maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[LV] Fix determinism for failing scalable-call.ll test. 

The sort function for emitting an OptRemark was not deterministic,
which caused scalable-call.ll to fail on some buildbots. This patch
fixes that.

This patch also fixes an issue where `Instruction::comesBefore()`
is called when two Instructions are in different basic blocks,
which would otherwise cause an assertion failure.
This commit is contained in:
Sander de Smalen 2021-07-15 12:22:24 +01:00
parent 01bdb0f75e
commit dc7bdc1e71
2 changed files with 44 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -6111,10 +6111,15 @@ VectorizationFactor LoopVectorizationCostModel::selectVectorizationFactor(
// Emit a report of VFs with invalid costs in the loop.
if (!InvalidCosts.empty()) {
// Sort/group per instruction
// Sort/group per instruction (lexicographically within basic blocks).
llvm::sort(InvalidCosts, [](InstructionVFPair &A, InstructionVFPair &B) {
const Instruction *AI = A.first, *BI = B.first;
if (AI->getParent() != BI->getParent())
return AI->getParent() < BI->getParent();
ElementCountComparator ECC;
return A.first->comesBefore(B.first) || ECC(A.second, B.second);
if (AI != BI)
return AI->comesBefore(BI);
return ECC(A.second, B.second);
});
// For a list of ordered instruction-vf pairs:

37
llvm/test/Transforms/LoopVectorize/AArch64/scalable-call.ll
View File

@ -123,6 +123,42 @@ for.cond.cleanup: ; preds = %for.body
ret void
}
; CHECK-REMARKS: UserVF ignored because of invalid costs.
; CHECK-REMARKS-NEXT: t.c:3:10: Instruction with invalid costs prevented vectorization at VF=(vscale x 1): load
; CHECK-REMARKS-NEXT: t.c:3:40: Instruction with invalid costs prevented vectorization at VF=(vscale x 1): store
; CHECK-REMARKS-NEXT: t.c:3:20: Instruction with invalid costs prevented vectorization at VF=(vscale x 1, vscale x 2): call to llvm.sin.f32
; CHECK-REMARKS-NEXT: t.c:3:30: Instruction with invalid costs prevented vectorization at VF=(vscale x 1, vscale x 2): call to llvm.sin.f32
define void @vec_sin_no_mapping_ite(float* noalias nocapture %dst, float* noalias nocapture readonly %src, i64 %n) {
; CHECK: @vec_sin_no_mapping_ite
; CHECK-NOT: <vscale x
; CHECK: ret
entry:
br label %for.body
for.body: ; preds = %entry, %if.end
%i.07 = phi i64 [ %inc, %if.end ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %src, i64 %i.07
%0 = load float, float* %arrayidx, align 4, !dbg !11
%cmp = fcmp ugt float %0, 0.0000
br i1 %cmp, label %if.then, label %if.else
if.then:
%1 = tail call fast float @llvm.sin.f32(float %0), !dbg !12
br label %if.end
if.else:
%2 = tail call fast float @llvm.sin.f32(float 0.0), !dbg !13
br label %if.end
if.end:
%3 = phi float [%1, %if.then], [%2, %if.else]
%arrayidx1 = getelementptr inbounds float, float* %dst, i64 %i.07
store float %3, float* %arrayidx1, align 4, !dbg !14
%inc = add nuw nsw i64 %i.07, 1
%exitcond.not = icmp eq i64 %inc, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body, !llvm.loop !1
for.cond.cleanup: ; preds = %for.body
ret void
}
; CHECK-REMARKS: UserVF ignored because of invalid costs.
; CHECK-REMARKS-NEXT: t.c:3:10: Instruction with invalid costs prevented vectorization at VF=(vscale x 1): load
; CHECK-REMARKS-NEXT: t.c:3:20: Instruction with invalid costs prevented vectorization at VF=(vscale x 1, vscale x 2): call to llvm.sin.f32
@ -208,3 +244,4 @@ attributes #3 = { "vector-function-abi-variant"="_ZGV_LLVM_N2v_llvm.sin.f64(sin_
!11 = !DILocation(line: 3, column: 10, scope: !9)
!12 = !DILocation(line: 3, column: 20, scope: !9)
!13 = !DILocation(line: 3, column: 30, scope: !9)
!14 = !DILocation(line: 3, column: 40, scope: !9)