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-conversion-nest.ll

121 lines
6.8 KiB
LLVM
Raw Normal View History

[LoopVectorize] auto-generate complete checks; NFC I'm looking at a cmp transform in InstCombine that would affect these tests, but it's hard to know if it makes things better or worse without seeing the full IR. OTOH, maybe these tests shouldn't be running a bunch of transform passes in the first place? llvm-svn: 307475
2017-07-09 00:10:42 +08:00
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
Rename getMaximumUnrollFactor -> getMaxInterleaveFactor; also rename option names controlling this variable. "Unroll" is not the appropriate name for this variable. Clang already uses the term "interleave" in pragmas and metadata for this. Differential Revision: http://reviews.llvm.org/D5066 llvm-svn: 217528
2014-09-11 01:58:16 +08:00
; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -enable-if-conversion -dce -instcombine -S | FileCheck %s
LoopVectorizer: Add support for if-conversion of PHINodes with 3+ incoming values. By supporting the vectorization of PHINodes with more than two incoming values we can increase the complexity of nested if statements. We can now vectorize this loop: int foo(int *A, int *B, int n) { for (int i=0; i < n; i++) { int x = 9; if (A[i] > B[i]) { if (A[i] > 19) { x = 3; } else if (B[i] < 4 ) { x = 4; } else { x = 5; } } A[i] = x; } } llvm-svn: 181037
2013-05-04 01:42:55 +08:00
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"
define i32 @foo(i32* nocapture %A, i32* nocapture %B, i32 %n) {
[LoopVectorize] auto-generate complete checks; NFC I'm looking at a cmp transform in InstCombine that would affect these tests, but it's hard to know if it makes things better or worse without seeing the full IR. OTOH, maybe these tests shouldn't be running a bunch of transform passes in the first place? llvm-svn: 307475
2017-07-09 00:10:42 +08:00
; CHECK-LABEL: @foo(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[CMP26:%.*]] = icmp sgt i32 [[N:%.*]], 0
; CHECK-NEXT: br i1 [[CMP26]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_END:%.*]]
; CHECK: for.body.preheader:
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[N]], -1
; CHECK-NEXT: [[TMP1:%.*]] = zext i32 [[TMP0]] to i64
; CHECK-NEXT: [[TMP2:%.*]] = add nuw nsw i64 [[TMP1]], 1
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP2]], 4
[LV] Test once if vector trip count is zero, instead of twice Generate a single test to decide if there are enough iterations to jump to the vectorized loop, or else go to the scalar remainder loop. This test compares the Scalar Trip Count: if STC < VF * UF go to the scalar loop. If requiresScalarEpilogue() holds, at-least one iteration must remain scalar; the rest can be used to form vector iterations. So in this case the test checks instead if (STC - 1) < VF * UF by comparing STC <= VF * UF, and going to the scalar loop if so. Otherwise the vector loop is entered for at-least one vector iteration. This test covers the case where incrementing the backedge-taken count will overflow leading to an incorrect trip count of zero. In this (rare) case we will also avoid the vector loop and jump to the scalar loop. This patch simplifies the existing tests and effectively removes the basic-block originally named "min.iters.checked", leaving the single test in block "vector.ph". Original observation and initial patch by Evgeny Stupachenko. Differential Revision: https://reviews.llvm.org/D34150 llvm-svn: 308421
2017-07-19 13:16:39 +08:00
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
[LoopVectorize] auto-generate complete checks; NFC I'm looking at a cmp transform in InstCombine that would affect these tests, but it's hard to know if it makes things better or worse without seeing the full IR. OTOH, maybe these tests shouldn't be running a bunch of transform passes in the first place? llvm-svn: 307475
2017-07-09 00:10:42 +08:00
; CHECK: vector.memcheck:
[LV] Test once if vector trip count is zero, instead of twice Generate a single test to decide if there are enough iterations to jump to the vectorized loop, or else go to the scalar remainder loop. This test compares the Scalar Trip Count: if STC < VF * UF go to the scalar loop. If requiresScalarEpilogue() holds, at-least one iteration must remain scalar; the rest can be used to form vector iterations. So in this case the test checks instead if (STC - 1) < VF * UF by comparing STC <= VF * UF, and going to the scalar loop if so. Otherwise the vector loop is entered for at-least one vector iteration. This test covers the case where incrementing the backedge-taken count will overflow leading to an incorrect trip count of zero. In this (rare) case we will also avoid the vector loop and jump to the scalar loop. This patch simplifies the existing tests and effectively removes the basic-block originally named "min.iters.checked", leaving the single test in block "vector.ph". Original observation and initial patch by Evgeny Stupachenko. Differential Revision: https://reviews.llvm.org/D34150 llvm-svn: 308421
2017-07-19 13:16:39 +08:00
; CHECK-NEXT: [[TMP3:%.*]] = add i32 [[N]], -1
; CHECK-NEXT: [[TMP4:%.*]] = zext i32 [[TMP3]] to i64
; CHECK-NEXT: [[TMP5:%.*]] = add nuw nsw i64 [[TMP4]], 1
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i32, i32* [[A:%.*]], i64 [[TMP5]]
; CHECK-NEXT: [[SCEVGEP4:%.*]] = getelementptr i32, i32* [[B:%.*]], i64 [[TMP5]]
[LoopVectorize] auto-generate complete checks; NFC I'm looking at a cmp transform in InstCombine that would affect these tests, but it's hard to know if it makes things better or worse without seeing the full IR. OTOH, maybe these tests shouldn't be running a bunch of transform passes in the first place? llvm-svn: 307475
2017-07-09 00:10:42 +08:00
; CHECK-NEXT: [[BOUND0:%.*]] = icmp ugt i32* [[SCEVGEP4]], [[A]]
; CHECK-NEXT: [[BOUND1:%.*]] = icmp ugt i32* [[SCEVGEP]], [[B]]
; CHECK-NEXT: [[MEMCHECK_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
; CHECK-NEXT: br i1 [[MEMCHECK_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
[LV] Test once if vector trip count is zero, instead of twice Generate a single test to decide if there are enough iterations to jump to the vectorized loop, or else go to the scalar remainder loop. This test compares the Scalar Trip Count: if STC < VF * UF go to the scalar loop. If requiresScalarEpilogue() holds, at-least one iteration must remain scalar; the rest can be used to form vector iterations. So in this case the test checks instead if (STC - 1) < VF * UF by comparing STC <= VF * UF, and going to the scalar loop if so. Otherwise the vector loop is entered for at-least one vector iteration. This test covers the case where incrementing the backedge-taken count will overflow leading to an incorrect trip count of zero. In this (rare) case we will also avoid the vector loop and jump to the scalar loop. This patch simplifies the existing tests and effectively removes the basic-block originally named "min.iters.checked", leaving the single test in block "vector.ph". Original observation and initial patch by Evgeny Stupachenko. Differential Revision: https://reviews.llvm.org/D34150 llvm-svn: 308421
2017-07-19 13:16:39 +08:00
; CHECK-NEXT: [[TMP6:%.*]] = and i32 [[N]], 3
; CHECK-NEXT: [[N_MOD_VF:%.*]] = zext i32 [[TMP6]] to i64
; CHECK-NEXT: [[N_VEC:%.*]] = sub nsw i64 [[TMP2]], [[N_MOD_VF]]
[LoopVectorize] auto-generate complete checks; NFC I'm looking at a cmp transform in InstCombine that would affect these tests, but it's hard to know if it makes things better or worse without seeing the full IR. OTOH, maybe these tests shouldn't be running a bunch of transform passes in the first place? llvm-svn: 307475
2017-07-09 00:10:42 +08:00
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP8:%.*]] = bitcast i32* [[TMP7]] to <4 x i32>*
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP8]], align 4, !alias.scope !0, !noalias !3
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP10:%.*]] = bitcast i32* [[TMP9]] to <4 x i32>*
; CHECK-NEXT: [[WIDE_LOAD6:%.*]] = load <4 x i32>, <4 x i32>* [[TMP10]], align 4, !alias.scope !3
; CHECK-NEXT: [[TMP11:%.*]] = icmp sgt <4 x i32> [[WIDE_LOAD]], [[WIDE_LOAD6]]
; CHECK-NEXT: [[TMP12:%.*]] = icmp sgt <4 x i32> [[WIDE_LOAD]], <i32 19, i32 19, i32 19, i32 19>
; CHECK-NEXT: [[TMP13:%.*]] = icmp slt <4 x i32> [[WIDE_LOAD6]], <i32 4, i32 4, i32 4, i32 4>
; CHECK-NEXT: [[TMP14:%.*]] = select <4 x i1> [[TMP13]], <4 x i32> <i32 4, i32 4, i32 4, i32 4>, <4 x i32> <i32 5, i32 5, i32 5, i32 5>
; CHECK-NEXT: [[TMP15:%.*]] = and <4 x i1> [[TMP12]], [[TMP11]]
; CHECK-NEXT: [[TMP16:%.*]] = xor <4 x i1> [[TMP12]], <i1 true, i1 true, i1 true, i1 true>
; CHECK-NEXT: [[TMP17:%.*]] = and <4 x i1> [[TMP11]], [[TMP16]]
[LV] Model masking in VPlan, introducing VPInstructions This patch adds a new abstraction layer to VPlan and leverages it to model the planned instructions that manipulate masks (AND, OR, NOT), introduced during predication. The new VPValue and VPUser classes model how data flows into, through and out of a VPlan, forming the vertices of a planned Def-Use graph. The new VPInstruction class is a generic single-instruction Recipe that models a planned instruction along with its opcode, operands and users. See VectorizationPlan.rst for more details. Differential Revision: https://reviews.llvm.org/D38676 llvm-svn: 318645
2017-11-20 20:01:47 +08:00
; CHECK-NEXT: [[PREDPHI:%.*]] = select <4 x i1> [[TMP15]], <4 x i32> <i32 3, i32 3, i32 3, i32 3>, <4 x i32> <i32 9, i32 9, i32 9, i32 9>
[LoopVectorize] auto-generate complete checks; NFC I'm looking at a cmp transform in InstCombine that would affect these tests, but it's hard to know if it makes things better or worse without seeing the full IR. OTOH, maybe these tests shouldn't be running a bunch of transform passes in the first place? llvm-svn: 307475
2017-07-09 00:10:42 +08:00
; CHECK-NEXT: [[PREDPHI7:%.*]] = select <4 x i1> [[TMP17]], <4 x i32> [[TMP14]], <4 x i32> [[PREDPHI]]
; CHECK-NEXT: [[TMP18:%.*]] = bitcast i32* [[TMP7]] to <4 x i32>*
; CHECK-NEXT: store <4 x i32> [[PREDPHI7]], <4 x i32>* [[TMP18]], align 4, !alias.scope !0, !noalias !3
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP19:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP19]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !5
; CHECK: middle.block:
[LV] Test once if vector trip count is zero, instead of twice Generate a single test to decide if there are enough iterations to jump to the vectorized loop, or else go to the scalar remainder loop. This test compares the Scalar Trip Count: if STC < VF * UF go to the scalar loop. If requiresScalarEpilogue() holds, at-least one iteration must remain scalar; the rest can be used to form vector iterations. So in this case the test checks instead if (STC - 1) < VF * UF by comparing STC <= VF * UF, and going to the scalar loop if so. Otherwise the vector loop is entered for at-least one vector iteration. This test covers the case where incrementing the backedge-taken count will overflow leading to an incorrect trip count of zero. In this (rare) case we will also avoid the vector loop and jump to the scalar loop. This patch simplifies the existing tests and effectively removes the basic-block originally named "min.iters.checked", leaving the single test in block "vector.ph". Original observation and initial patch by Evgeny Stupachenko. Differential Revision: https://reviews.llvm.org/D34150 llvm-svn: 308421
2017-07-19 13:16:39 +08:00
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[TMP6]], 0
[LoopVectorize] auto-generate complete checks; NFC I'm looking at a cmp transform in InstCombine that would affect these tests, but it's hard to know if it makes things better or worse without seeing the full IR. OTOH, maybe these tests shouldn't be running a bunch of transform passes in the first place? llvm-svn: 307475
2017-07-09 00:10:42 +08:00
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
[LV] Test once if vector trip count is zero, instead of twice Generate a single test to decide if there are enough iterations to jump to the vectorized loop, or else go to the scalar remainder loop. This test compares the Scalar Trip Count: if STC < VF * UF go to the scalar loop. If requiresScalarEpilogue() holds, at-least one iteration must remain scalar; the rest can be used to form vector iterations. So in this case the test checks instead if (STC - 1) < VF * UF by comparing STC <= VF * UF, and going to the scalar loop if so. Otherwise the vector loop is entered for at-least one vector iteration. This test covers the case where incrementing the backedge-taken count will overflow leading to an incorrect trip count of zero. In this (rare) case we will also avoid the vector loop and jump to the scalar loop. This patch simplifies the existing tests and effectively removes the basic-block originally named "min.iters.checked", leaving the single test in block "vector.ph". Original observation and initial patch by Evgeny Stupachenko. Differential Revision: https://reviews.llvm.org/D34150 llvm-svn: 308421
2017-07-19 13:16:39 +08:00
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY_PREHEADER]] ], [ 0, [[VECTOR_MEMCHECK]] ]
[LoopVectorize] auto-generate complete checks; NFC I'm looking at a cmp transform in InstCombine that would affect these tests, but it's hard to know if it makes things better or worse without seeing the full IR. OTOH, maybe these tests shouldn't be running a bunch of transform passes in the first place? llvm-svn: 307475
2017-07-09 00:10:42 +08:00
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[IF_END14:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP20:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDVARS_IV]]
; CHECK-NEXT: [[TMP21:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4
; CHECK-NEXT: [[CMP3:%.*]] = icmp sgt i32 [[TMP20]], [[TMP21]]
; CHECK-NEXT: br i1 [[CMP3]], label [[IF_THEN:%.*]], label [[IF_END14]]
; CHECK: if.then:
; CHECK-NEXT: [[CMP6:%.*]] = icmp sgt i32 [[TMP20]], 19
; CHECK-NEXT: br i1 [[CMP6]], label [[IF_END14]], label [[IF_ELSE:%.*]]
; CHECK: if.else:
; CHECK-NEXT: [[CMP10:%.*]] = icmp slt i32 [[TMP21]], 4
; CHECK-NEXT: [[DOT:%.*]] = select i1 [[CMP10]], i32 4, i32 5
; CHECK-NEXT: br label [[IF_END14]]
; CHECK: if.end14:
; CHECK-NEXT: [[X_0:%.*]] = phi i32 [ 9, [[FOR_BODY]] ], [ 3, [[IF_THEN]] ], [ [[DOT]], [[IF_ELSE]] ]
; CHECK-NEXT: store i32 [[X_0]], i32* [[ARRAYIDX]], align 4
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[N]]
[Loop Vectorize] Added a separate metadata Added a separate metadata to indicate when the loop has already been vectorized instead of setting width and count to 1. Patch written by Divya Shanmughan and Aditya Kumar Differential Revision: https://reviews.llvm.org/D36220 llvm-svn: 311281
2017-08-20 18:32:41 +08:00
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT]], label [[FOR_BODY]], !llvm.loop !7
[LoopVectorize] auto-generate complete checks; NFC I'm looking at a cmp transform in InstCombine that would affect these tests, but it's hard to know if it makes things better or worse without seeing the full IR. OTOH, maybe these tests shouldn't be running a bunch of transform passes in the first place? llvm-svn: 307475
2017-07-09 00:10:42 +08:00
; CHECK: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end:
; CHECK-NEXT: ret i32 undef
;
LoopVectorizer: Add support for if-conversion of PHINodes with 3+ incoming values. By supporting the vectorization of PHINodes with more than two incoming values we can increase the complexity of nested if statements. We can now vectorize this loop: int foo(int *A, int *B, int n) { for (int i=0; i < n; i++) { int x = 9; if (A[i] > B[i]) { if (A[i] > 19) { x = 3; } else if (B[i] < 4 ) { x = 4; } else { x = 5; } } A[i] = x; } } llvm-svn: 181037
2013-05-04 01:42:55 +08:00
entry:
%cmp26 = icmp sgt i32 %n, 0
br i1 %cmp26, label %for.body, label %for.end
for.body:
%indvars.iv = phi i64 [ %indvars.iv.next, %if.end14 ], [ 0, %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 i32, i32* %A, 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
[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
%arrayidx2 = getelementptr inbounds i32, i32* %B, 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
%1 = load i32, i32* %arrayidx2, align 4
LoopVectorizer: Add support for if-conversion of PHINodes with 3+ incoming values. By supporting the vectorization of PHINodes with more than two incoming values we can increase the complexity of nested if statements. We can now vectorize this loop: int foo(int *A, int *B, int n) { for (int i=0; i < n; i++) { int x = 9; if (A[i] > B[i]) { if (A[i] > 19) { x = 3; } else if (B[i] < 4 ) { x = 4; } else { x = 5; } } A[i] = x; } } llvm-svn: 181037
2013-05-04 01:42:55 +08:00
%cmp3 = icmp sgt i32 %0, %1
br i1 %cmp3, label %if.then, label %if.end14
if.then:
%cmp6 = icmp sgt i32 %0, 19
br i1 %cmp6, label %if.end14, label %if.else
if.else:
%cmp10 = icmp slt i32 %1, 4
%. = select i1 %cmp10, i32 4, i32 5
br label %if.end14
if.end14:
%x.0 = phi i32 [ 9, %for.body ], [ 3, %if.then ], [ %., %if.else ] ; <------------- A PHI with 3 entries that we can still vectorize.
store i32 %x.0, i32* %arrayidx, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret i32 undef
}
[LoopVectorize] auto-generate complete checks; NFC I'm looking at a cmp transform in InstCombine that would affect these tests, but it's hard to know if it makes things better or worse without seeing the full IR. OTOH, maybe these tests shouldn't be running a bunch of transform passes in the first place? llvm-svn: 307475
2017-07-09 00:10:42 +08:00