maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/LoopVectorize/if-pred-stores.ll

152 lines
5.8 KiB
LLVM
Raw Normal View History

Delay predication of stores until near the end of vector code generation Predicating stores requires creating extra blocks. It's much cleaner if we do this in one pass instead of mutating the CFG while writing vector instructions. Besides which we can make use of helper functions to update domtree for us, reducing the work we need to do. llvm-svn: 247139
2015-09-09 20:51:06 +08:00
; RUN: opt -S -vectorize-num-stores-pred=1 -force-vector-width=1 -force-vector-interleave=2 -loop-vectorize -simplifycfg < %s | FileCheck %s --check-prefix=UNROLL
; RUN: opt -S -vectorize-num-stores-pred=1 -force-vector-width=1 -force-vector-interleave=2 -loop-vectorize < %s | FileCheck %s --check-prefix=UNROLL-NOSIMPLIFY
; RUN: opt -S -vectorize-num-stores-pred=1 -force-vector-width=2 -force-vector-interleave=1 -loop-vectorize -enable-cond-stores-vec -simplifycfg < %s | FileCheck %s --check-prefix=VEC
; RUN: opt -S -vectorize-num-stores-pred=1 -force-vector-width=2 -force-vector-interleave=1 -loop-vectorize -enable-cond-stores-vec -simplifycfg -instcombine < %s | FileCheck %s --check-prefix=VEC-IC
LoopVectorize: Support conditional stores by scalarizing The vectorizer takes a loop like this and widens all instructions except for the store. The stores are scalarized/unrolled and hidden behind an "if" block. for (i = 0; i < 128; ++i) { if (a[i] < 10) a[i] += val; } for (i = 0; i < 128; i+=2) { v = a[i:i+1]; v0 = (extract v, 0) + 10; v1 = (extract v, 1) + 10; if (v0 < 10) a[i] = v0; if (v1 < 10) a[i] = v1; } The vectorizer relies on subsequent optimizations to sink instructions into the conditional block where they are anticipated. The flag "vectorize-num-stores-pred" controls whether and how many stores to handle this way. Vectorization of conditional stores is disabled per default for now. This patch also adds a change to the heuristic when the flag "enable-loadstore-runtime-unroll" is enabled (off by default). It unrolls small loops until load/store ports are saturated. This heuristic uses TTI's getMaxUnrollFactor as a measure for load/store ports. I also added a second flag -enable-cond-stores-vec. It will enable vectorization of conditional stores. But there is no cost model for vectorization of conditional stores in place yet so this will not do good at the moment. rdar://15892953 Results for x86-64 -O3 -mavx +/- -mllvm -enable-loadstore-runtime-unroll -vectorize-num-stores-pred=1 (before the BFI change): Performance Regressions: Benchmarks/Ptrdist/yacr2/yacr2 7.35% (maze3() is identical but 10% slower) Applications/siod/siod 2.18% Performance improvements: mesa -4.42% libquantum -4.15% With a patch that slightly changes the register heuristics (by subtracting the induction variable on both sides of the register pressure equation, as the induction variable is probably not really unrolled): Performance Regressions: Benchmarks/Ptrdist/yacr2/yacr2 7.73% Applications/siod/siod 1.97% Performance Improvements: libquantum -13.05% (we now also unroll quantum_toffoli) mesa -4.27% llvm-svn: 200270
2014-01-28 09:01:53 +08:00
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.9.0"
; Test predication of stores.
define i32 @test(i32* nocapture %f) #0 {
entry:
br label %for.body
; VEC-LABEL: test
; VEC: %[[v8:.+]] = icmp sgt <2 x i32> %{{.*}}, <i32 100, i32 100>
; VEC: %[[v9:.+]] = add nsw <2 x i32> %{{.*}}, <i32 20, i32 20>
; VEC: %[[v10:.+]] = and <2 x i1> %[[v8]], <i1 true, i1 true>
; VEC: %[[v11:.+]] = extractelement <2 x i1> %[[v10]], i32 0
; VEC: %[[v12:.+]] = icmp eq i1 %[[v11]], true
Delay predication of stores until near the end of vector code generation Predicating stores requires creating extra blocks. It's much cleaner if we do this in one pass instead of mutating the CFG while writing vector instructions. Besides which we can make use of helper functions to update domtree for us, reducing the work we need to do. llvm-svn: 247139
2015-09-09 20:51:06 +08:00
; VEC: %[[v13:.+]] = extractelement <2 x i32> %[[v9]], i32 0
; VEC: %[[v14:.+]] = extractelement <2 x i32*> %{{.*}}, i32 0
LoopVectorize: Support conditional stores by scalarizing The vectorizer takes a loop like this and widens all instructions except for the store. The stores are scalarized/unrolled and hidden behind an "if" block. for (i = 0; i < 128; ++i) { if (a[i] < 10) a[i] += val; } for (i = 0; i < 128; i+=2) { v = a[i:i+1]; v0 = (extract v, 0) + 10; v1 = (extract v, 1) + 10; if (v0 < 10) a[i] = v0; if (v1 < 10) a[i] = v1; } The vectorizer relies on subsequent optimizations to sink instructions into the conditional block where they are anticipated. The flag "vectorize-num-stores-pred" controls whether and how many stores to handle this way. Vectorization of conditional stores is disabled per default for now. This patch also adds a change to the heuristic when the flag "enable-loadstore-runtime-unroll" is enabled (off by default). It unrolls small loops until load/store ports are saturated. This heuristic uses TTI's getMaxUnrollFactor as a measure for load/store ports. I also added a second flag -enable-cond-stores-vec. It will enable vectorization of conditional stores. But there is no cost model for vectorization of conditional stores in place yet so this will not do good at the moment. rdar://15892953 Results for x86-64 -O3 -mavx +/- -mllvm -enable-loadstore-runtime-unroll -vectorize-num-stores-pred=1 (before the BFI change): Performance Regressions: Benchmarks/Ptrdist/yacr2/yacr2 7.35% (maze3() is identical but 10% slower) Applications/siod/siod 2.18% Performance improvements: mesa -4.42% libquantum -4.15% With a patch that slightly changes the register heuristics (by subtracting the induction variable on both sides of the register pressure equation, as the induction variable is probably not really unrolled): Performance Regressions: Benchmarks/Ptrdist/yacr2/yacr2 7.73% Applications/siod/siod 1.97% Performance Improvements: libquantum -13.05% (we now also unroll quantum_toffoli) mesa -4.27% llvm-svn: 200270
2014-01-28 09:01:53 +08:00
; VEC: br i1 %[[v12]], label %[[cond:.+]], label %[[else:.+]]
;
; VEC: [[cond]]:
; VEC: store i32 %[[v13]], i32* %[[v14]], align 4
; VEC: br label %[[else:.+]]
;
; VEC: [[else]]:
; VEC: %[[v15:.+]] = extractelement <2 x i1> %[[v10]], i32 1
; VEC: %[[v16:.+]] = icmp eq i1 %[[v15]], true
Delay predication of stores until near the end of vector code generation Predicating stores requires creating extra blocks. It's much cleaner if we do this in one pass instead of mutating the CFG while writing vector instructions. Besides which we can make use of helper functions to update domtree for us, reducing the work we need to do. llvm-svn: 247139
2015-09-09 20:51:06 +08:00
; VEC: %[[v17:.+]] = extractelement <2 x i32> %[[v9]], i32 1
; VEC: %[[v18:.+]] = extractelement <2 x i32*> %{{.+}} i32 1
LoopVectorize: Support conditional stores by scalarizing The vectorizer takes a loop like this and widens all instructions except for the store. The stores are scalarized/unrolled and hidden behind an "if" block. for (i = 0; i < 128; ++i) { if (a[i] < 10) a[i] += val; } for (i = 0; i < 128; i+=2) { v = a[i:i+1]; v0 = (extract v, 0) + 10; v1 = (extract v, 1) + 10; if (v0 < 10) a[i] = v0; if (v1 < 10) a[i] = v1; } The vectorizer relies on subsequent optimizations to sink instructions into the conditional block where they are anticipated. The flag "vectorize-num-stores-pred" controls whether and how many stores to handle this way. Vectorization of conditional stores is disabled per default for now. This patch also adds a change to the heuristic when the flag "enable-loadstore-runtime-unroll" is enabled (off by default). It unrolls small loops until load/store ports are saturated. This heuristic uses TTI's getMaxUnrollFactor as a measure for load/store ports. I also added a second flag -enable-cond-stores-vec. It will enable vectorization of conditional stores. But there is no cost model for vectorization of conditional stores in place yet so this will not do good at the moment. rdar://15892953 Results for x86-64 -O3 -mavx +/- -mllvm -enable-loadstore-runtime-unroll -vectorize-num-stores-pred=1 (before the BFI change): Performance Regressions: Benchmarks/Ptrdist/yacr2/yacr2 7.35% (maze3() is identical but 10% slower) Applications/siod/siod 2.18% Performance improvements: mesa -4.42% libquantum -4.15% With a patch that slightly changes the register heuristics (by subtracting the induction variable on both sides of the register pressure equation, as the induction variable is probably not really unrolled): Performance Regressions: Benchmarks/Ptrdist/yacr2/yacr2 7.73% Applications/siod/siod 1.97% Performance Improvements: libquantum -13.05% (we now also unroll quantum_toffoli) mesa -4.27% llvm-svn: 200270
2014-01-28 09:01:53 +08:00
; VEC: br i1 %[[v16]], label %[[cond2:.+]], label %[[else2:.+]]
;
; VEC: [[cond2]]:
; VEC: store i32 %[[v17]], i32* %[[v18]], align 4
; VEC: br label %[[else2:.+]]
;
; VEC: [[else2]]:
Delay predication of stores until near the end of vector code generation Predicating stores requires creating extra blocks. It's much cleaner if we do this in one pass instead of mutating the CFG while writing vector instructions. Besides which we can make use of helper functions to update domtree for us, reducing the work we need to do. llvm-svn: 247139
2015-09-09 20:51:06 +08:00
; VEC-IC-LABEL: test
; VEC-IC: %[[v1:.+]] = icmp sgt <2 x i32> %{{.*}}, <i32 100, i32 100>
; VEC-IC: %[[v2:.+]] = add nsw <2 x i32> %{{.*}}, <i32 20, i32 20>
; VEC-IC: %[[v3:.+]] = extractelement <2 x i1> %[[v1]], i32 0
; VEC-IC: br i1 %[[v3]], label %[[cond:.+]], label %[[else:.+]]
;
; VEC-IC: [[cond]]:
; VEC-IC: %[[v4:.+]] = extractelement <2 x i32> %[[v2]], i32 0
; VEC-IC: store i32 %[[v4]], i32* %{{.*}}, align 4
; VEC-IC: br label %[[else:.+]]
;
; VEC-IC: [[else]]:
; VEC-IC: %[[v5:.+]] = extractelement <2 x i1> %[[v1]], i32 1
; VEC-IC: br i1 %[[v5]], label %[[cond2:.+]], label %[[else2:.+]]
;
; VEC-IC: [[cond2]]:
; VEC-IC: %[[v6:.+]] = extractelement <2 x i32> %[[v2]], i32 1
; VEC-IC: store i32 %[[v6]], i32* %{{.*}}, align 4
; VEC-IC: br label %[[else2:.+]]
;
; VEC-IC: [[else2]]:
LoopVectorize: Support conditional stores by scalarizing The vectorizer takes a loop like this and widens all instructions except for the store. The stores are scalarized/unrolled and hidden behind an "if" block. for (i = 0; i < 128; ++i) { if (a[i] < 10) a[i] += val; } for (i = 0; i < 128; i+=2) { v = a[i:i+1]; v0 = (extract v, 0) + 10; v1 = (extract v, 1) + 10; if (v0 < 10) a[i] = v0; if (v1 < 10) a[i] = v1; } The vectorizer relies on subsequent optimizations to sink instructions into the conditional block where they are anticipated. The flag "vectorize-num-stores-pred" controls whether and how many stores to handle this way. Vectorization of conditional stores is disabled per default for now. This patch also adds a change to the heuristic when the flag "enable-loadstore-runtime-unroll" is enabled (off by default). It unrolls small loops until load/store ports are saturated. This heuristic uses TTI's getMaxUnrollFactor as a measure for load/store ports. I also added a second flag -enable-cond-stores-vec. It will enable vectorization of conditional stores. But there is no cost model for vectorization of conditional stores in place yet so this will not do good at the moment. rdar://15892953 Results for x86-64 -O3 -mavx +/- -mllvm -enable-loadstore-runtime-unroll -vectorize-num-stores-pred=1 (before the BFI change): Performance Regressions: Benchmarks/Ptrdist/yacr2/yacr2 7.35% (maze3() is identical but 10% slower) Applications/siod/siod 2.18% Performance improvements: mesa -4.42% libquantum -4.15% With a patch that slightly changes the register heuristics (by subtracting the induction variable on both sides of the register pressure equation, as the induction variable is probably not really unrolled): Performance Regressions: Benchmarks/Ptrdist/yacr2/yacr2 7.73% Applications/siod/siod 1.97% Performance Improvements: libquantum -13.05% (we now also unroll quantum_toffoli) mesa -4.27% llvm-svn: 200270
2014-01-28 09:01:53 +08:00
; UNROLL-LABEL: test
; UNROLL: vector.body:
; UNROLL: %[[IND:[a-zA-Z0-9]+]] = add i64 %{{.*}}, 0
; UNROLL: %[[IND1:[a-zA-Z0-9]+]] = add i64 %{{.*}}, 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
; UNROLL: %[[v0:[a-zA-Z0-9]+]] = getelementptr inbounds i32, i32* %f, i64 %[[IND]]
; UNROLL: %[[v1:[a-zA-Z0-9]+]] = getelementptr inbounds i32, i32* %f, i64 %[[IND1]]
[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
; UNROLL: %[[v2:[a-zA-Z0-9]+]] = load i32, i32* %[[v0]], align 4
; UNROLL: %[[v3:[a-zA-Z0-9]+]] = load i32, i32* %[[v1]], align 4
LoopVectorize: Support conditional stores by scalarizing The vectorizer takes a loop like this and widens all instructions except for the store. The stores are scalarized/unrolled and hidden behind an "if" block. for (i = 0; i < 128; ++i) { if (a[i] < 10) a[i] += val; } for (i = 0; i < 128; i+=2) { v = a[i:i+1]; v0 = (extract v, 0) + 10; v1 = (extract v, 1) + 10; if (v0 < 10) a[i] = v0; if (v1 < 10) a[i] = v1; } The vectorizer relies on subsequent optimizations to sink instructions into the conditional block where they are anticipated. The flag "vectorize-num-stores-pred" controls whether and how many stores to handle this way. Vectorization of conditional stores is disabled per default for now. This patch also adds a change to the heuristic when the flag "enable-loadstore-runtime-unroll" is enabled (off by default). It unrolls small loops until load/store ports are saturated. This heuristic uses TTI's getMaxUnrollFactor as a measure for load/store ports. I also added a second flag -enable-cond-stores-vec. It will enable vectorization of conditional stores. But there is no cost model for vectorization of conditional stores in place yet so this will not do good at the moment. rdar://15892953 Results for x86-64 -O3 -mavx +/- -mllvm -enable-loadstore-runtime-unroll -vectorize-num-stores-pred=1 (before the BFI change): Performance Regressions: Benchmarks/Ptrdist/yacr2/yacr2 7.35% (maze3() is identical but 10% slower) Applications/siod/siod 2.18% Performance improvements: mesa -4.42% libquantum -4.15% With a patch that slightly changes the register heuristics (by subtracting the induction variable on both sides of the register pressure equation, as the induction variable is probably not really unrolled): Performance Regressions: Benchmarks/Ptrdist/yacr2/yacr2 7.73% Applications/siod/siod 1.97% Performance Improvements: libquantum -13.05% (we now also unroll quantum_toffoli) mesa -4.27% llvm-svn: 200270
2014-01-28 09:01:53 +08:00
; UNROLL: %[[v4:[a-zA-Z0-9]+]] = icmp sgt i32 %[[v2]], 100
; UNROLL: %[[v5:[a-zA-Z0-9]+]] = icmp sgt i32 %[[v3]], 100
; UNROLL: %[[v6:[a-zA-Z0-9]+]] = add nsw i32 %[[v2]], 20
; UNROLL: %[[v7:[a-zA-Z0-9]+]] = add nsw i32 %[[v3]], 20
; UNROLL: %[[v8:[a-zA-Z0-9]+]] = icmp eq i1 %[[v4]], true
; UNROLL: br i1 %[[v8]], label %[[cond:[a-zA-Z0-9.]+]], label %[[else:[a-zA-Z0-9.]+]]
;
; UNROLL: [[cond]]:
; UNROLL: store i32 %[[v6]], i32* %[[v0]], align 4
; UNROLL: br label %[[else]]
;
; UNROLL: [[else]]:
; UNROLL: %[[v9:[a-zA-Z0-9]+]] = icmp eq i1 %[[v5]], true
; UNROLL: br i1 %[[v9]], label %[[cond2:[a-zA-Z0-9.]+]], label %[[else2:[a-zA-Z0-9.]+]]
;
; UNROLL: [[cond2]]:
; UNROLL: store i32 %[[v7]], i32* %[[v1]], align 4
; UNROLL: br label %[[else2]]
;
; UNROLL: [[else2]]:
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.inc ]
[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 i32, i32* %f, i64 %indvars.iv
[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
%0 = load i32, i32* %arrayidx, align 4
LoopVectorize: Support conditional stores by scalarizing The vectorizer takes a loop like this and widens all instructions except for the store. The stores are scalarized/unrolled and hidden behind an "if" block. for (i = 0; i < 128; ++i) { if (a[i] < 10) a[i] += val; } for (i = 0; i < 128; i+=2) { v = a[i:i+1]; v0 = (extract v, 0) + 10; v1 = (extract v, 1) + 10; if (v0 < 10) a[i] = v0; if (v1 < 10) a[i] = v1; } The vectorizer relies on subsequent optimizations to sink instructions into the conditional block where they are anticipated. The flag "vectorize-num-stores-pred" controls whether and how many stores to handle this way. Vectorization of conditional stores is disabled per default for now. This patch also adds a change to the heuristic when the flag "enable-loadstore-runtime-unroll" is enabled (off by default). It unrolls small loops until load/store ports are saturated. This heuristic uses TTI's getMaxUnrollFactor as a measure for load/store ports. I also added a second flag -enable-cond-stores-vec. It will enable vectorization of conditional stores. But there is no cost model for vectorization of conditional stores in place yet so this will not do good at the moment. rdar://15892953 Results for x86-64 -O3 -mavx +/- -mllvm -enable-loadstore-runtime-unroll -vectorize-num-stores-pred=1 (before the BFI change): Performance Regressions: Benchmarks/Ptrdist/yacr2/yacr2 7.35% (maze3() is identical but 10% slower) Applications/siod/siod 2.18% Performance improvements: mesa -4.42% libquantum -4.15% With a patch that slightly changes the register heuristics (by subtracting the induction variable on both sides of the register pressure equation, as the induction variable is probably not really unrolled): Performance Regressions: Benchmarks/Ptrdist/yacr2/yacr2 7.73% Applications/siod/siod 1.97% Performance Improvements: libquantum -13.05% (we now also unroll quantum_toffoli) mesa -4.27% llvm-svn: 200270
2014-01-28 09:01:53 +08:00
%cmp1 = icmp sgt i32 %0, 100
br i1 %cmp1, label %if.then, label %for.inc
if.then:
%add = add nsw i32 %0, 20
store i32 %add, i32* %arrayidx, align 4
br label %for.inc
for.inc:
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 128
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret i32 0
}
LoopVectorizer: Keep track of conditional store basic blocks Before conditional store vectorization/unrolling we had only one vectorized/unrolled basic block. After adding support for conditional store vectorization this will not only be one block but multiple basic blocks. The last block would have the back-edge. I updated the code to use a vector of basic blocks instead of a single basic block and fixed the users to use the last entry in this vector. But, I forgot to add the basic blocks to this vector! Fixes PR18724. llvm-svn: 201028
2014-02-09 04:41:13 +08:00
; Track basic blocks when unrolling conditional blocks. This code used to assert
; because we did not update the phi nodes with the proper predecessor in the
; vectorized loop body.
; PR18724
Delay predication of stores until near the end of vector code generation Predicating stores requires creating extra blocks. It's much cleaner if we do this in one pass instead of mutating the CFG while writing vector instructions. Besides which we can make use of helper functions to update domtree for us, reducing the work we need to do. llvm-svn: 247139
2015-09-09 20:51:06 +08:00
; UNROLL-NOSIMPLIFY-LABEL: bug18724
; UNROLL-NOSIMPLIFY: store i32
; UNROLL-NOSIMPLIFY: store i32
LoopVectorizer: Keep track of conditional store basic blocks Before conditional store vectorization/unrolling we had only one vectorized/unrolled basic block. After adding support for conditional store vectorization this will not only be one block but multiple basic blocks. The last block would have the back-edge. I updated the code to use a vector of basic blocks instead of a single basic block and fixed the users to use the last entry in this vector. But, I forgot to add the basic blocks to this vector! Fixes PR18724. llvm-svn: 201028
2014-02-09 04:41:13 +08:00
define void @bug18724() {
entry:
br label %for.body9
for.body9:
br i1 undef, label %for.inc26, label %for.body14
for.body14:
%indvars.iv3 = phi i64 [ %indvars.iv.next4, %for.inc23 ], [ undef, %for.body9 ]
%iNewChunks.120 = phi i32 [ %iNewChunks.2, %for.inc23 ], [ undef, %for.body9 ]
[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
%arrayidx16 = getelementptr inbounds [768 x i32], [768 x i32]* undef, i64 0, i64 %indvars.iv3
[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 i32, i32* %arrayidx16, align 4
LoopVectorizer: Keep track of conditional store basic blocks Before conditional store vectorization/unrolling we had only one vectorized/unrolled basic block. After adding support for conditional store vectorization this will not only be one block but multiple basic blocks. The last block would have the back-edge. I updated the code to use a vector of basic blocks instead of a single basic block and fixed the users to use the last entry in this vector. But, I forgot to add the basic blocks to this vector! Fixes PR18724. llvm-svn: 201028
2014-02-09 04:41:13 +08:00
br i1 undef, label %if.then18, label %for.inc23
if.then18:
store i32 2, i32* %arrayidx16, align 4
%inc21 = add nsw i32 %iNewChunks.120, 1
br label %for.inc23
for.inc23:
%iNewChunks.2 = phi i32 [ %inc21, %if.then18 ], [ %iNewChunks.120, %for.body14 ]
%indvars.iv.next4 = add nsw i64 %indvars.iv3, 1
%tmp1 = trunc i64 %indvars.iv3 to i32
%cmp13 = icmp slt i32 %tmp1, 0
br i1 %cmp13, label %for.body14, label %for.inc26
for.inc26:
%iNewChunks.1.lcssa = phi i32 [ undef, %for.body9 ], [ %iNewChunks.2, %for.inc23 ]
unreachable
}