llvm-project/llvm/test/Transforms/SLPVectorizer/X86/external_user.ll

97 lines
3.1 KiB
LLVM
Raw Normal View History

; RUN: opt < %s -basicaa -slp-vectorizer -dce -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.8.0"
; double foo(double * restrict b, double * restrict a, int n, int m) {
; double r=a[1];
; double g=a[0];
; double x;
; for (int i=0; i < 100; i++) {
; r += 10;
; g += 10;
; r *= 4;
; g *= 4;
; x = g; <----- external user!
; r += 4;
; g += 4;
; }
; b[0] = g;
; b[1] = r;
;
; return x; <-- must extract here!
; }
;CHECK: ext_user
;CHECK: phi <2 x double>
;CHECK: fadd <2 x double>
;CHECK: fmul <2 x double>
;CHECK: br
;CHECK: store <2 x double>
;CHECK: extractelement <2 x double>
;CHECK: ret double
define double @ext_user(double* noalias nocapture %B, double* noalias nocapture %A, i32 %n, i32 %m) {
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
%arrayidx = getelementptr inbounds double, double* %A, i64 1
%0 = load double* %arrayidx, align 8
%1 = load double* %A, align 8
br label %for.body
for.body: ; preds = %for.body, %entry
%i.020 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%G.019 = phi double [ %1, %entry ], [ %add5, %for.body ]
%R.018 = phi double [ %0, %entry ], [ %add4, %for.body ]
%add = fadd double %R.018, 1.000000e+01
%add2 = fadd double %G.019, 1.000000e+01
%mul = fmul double %add, 4.000000e+00
%mul3 = fmul double %add2, 4.000000e+00
%add4 = fadd double %mul, 4.000000e+00
%add5 = fadd double %mul3, 4.000000e+00
%inc = add nsw i32 %i.020, 1
%exitcond = icmp eq i32 %inc, 100
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
store double %add5, double* %B, align 8
[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
%arrayidx7 = getelementptr inbounds double, double* %B, i64 1
store double %add4, double* %arrayidx7, align 8
ret double %mul3
}
; A need-to-gather entry cannot be an external use of the scalar element.
; Instead the insertelement instructions of the need-to-gather entry are the
; external users.
; This test would assert because we would keep the scalar fpext and fadd alive.
; PR18129
; CHECK-LABEL: needtogather
define i32 @needtogather(double *noalias %a, i32 *noalias %b, float * noalias %c,
i32 * noalias %d) {
entry:
%0 = load i32* %d, align 4
%conv = sitofp i32 %0 to float
%1 = load float* %c
%sub = fsub float 0.000000e+00, %1
%mul = fmul float %sub, 0.000000e+00
%add = fadd float %conv, %mul
%conv1 = fpext float %add to double
%sub3 = fsub float 1.000000e+00, %1
%mul4 = fmul float %sub3, 0.000000e+00
%add5 = fadd float %conv, %mul4
%conv6 = fpext float %add5 to double
%tobool = fcmp une float %add, 0.000000e+00
br i1 %tobool, label %if.then, label %if.end
if.then:
br label %if.end
if.end:
%storemerge = phi double [ %conv6, %if.then ], [ %conv1, %entry ]
%e.0 = phi double [ %conv1, %if.then ], [ %conv6, %entry ]
store double %storemerge, double* %a, align 8
%conv7 = fptosi double %e.0 to i32
store i32 %conv7, i32* %b, align 4
ret i32 undef
}