(i32 %x) nounwind readnone {
entry:
%0 = icmp eq i32 %x, 0 ; <i1> [#uses=1]
%iftmp.0.0 = select i1 %0, float 4.200000e+01, float 2.300000e+01 ; <float> [#uses=1]
ret float %iftmp.0.0
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test3:
relax this to handle linux defaulting to -static. llvm-svn: 120930
2010-12-05 09:31:13 +08:00
; CHECK: movss {{.*}},4), %xmm0
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test3:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: movss {{.*}},4), %xmm0
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
}
define signext i8 @test4(i8* nocapture %P, double %F) nounwind readonly {
entry:
%0 = fcmp olt double %F, 4.200000e+01 ; <i1> [#uses=1]
%iftmp.0.0 = select i1 %0, i32 4, i32 0 ; <i32> [#uses=1]
[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
%1 = getelementptr i8, i8* %P, i32 %iftmp.0.0 ; <i8*> [#uses=1]
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%2 = load i8, i8* %1, align 1 ; <i8> [#uses=1]
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
ret i8 %2
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test4:
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
; CHECK: movsbl ({{.*}},4), %eax
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test4:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: movsbl ({{.*}},4), %eax
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
}
define void @test5(i1 %c, <2 x i16> %a, <2 x i16> %b, <2 x i16>* %p) nounwind {
%x = select i1 %c, <2 x i16> %a, <2 x i16> %b
store <2 x i16> %x, <2 x i16>* %p
ret void
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test5:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test5:
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
}
define void @test6(i32 %C, <4 x float>* %A, <4 x float>* %B) nounwind {
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%tmp = load <4 x float>, <4 x float>* %A ; <<4 x float>> [#uses=1]
%tmp3 = load <4 x float>, <4 x float>* %B ; <<4 x float>> [#uses=2]
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
%tmp9 = fmul <4 x float> %tmp3, %tmp3 ; <<4 x float>> [#uses=1]
%tmp.upgrd.1 = icmp eq i32 %C, 0 ; <i1> [#uses=1]
%iftmp.38.0 = select i1 %tmp.upgrd.1, <4 x float> %tmp9, <4 x float> %tmp ; <<4 x float>> [#uses=1]
store <4 x float> %iftmp.38.0, <4 x float>* %A
ret void
; Verify that the fmul gets sunk into the one part of the diamond where it is
; needed.
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test6:
Flip the new block-placement pass to be on by default. This is mostly to test the waters. I'd like to get results from FNT build bots and other bots running on non-x86 platforms. This feature has been pretty heavily tested over the last few months by me, and it fixes several of the execution time regressions caused by the inlining work by preventing inlining decisions from radically impacting block layout. I've seen very large improvements in yacr2 and ackermann benchmarks, along with the expected noise across all of the benchmark suite whenever code layout changes. I've analyzed all of the regressions and fixed them, or found them to be impossible to fix. See my email to llvmdev for more details. I'd like for this to be in 3.1 as it complements the inliner changes, but if any failures are showing up or anyone has concerns, it is just a flag flip and so can be easily turned off. I'm switching it on tonight to try and get at least one run through various folks' performance suites in case SPEC or something else has serious issues with it. I'll watch bots and revert if anything shows up. llvm-svn: 154816
2012-04-16 21:49:17 +08:00
; CHECK: je
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
; CHECK: ret
Flip the new block-placement pass to be on by default. This is mostly to test the waters. I'd like to get results from FNT build bots and other bots running on non-x86 platforms. This feature has been pretty heavily tested over the last few months by me, and it fixes several of the execution time regressions caused by the inlining work by preventing inlining decisions from radically impacting block layout. I've seen very large improvements in yacr2 and ackermann benchmarks, along with the expected noise across all of the benchmark suite whenever code layout changes. I've analyzed all of the regressions and fixed them, or found them to be impossible to fix. See my email to llvmdev for more details. I'd like for this to be in 3.1 as it complements the inliner changes, but if any failures are showing up or anyone has concerns, it is just a flag flip and so can be easily turned off. I'm switching it on tonight to try and get at least one run through various folks' performance suites in case SPEC or something else has serious issues with it. I'll watch bots and revert if anything shows up. llvm-svn: 154816
2012-04-16 21:49:17 +08:00
; CHECK: mulps
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
; CHECK: ret
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test6:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: je
; ATOM: ret
; ATOM: mulps
; ATOM: ret
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
}
; Select with fp80's
define x86_fp80 @test7(i32 %tmp8) nounwind {
%tmp9 = icmp sgt i32 %tmp8, -1 ; <i1> [#uses=1]
%retval = select i1 %tmp9, x86_fp80 0xK4005B400000000000000, x86_fp80 0xK40078700000000000000
ret x86_fp80 %retval
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test7:
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
; CHECK: leaq
; CHECK: fldt (%r{{.}}x,%r{{.}}x)
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test7:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: leaq
; ATOM: fldt (%r{{.}}x,%r{{.}}x)
merge some tests into select.ll and make them more specific. llvm-svn: 120928
2010-12-05 09:13:58 +08:00
}
; widening select v6i32 and then a sub
define void @test8(i1 %c, <6 x i32>* %dst.addr, <6 x i32> %src1,<6 x i32> %src2) nounwind {
%x = select i1 %c, <6 x i32> %src1, <6 x i32> %src2
%val = sub <6 x i32> %x, < i32 1, i32 1, i32 1, i32 1, i32 1, i32 1 >
store <6 x i32> %val, <6 x i32>* %dst.addr
ret void
test/CodeGen/X86/select.ll: remove spaces llvm-svn: 155840
2012-05-01 02:54:27 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test8:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test8:
Fix the result type of SELECT nodes lowered from Select instructions with aggregate return values. This fixes PR5754. llvm-svn: 91145
2009-12-12 03:50:50 +08:00
}
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
;; Test integer select between values and constants.
define i64 @test9(i64 %x, i64 %y) nounwind readnone ssp noredzone {
%cmp = icmp ne i64 %x, 0
%cond = select i1 %cmp, i64 %y, i64 -1
ret i64 %cond
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test9:
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
; CHECK: cmpq $1, %rdi
; CHECK: sbbq %rax, %rax
; CHECK: orq %rsi, %rax
; CHECK: ret
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test9:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: cmpq $1, %rdi
; ATOM: sbbq %rax, %rax
; ATOM: orq %rsi, %rax
; ATOM: ret
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
}
;; Same as test9
define i64 @test9a(i64 %x, i64 %y) nounwind readnone ssp noredzone {
%cmp = icmp eq i64 %x, 0
%cond = select i1 %cmp, i64 -1, i64 %y
ret i64 %cond
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test9a:
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
; CHECK: cmpq $1, %rdi
; CHECK: sbbq %rax, %rax
; CHECK: orq %rsi, %rax
; CHECK: ret
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test9a:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: cmpq $1, %rdi
; ATOM: sbbq %rax, %rax
; ATOM: orq %rsi, %rax
; ATOM: ret
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
}
define i64 @test9b(i64 %x, i64 %y) nounwind readnone ssp noredzone {
%cmp = icmp eq i64 %x, 0
%A = sext i1 %cmp to i64
%cond = or i64 %y, %A
ret i64 %cond
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test9b:
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
; CHECK: cmpq $1, %rdi
; CHECK: sbbq %rax, %rax
; CHECK: orq %rsi, %rax
; CHECK: ret
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test9b:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: cmpq $1, %rdi
; ATOM: sbbq %rax, %rax
; ATOM: orq %rsi, %rax
; ATOM: ret
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
}
;; Select between -1 and 1.
define i64 @test10(i64 %x, i64 %y) nounwind readnone ssp noredzone {
%cmp = icmp eq i64 %x, 0
%cond = select i1 %cmp, i64 -1, i64 1
ret i64 %cond
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test10:
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
; CHECK: cmpq $1, %rdi
; CHECK: sbbq %rax, %rax
; CHECK: orq $1, %rax
; CHECK: ret
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test10:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: cmpq $1, %rdi
; ATOM: sbbq %rax, %rax
; ATOM: orq $1, %rax
; ATOM: ret
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
}
generalize the previous check to handle -1 on either side of the select, inserting a not to compensate. Add a missing isZero check that I lost somehow. This improves codegen of: void *func(long count) { return new int[count]; } from: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] testq %rdx, %rdx ## encoding: [0x48,0x85,0xd2] movq $-1, %rdi ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff] cmoveq %rax, %rdi ## encoding: [0x48,0x0f,0x44,0xf8] jmp __Znam ## TAILCALL ## encoding: [0xeb,A] to: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] cmpq $1, %rdx ## encoding: [0x48,0x83,0xfa,0x01] sbbq %rdi, %rdi ## encoding: [0x48,0x19,0xff] notq %rdi ## encoding: [0x48,0xf7,0xd7] orq %rax, %rdi ## encoding: [0x48,0x09,0xc7] jmp __Znam ## TAILCALL ## encoding: [0xeb,A] llvm-svn: 120932
2010-12-05 10:00:51 +08:00
define i64 @test11(i64 %x, i64 %y) nounwind readnone ssp noredzone {
%cmp = icmp eq i64 %x, 0
%cond = select i1 %cmp, i64 %y, i64 -1
ret i64 %cond
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test11:
generalize the previous check to handle -1 on either side of the select, inserting a not to compensate. Add a missing isZero check that I lost somehow. This improves codegen of: void *func(long count) { return new int[count]; } from: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] testq %rdx, %rdx ## encoding: [0x48,0x85,0xd2] movq $-1, %rdi ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff] cmoveq %rax, %rdi ## encoding: [0x48,0x0f,0x44,0xf8] jmp __Znam ## TAILCALL ## encoding: [0xeb,A] to: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] cmpq $1, %rdx ## encoding: [0x48,0x83,0xfa,0x01] sbbq %rdi, %rdi ## encoding: [0x48,0x19,0xff] notq %rdi ## encoding: [0x48,0xf7,0xd7] orq %rax, %rdi ## encoding: [0x48,0x09,0xc7] jmp __Znam ## TAILCALL ## encoding: [0xeb,A] llvm-svn: 120932
2010-12-05 10:00:51 +08:00
; CHECK: cmpq $1, %rdi
; CHECK: sbbq %rax, %rax
; CHECK: notq %rax
; CHECK: orq %rsi, %rax
; CHECK: ret
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test11:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: cmpq $1, %rdi
; ATOM: sbbq %rax, %rax
; ATOM: notq %rax
; ATOM: orq %rsi, %rax
; ATOM: ret
generalize the previous check to handle -1 on either side of the select, inserting a not to compensate. Add a missing isZero check that I lost somehow. This improves codegen of: void *func(long count) { return new int[count]; } from: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] testq %rdx, %rdx ## encoding: [0x48,0x85,0xd2] movq $-1, %rdi ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff] cmoveq %rax, %rdi ## encoding: [0x48,0x0f,0x44,0xf8] jmp __Znam ## TAILCALL ## encoding: [0xeb,A] to: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] cmpq $1, %rdx ## encoding: [0x48,0x83,0xfa,0x01] sbbq %rdi, %rdi ## encoding: [0x48,0x19,0xff] notq %rdi ## encoding: [0x48,0xf7,0xd7] orq %rax, %rdi ## encoding: [0x48,0x09,0xc7] jmp __Znam ## TAILCALL ## encoding: [0xeb,A] llvm-svn: 120932
2010-12-05 10:00:51 +08:00
}
define i64 @test11a(i64 %x, i64 %y) nounwind readnone ssp noredzone {
%cmp = icmp ne i64 %x, 0
%cond = select i1 %cmp, i64 -1, i64 %y
ret i64 %cond
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test11a:
generalize the previous check to handle -1 on either side of the select, inserting a not to compensate. Add a missing isZero check that I lost somehow. This improves codegen of: void *func(long count) { return new int[count]; } from: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] testq %rdx, %rdx ## encoding: [0x48,0x85,0xd2] movq $-1, %rdi ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff] cmoveq %rax, %rdi ## encoding: [0x48,0x0f,0x44,0xf8] jmp __Znam ## TAILCALL ## encoding: [0xeb,A] to: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] cmpq $1, %rdx ## encoding: [0x48,0x83,0xfa,0x01] sbbq %rdi, %rdi ## encoding: [0x48,0x19,0xff] notq %rdi ## encoding: [0x48,0xf7,0xd7] orq %rax, %rdi ## encoding: [0x48,0x09,0xc7] jmp __Znam ## TAILCALL ## encoding: [0xeb,A] llvm-svn: 120932
2010-12-05 10:00:51 +08:00
; CHECK: cmpq $1, %rdi
; CHECK: sbbq %rax, %rax
; CHECK: notq %rax
; CHECK: orq %rsi, %rax
; CHECK: ret
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test11a:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: cmpq $1, %rdi
; ATOM: sbbq %rax, %rax
; ATOM: notq %rax
; ATOM: orq %rsi, %rax
; ATOM: ret
generalize the previous check to handle -1 on either side of the select, inserting a not to compensate. Add a missing isZero check that I lost somehow. This improves codegen of: void *func(long count) { return new int[count]; } from: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] testq %rdx, %rdx ## encoding: [0x48,0x85,0xd2] movq $-1, %rdi ## encoding: [0x48,0xc7,0xc7,0xff,0xff,0xff,0xff] cmoveq %rax, %rdi ## encoding: [0x48,0x0f,0x44,0xf8] jmp __Znam ## TAILCALL ## encoding: [0xeb,A] to: __Z4funcl: ## @_Z4funcl movl $4, %ecx ## encoding: [0xb9,0x04,0x00,0x00,0x00] movq %rdi, %rax ## encoding: [0x48,0x89,0xf8] mulq %rcx ## encoding: [0x48,0xf7,0xe1] cmpq $1, %rdx ## encoding: [0x48,0x83,0xfa,0x01] sbbq %rdi, %rdi ## encoding: [0x48,0x19,0xff] notq %rdi ## encoding: [0x48,0xf7,0xd7] orq %rax, %rdi ## encoding: [0x48,0x09,0xc7] jmp __Znam ## TAILCALL ## encoding: [0xeb,A] llvm-svn: 120932
2010-12-05 10:00:51 +08:00
}
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
Teach X86ISelLowering that the second result of X86ISD::UMUL is a flags result. This allows us to compile: void *test12(long count) { return new int[count]; } into: test12: movl $4, %ecx movq %rdi, %rax mulq %rcx movq $-1, %rdi cmovnoq %rax, %rdi jmp __Znam ## TAILCALL instead of: test12: movl $4, %ecx movq %rdi, %rax mulq %rcx seto %cl testb %cl, %cl movq $-1, %rdi cmoveq %rax, %rdi jmp __Znam Of course it would be even better if the regalloc inverted the cmov to 'cmovoq', which would eliminate the need for the 'movq %rdi, %rax'. llvm-svn: 120936
2010-12-05 15:49:54 +08:00
declare noalias i8* @_Znam(i64) noredzone
define noalias i8* @test12(i64 %count) nounwind ssp noredzone {
entry:
%A = tail call { i64, i1 } @llvm.umul.with.overflow.i64(i64 %count, i64 4)
%B = extractvalue { i64, i1 } %A, 1
%C = extractvalue { i64, i1 } %A, 0
%D = select i1 %B, i64 -1, i64 %C
%call = tail call noalias i8* @_Znam(i64 %D) nounwind noredzone
ret i8* %call
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test12:
Revert "Temporarily enable MI-Sched on X86." This reverts commit 98a9b72e8c56dc13a2617de84503a3d78352789c. llvm-svn: 184823
2013-06-25 10:48:58 +08:00
; CHECK: mulq
Enable MI Sched for x86. This changes the SelectionDAG scheduling preference to source order. Soon, the SelectionDAG scheduler can be bypassed saving a nice chunk of compile time. Performance differences that result from this change are often a consequence of register coalescing. The register coalescer is far from perfect. Bugs can be filed for deficiencies. On x86 SandyBridge/Haswell, the source order schedule is often preserved, particularly for small blocks. Register pressure is generally improved over the SD scheduler's ILP mode. However, we are still able to handle large blocks that require latency hiding, unlike the SD scheduler's BURR mode. MI scheduler also attempts to discover the critical path in single-block loops and adjust heuristics accordingly. The MI scheduler relies on the new machine model. This is currently unimplemented for AVX, so we may not be generating the best code yet. Unit tests are updated so they don't depend on SD scheduling heuristics. llvm-svn: 192750
2013-10-16 07:33:07 +08:00
; CHECK: movq $-1, %[[R:r..]]
Allocate local registers in order for optimal coloring. Also avoid locals evicting locals just because they want a cheaper register. Problem: MI Sched knows exactly how many registers we have and assumes they can be colored. In cases where we have large blocks, usually from unrolled loops, greedy coloring fails. This is a source of "regressions" from the MI Scheduler on x86. I noticed this issue on x86 where we have long chains of two-address defs in the same live range. It's easy to see this in matrix multiplication benchmarks like IRSmk and even the unit test misched-matmul.ll. A fundamental difference between the LLVM register allocator and conventional graph coloring is that in our model a live range can't discover its neighbors, it can only verify its neighbors. That's why we initially went for greedy coloring and added eviction to deal with the hard cases. However, for singly defined and two-address live ranges, we can optimally color without visiting neighbors simply by processing the live ranges in instruction order. Other beneficial side effects: It is much easier to understand and debug regalloc for large blocks when the live ranges are allocated in order. Yes, global allocation is still very confusing, but it's nice to be able to comprehend what happened locally. Heuristics could be added to bias register assignment based on instruction locality (think late register pairing, banks...). Intuituvely this will make some test cases that are on the threshold of register pressure more stable. llvm-svn: 187139
2013-07-26 02:35:14 +08:00
; CHECK: cmovnoq %rax, %[[R]]
Teach X86ISelLowering that the second result of X86ISD::UMUL is a flags result. This allows us to compile: void *test12(long count) { return new int[count]; } into: test12: movl $4, %ecx movq %rdi, %rax mulq %rcx movq $-1, %rdi cmovnoq %rax, %rdi jmp __Znam ## TAILCALL instead of: test12: movl $4, %ecx movq %rdi, %rax mulq %rcx seto %cl testb %cl, %cl movq $-1, %rdi cmoveq %rax, %rdi jmp __Znam Of course it would be even better if the regalloc inverted the cmov to 'cmovoq', which would eliminate the need for the 'movq %rdi, %rax'. llvm-svn: 120936
2010-12-05 15:49:54 +08:00
; CHECK: jmp __Znam
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test12:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: mulq
; ATOM: movq $-1, %rdi
; ATOM: cmovnoq %rax, %rdi
; ATOM: jmp __Znam
Teach X86ISelLowering that the second result of X86ISD::UMUL is a flags result. This allows us to compile: void *test12(long count) { return new int[count]; } into: test12: movl $4, %ecx movq %rdi, %rax mulq %rcx movq $-1, %rdi cmovnoq %rax, %rdi jmp __Znam ## TAILCALL instead of: test12: movl $4, %ecx movq %rdi, %rax mulq %rcx seto %cl testb %cl, %cl movq $-1, %rdi cmoveq %rax, %rdi jmp __Znam Of course it would be even better if the regalloc inverted the cmov to 'cmovoq', which would eliminate the need for the 'movq %rdi, %rax'. llvm-svn: 120936
2010-12-05 15:49:54 +08:00
}
declare { i64, i1 } @llvm.umul.with.overflow.i64(i64, i64) nounwind readnone
X86: Lower a select directly to a setcc_carry if possible. int test(unsigned long a, unsigned long b) { return -(a < b); } compiles to _test: ## @test cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] sbbl %eax, %eax ## encoding: [0x19,0xc0] ret ## encoding: [0xc3] instead of _test: ## @test xorl %ecx, %ecx ## encoding: [0x31,0xc9] cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] movl $-1, %eax ## encoding: [0xb8,0xff,0xff,0xff,0xff] cmovael %ecx, %eax ## encoding: [0x0f,0x43,0xc1] ret ## encoding: [0xc3] llvm-svn: 122451
2010-12-23 07:09:28 +08:00
define i32 @test13(i32 %a, i32 %b) nounwind {
%c = icmp ult i32 %a, %b
%d = sext i1 %c to i32
ret i32 %d
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test13:
X86: Lower a select directly to a setcc_carry if possible. int test(unsigned long a, unsigned long b) { return -(a < b); } compiles to _test: ## @test cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] sbbl %eax, %eax ## encoding: [0x19,0xc0] ret ## encoding: [0xc3] instead of _test: ## @test xorl %ecx, %ecx ## encoding: [0x31,0xc9] cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] movl $-1, %eax ## encoding: [0xb8,0xff,0xff,0xff,0xff] cmovael %ecx, %eax ## encoding: [0x0f,0x43,0xc1] ret ## encoding: [0xc3] llvm-svn: 122451
2010-12-23 07:09:28 +08:00
; CHECK: cmpl
; CHECK-NEXT: sbbl
; CHECK-NEXT: ret
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test13:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: cmpl
; ATOM-NEXT: sbbl
Pad Short Functions for Intel Atom The current Intel Atom microarchitecture has a feature whereby when a function returns early then it is slightly faster to execute a sequence of NOP instructions to wait until the return address is ready, as opposed to simply stalling on the ret instruction until the return address is ready. When compiling for X86 Atom only, this patch will run a pass, called "X86PadShortFunction" which will add NOP instructions where less than four cycles elapse between function entry and return. It includes tests. This patch has been updated to address Nadav's review comments - Optimize only at >= O1 and don't do optimization if -Os is set - Stores MachineBasicBlock* instead of BBNum - Uses DenseMap instead of std::map - Fixes placement of braces Patch by Andy Zhang. llvm-svn: 171879
2013-01-09 02:27:24 +08:00
; ATOM: ret
X86: Lower a select directly to a setcc_carry if possible. int test(unsigned long a, unsigned long b) { return -(a < b); } compiles to _test: ## @test cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] sbbl %eax, %eax ## encoding: [0x19,0xc0] ret ## encoding: [0xc3] instead of _test: ## @test xorl %ecx, %ecx ## encoding: [0x31,0xc9] cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] movl $-1, %eax ## encoding: [0xb8,0xff,0xff,0xff,0xff] cmovael %ecx, %eax ## encoding: [0x0f,0x43,0xc1] ret ## encoding: [0xc3] llvm-svn: 122451
2010-12-23 07:09:28 +08:00
}
Teach X86ISelLowering that the second result of X86ISD::UMUL is a flags result. This allows us to compile: void *test12(long count) { return new int[count]; } into: test12: movl $4, %ecx movq %rdi, %rax mulq %rcx movq $-1, %rdi cmovnoq %rax, %rdi jmp __Znam ## TAILCALL instead of: test12: movl $4, %ecx movq %rdi, %rax mulq %rcx seto %cl testb %cl, %cl movq $-1, %rdi cmoveq %rax, %rdi jmp __Znam Of course it would be even better if the regalloc inverted the cmov to 'cmovoq', which would eliminate the need for the 'movq %rdi, %rax'. llvm-svn: 120936
2010-12-05 15:49:54 +08:00
X86: Lower a select directly to a setcc_carry if possible. int test(unsigned long a, unsigned long b) { return -(a < b); } compiles to _test: ## @test cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] sbbl %eax, %eax ## encoding: [0x19,0xc0] ret ## encoding: [0xc3] instead of _test: ## @test xorl %ecx, %ecx ## encoding: [0x31,0xc9] cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] movl $-1, %eax ## encoding: [0xb8,0xff,0xff,0xff,0xff] cmovael %ecx, %eax ## encoding: [0x0f,0x43,0xc1] ret ## encoding: [0xc3] llvm-svn: 122451
2010-12-23 07:09:28 +08:00
define i32 @test14(i32 %a, i32 %b) nounwind {
%c = icmp uge i32 %a, %b
%d = sext i1 %c to i32
ret i32 %d
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test14:
X86: Lower a select directly to a setcc_carry if possible. int test(unsigned long a, unsigned long b) { return -(a < b); } compiles to _test: ## @test cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] sbbl %eax, %eax ## encoding: [0x19,0xc0] ret ## encoding: [0xc3] instead of _test: ## @test xorl %ecx, %ecx ## encoding: [0x31,0xc9] cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] movl $-1, %eax ## encoding: [0xb8,0xff,0xff,0xff,0xff] cmovael %ecx, %eax ## encoding: [0x0f,0x43,0xc1] ret ## encoding: [0xc3] llvm-svn: 122451
2010-12-23 07:09:28 +08:00
; CHECK: cmpl
; CHECK-NEXT: sbbl
; CHECK-NEXT: notl
; CHECK-NEXT: ret
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test14:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: cmpl
; ATOM-NEXT: sbbl
; ATOM-NEXT: notl
Pad Short Functions for Intel Atom The current Intel Atom microarchitecture has a feature whereby when a function returns early then it is slightly faster to execute a sequence of NOP instructions to wait until the return address is ready, as opposed to simply stalling on the ret instruction until the return address is ready. When compiling for X86 Atom only, this patch will run a pass, called "X86PadShortFunction" which will add NOP instructions where less than four cycles elapse between function entry and return. It includes tests. This patch has been updated to address Nadav's review comments - Optimize only at >= O1 and don't do optimization if -Os is set - Stores MachineBasicBlock* instead of BBNum - Uses DenseMap instead of std::map - Fixes placement of braces Patch by Andy Zhang. llvm-svn: 171879
2013-01-09 02:27:24 +08:00
; ATOM: ret
X86: Lower a select directly to a setcc_carry if possible. int test(unsigned long a, unsigned long b) { return -(a < b); } compiles to _test: ## @test cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] sbbl %eax, %eax ## encoding: [0x19,0xc0] ret ## encoding: [0xc3] instead of _test: ## @test xorl %ecx, %ecx ## encoding: [0x31,0xc9] cmpq %rsi, %rdi ## encoding: [0x48,0x39,0xf7] movl $-1, %eax ## encoding: [0xb8,0xff,0xff,0xff,0xff] cmovael %ecx, %eax ## encoding: [0x0f,0x43,0xc1] ret ## encoding: [0xc3] llvm-svn: 122451
2010-12-23 07:09:28 +08:00
}
Improve an integer select optimization in two ways: 1. generalize (select (x == 0), -1, 0) -> (sign_bit (x - 1)) to: (select (x == 0), -1, y) -> (sign_bit (x - 1)) | y 2. Handle the identical pattern that happens with !=: (select (x != 0), y, -1) -> (sign_bit (x - 1)) | y cmov is often high latency and can't fold immediates or memory operands. For example for (x == 0) ? -1 : 1, before we got: < testb %sil, %sil < movl $-1, %ecx < movl $1, %eax < cmovel %ecx, %eax now we get: > cmpb $1, %sil > sbbl %eax, %eax > orl $1, %eax llvm-svn: 120929
2010-12-05 09:23:24 +08:00
X86: optimization for -(x != 0) This patch will optimize -(x != 0) on X86 FROM cmpl $0x01,%edi sbbl %eax,%eax notl %eax TO negl %edi sbbl %eax %eax In order to generate negl, I added patterns in Target/X86/X86InstrCompiler.td: def : Pat<(X86sub_flag 0, GR32:$src), (NEG32r GR32:$src)>; rdar: 10961709 llvm-svn: 156312
2012-05-08 02:06:23 +08:00
; rdar://10961709
define i32 @test15(i32 %x) nounwind {
entry:
%cmp = icmp ne i32 %x, 0
%sub = sext i1 %cmp to i32
ret i32 %sub
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test15:
X86: optimization for -(x != 0) This patch will optimize -(x != 0) on X86 FROM cmpl $0x01,%edi sbbl %eax,%eax notl %eax TO negl %edi sbbl %eax %eax In order to generate negl, I added patterns in Target/X86/X86InstrCompiler.td: def : Pat<(X86sub_flag 0, GR32:$src), (NEG32r GR32:$src)>; rdar: 10961709 llvm-svn: 156312
2012-05-08 02:06:23 +08:00
; CHECK: negl
; CHECK: sbbl
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test15:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: negl
; ATOM: sbbl
X86: optimization for -(x != 0) This patch will optimize -(x != 0) on X86 FROM cmpl $0x01,%edi sbbl %eax,%eax notl %eax TO negl %edi sbbl %eax %eax In order to generate negl, I added patterns in Target/X86/X86InstrCompiler.td: def : Pat<(X86sub_flag 0, GR32:$src), (NEG32r GR32:$src)>; rdar: 10961709 llvm-svn: 156312
2012-05-08 02:06:23 +08:00
}
define i64 @test16(i64 %x) nounwind uwtable readnone ssp {
entry:
%cmp = icmp ne i64 %x, 0
%conv1 = sext i1 %cmp to i64
ret i64 %conv1
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test16:
X86: optimization for -(x != 0) This patch will optimize -(x != 0) on X86 FROM cmpl $0x01,%edi sbbl %eax,%eax notl %eax TO negl %edi sbbl %eax %eax In order to generate negl, I added patterns in Target/X86/X86InstrCompiler.td: def : Pat<(X86sub_flag 0, GR32:$src), (NEG32r GR32:$src)>; rdar: 10961709 llvm-svn: 156312
2012-05-08 02:06:23 +08:00
; CHECK: negq
; CHECK: sbbq
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test16:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: negq
; ATOM: sbbq
X86: optimization for -(x != 0) This patch will optimize -(x != 0) on X86 FROM cmpl $0x01,%edi sbbl %eax,%eax notl %eax TO negl %edi sbbl %eax %eax In order to generate negl, I added patterns in Target/X86/X86InstrCompiler.td: def : Pat<(X86sub_flag 0, GR32:$src), (NEG32r GR32:$src)>; rdar: 10961709 llvm-svn: 156312
2012-05-08 02:06:23 +08:00
}
define i16 @test17(i16 %x) nounwind {
entry:
%cmp = icmp ne i16 %x, 0
%sub = sext i1 %cmp to i16
ret i16 %sub
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test17:
X86: optimization for -(x != 0) This patch will optimize -(x != 0) on X86 FROM cmpl $0x01,%edi sbbl %eax,%eax notl %eax TO negl %edi sbbl %eax %eax In order to generate negl, I added patterns in Target/X86/X86InstrCompiler.td: def : Pat<(X86sub_flag 0, GR32:$src), (NEG32r GR32:$src)>; rdar: 10961709 llvm-svn: 156312
2012-05-08 02:06:23 +08:00
; CHECK: negw
; CHECK: sbbw
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test17:
Update testing case for Atom when disabling rematerialization in TwoAddressInstructionPass. The generated code for Atom has a different code sequence. This is realted to commit r160749. llvm-svn: 160755
2012-07-26 04:17:14 +08:00
; ATOM: negw
; ATOM: sbbw
X86: optimization for -(x != 0) This patch will optimize -(x != 0) on X86 FROM cmpl $0x01,%edi sbbl %eax,%eax notl %eax TO negl %edi sbbl %eax %eax In order to generate negl, I added patterns in Target/X86/X86InstrCompiler.td: def : Pat<(X86sub_flag 0, GR32:$src), (NEG32r GR32:$src)>; rdar: 10961709 llvm-svn: 156312
2012-05-08 02:06:23 +08:00
}
X86: Promote i8 cmov when both operands are coming from truncates of the same width. X86 doesn't have i8 cmovs so isel would emit a branch. Emitting branches at this level is often not a good idea because it's too late for many optimizations to kick in. This solution doesn't add any extensions (truncs are free) and tries to avoid introducing partial register stalls by filtering direct copyfromregs. I'm seeing a ~10% speedup on reading a random .png file with libpng15 via graphicsmagick on x86_64/westmere, but YMMV depending on the microarchitecture. llvm-svn: 165868
2012-10-13 18:39:49 +08:00
define i8 @test18(i32 %x, i8 zeroext %a, i8 zeroext %b) nounwind {
%cmp = icmp slt i32 %x, 15
%sel = select i1 %cmp, i8 %a, i8 %b
ret i8 %sel
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test18:
X86: Fix accidentally swapped operands. llvm-svn: 165871
2012-10-13 20:50:19 +08:00
; CHECK: cmpl $15, %edi
; CHECK: cmovgel %edx
X86: Promote i8 cmov when both operands are coming from truncates of the same width. X86 doesn't have i8 cmovs so isel would emit a branch. Emitting branches at this level is often not a good idea because it's too late for many optimizations to kick in. This solution doesn't add any extensions (truncs are free) and tries to avoid introducing partial register stalls by filtering direct copyfromregs. I'm seeing a ~10% speedup on reading a random .png file with libpng15 via graphicsmagick on x86_64/westmere, but YMMV depending on the microarchitecture. llvm-svn: 165868
2012-10-13 18:39:49 +08:00
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; ATOM-LABEL: test18:
X86: Fix accidentally swapped operands. llvm-svn: 165871
2012-10-13 20:50:19 +08:00
; ATOM: cmpl $15, %edi
; ATOM: cmovgel %edx
X86: Promote i8 cmov when both operands are coming from truncates of the same width. X86 doesn't have i8 cmovs so isel would emit a branch. Emitting branches at this level is often not a good idea because it's too late for many optimizations to kick in. This solution doesn't add any extensions (truncs are free) and tries to avoid introducing partial register stalls by filtering direct copyfromregs. I'm seeing a ~10% speedup on reading a random .png file with libpng15 via graphicsmagick on x86_64/westmere, but YMMV depending on the microarchitecture. llvm-svn: 165868
2012-10-13 18:39:49 +08:00
}
Revert "Revert r212640, "Add trunc (select c, a, b) -> select c (trunc a), (trunc b) combine."" Don't try to convert the select condition type. llvm-svn: 212750
2014-07-11 02:21:04 +08:00
; CHECK-LABEL: @trunc_select_miscompile
; CHECK-NOT: sarb
define i32 @trunc_select_miscompile(i32 %a, i1 zeroext %cc) {
%tmp1 = select i1 %cc, i32 3, i32 2
%tmp2 = shl i32 %a, %tmp1
ret i32 %tmp2
[SDAG] Fix a really, really terrible bug in the DAG combiner. This code is completely wrong. It is also dead, as if it were to *ever* run, it would crash. Fortunately, after my work to the combiner, it is at least *possible* to reach the code, and llvm-stress has found a test case. Thanks to Patrick for reporting. It would be really good if anyone who remembers how this code works and what it was intended to do could add some more obvious test coverage instead of my completely contrived and reduced test case. My test case was so brittle I left a bread crumb comment in it to help the next person to stumble on it and not know what it was actually testing for. llvm-svn: 214785
2014-08-05 05:29:59 +08:00
}
define void @test19() {
; This is a massive reduction of an llvm-stress test case that generates
; interesting chains feeding setcc and eventually a f32 select operation. This
; is intended to exercise the SELECT formation in the DAG combine simplifying
; a simplified select_cc node. If it it regresses and is no longer triggering
; that code path, it can be deleted.
;
; CHECK-LABEL: @test19
; CHECK: testb
; CHECK: cmpl
; CHECK: ucomiss
BB:
br label %CF
CF:
%Cmp10 = icmp ule i8 undef, undef
br i1 %Cmp10, label %CF, label %CF250
CF250:
%E12 = extractelement <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, i32 2
%Cmp32 = icmp ugt i1 %Cmp10, false
br i1 %Cmp32, label %CF, label %CF242
CF242:
%Cmp38 = icmp uge i32 %E12, undef
%FC = uitofp i1 %Cmp38 to float
%Sl59 = select i1 %Cmp32, float %FC, float undef
%Cmp60 = fcmp ugt float undef, undef
br i1 %Cmp60, label %CF242, label %CF244
CF244:
%B122 = fadd float %Sl59, undef
ret void
}