diff options
author | Guozhi Wei <carrot@google.com> | 2016-10-25 20:43:42 +0000 |
---|---|---|
committer | Guozhi Wei <carrot@google.com> | 2016-10-25 20:43:42 +0000 |
commit | ae541f6a71ebffc96411fc6ce7437ad1cd03181c (patch) | |
tree | a39b9b89758a8da7c59c13ef8c86ce239b71c252 /llvm/test | |
parent | b3f709e10f37225ae65c1d48c4623f6abc2cac1e (diff) | |
download | bcm5719-llvm-ae541f6a71ebffc96411fc6ce7437ad1cd03181c.tar.gz bcm5719-llvm-ae541f6a71ebffc96411fc6ce7437ad1cd03181c.zip |
[InstCombine] Resubmit the combine of A->B->A BitCast and fix for pr27996
The original patch of the A->B->A BitCast optimization was reverted by r274094 because it may cause infinite loop inside compiler https://llvm.org/bugs/show_bug.cgi?id=27996.
The problem is with following code
xB = load (type B);
xA = load (type A);
+yA = (A)xB; B -> A
+zAn = PHI[yA, xA]; PHI
+zBn = (B)zAn; // A -> B
store zAn;
store zBn;
optimizeBitCastFromPhi generates
+zBn = (B)zAn; // A -> B
and expects it will be combined with the following store instruction to another
store zAn
Unfortunately before combineStoreToValueType is called on the store instruction, optimizeBitCastFromPhi is called on the new BitCast again, and this pattern repeats indefinitely.
optimizeBitCastFromPhi only generates BitCast for load/store instructions, only the BitCast before store can cause the reexecution of optimizeBitCastFromPhi, and BitCast before store can easily be handled by InstCombineLoadStoreAlloca.cpp. So the solution to the problem is if all users of a CI are store instructions, we should not do optimizeBitCastFromPhi on it. Then optimizeBitCastFromPhi will not be called on the new BitCast instructions.
Differential Revision: https://reviews.llvm.org/D23896
llvm-svn: 285116
Diffstat (limited to 'llvm/test')
-rw-r--r-- | llvm/test/Transforms/InstCombine/pr25342.ll | 93 | ||||
-rw-r--r-- | llvm/test/Transforms/InstCombine/pr27703.ll | 20 | ||||
-rw-r--r-- | llvm/test/Transforms/InstCombine/pr27996.ll | 41 |
3 files changed, 154 insertions, 0 deletions
diff --git a/llvm/test/Transforms/InstCombine/pr25342.ll b/llvm/test/Transforms/InstCombine/pr25342.ll new file mode 100644 index 00000000000..b9cc3755a20 --- /dev/null +++ b/llvm/test/Transforms/InstCombine/pr25342.ll @@ -0,0 +1,93 @@ +; RUN: opt < %s -instcombine -S | FileCheck %s + +%"struct.std::complex" = type { { float, float } } +@dd = external global %"struct.std::complex", align 4 +@dd2 = external global %"struct.std::complex", align 4 + +define void @_Z3fooi(i32 signext %n) { +entry: + br label %for.cond + +for.cond: + %ldd.sroa.0.0 = phi i32 [ 0, %entry ], [ %5, %for.body ] + %ldd.sroa.6.0 = phi i32 [ 0, %entry ], [ %7, %for.body ] + %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ] + %cmp = icmp slt i32 %i.0, %n + br i1 %cmp, label %for.body, label %for.end + +for.body: + %0 = load float, float* getelementptr inbounds (%"struct.std::complex", %"struct.std::complex"* @dd, i64 0, i32 0, i32 0), align 4 + %1 = load float, float* getelementptr inbounds (%"struct.std::complex", %"struct.std::complex"* @dd, i64 0, i32 0, i32 1), align 4 + %2 = load float, float* getelementptr inbounds (%"struct.std::complex", %"struct.std::complex"* @dd2, i64 0, i32 0, i32 0), align 4 + %3 = load float, float* getelementptr inbounds (%"struct.std::complex", %"struct.std::complex"* @dd2, i64 0, i32 0, i32 1), align 4 + %mul.i = fmul float %0, %2 + %mul4.i = fmul float %1, %3 + %sub.i = fsub float %mul.i, %mul4.i + %mul5.i = fmul float %1, %2 + %mul6.i = fmul float %0, %3 + %add.i4 = fadd float %mul5.i, %mul6.i + %4 = bitcast i32 %ldd.sroa.0.0 to float + %add.i = fadd float %sub.i, %4 + %5 = bitcast float %add.i to i32 + %6 = bitcast i32 %ldd.sroa.6.0 to float + %add4.i = fadd float %add.i4, %6 + %7 = bitcast float %add4.i to i32 + %inc = add nsw i32 %i.0, 1 + br label %for.cond + +for.end: + store i32 %ldd.sroa.0.0, i32* bitcast (%"struct.std::complex"* @dd to i32*), align 4 + store i32 %ldd.sroa.6.0, i32* bitcast (float* getelementptr inbounds (%"struct.std::complex", %"struct.std::complex"* @dd, i64 0, i32 0, i32 1) to i32*), align 4 + ret void + +; CHECK: phi float +; CHECK: store float +; CHECK-NOT: bitcast +} + + +define void @multi_phi(i32 signext %n) { +entry: + br label %for.cond + +for.cond: + %ldd.sroa.0.0 = phi i32 [ 0, %entry ], [ %9, %odd.bb ] + %i.0 = phi i32 [ 0, %entry ], [ %inc, %odd.bb ] + %cmp = icmp slt i32 %i.0, %n + br i1 %cmp, label %for.body, label %for.end + +for.body: + %0 = load float, float* getelementptr inbounds (%"struct.std::complex", %"struct.std::complex"* @dd, i64 0, i32 0, i32 0), align 4 + %1 = load float, float* getelementptr inbounds (%"struct.std::complex", %"struct.std::complex"* @dd, i64 0, i32 0, i32 1), align 4 + %2 = load float, float* getelementptr inbounds (%"struct.std::complex", %"struct.std::complex"* @dd2, i64 0, i32 0, i32 0), align 4 + %3 = load float, float* getelementptr inbounds (%"struct.std::complex", %"struct.std::complex"* @dd2, i64 0, i32 0, i32 1), align 4 + %mul.i = fmul float %0, %2 + %mul4.i = fmul float %1, %3 + %sub.i = fsub float %mul.i, %mul4.i + %4 = bitcast i32 %ldd.sroa.0.0 to float + %add.i = fadd float %sub.i, %4 + %5 = bitcast float %add.i to i32 + %inc = add nsw i32 %i.0, 1 + %bit0 = and i32 %inc, 1 + %even = icmp slt i32 %bit0, 1 + br i1 %even, label %even.bb, label %odd.bb + +even.bb: + %6 = bitcast i32 %5 to float + %7 = fadd float %sub.i, %6 + %8 = bitcast float %7 to i32 + br label %odd.bb + +odd.bb: + %9 = phi i32 [ %5, %for.body ], [ %8, %even.bb ] + br label %for.cond + +for.end: + store i32 %ldd.sroa.0.0, i32* bitcast (%"struct.std::complex"* @dd to i32*), align 4 + ret void + +; CHECK-LABEL: @multi_phi( +; CHECK: phi float +; CHECK: store float +; CHECK-NOT: bitcast +} diff --git a/llvm/test/Transforms/InstCombine/pr27703.ll b/llvm/test/Transforms/InstCombine/pr27703.ll new file mode 100644 index 00000000000..2981afe171e --- /dev/null +++ b/llvm/test/Transforms/InstCombine/pr27703.ll @@ -0,0 +1,20 @@ +; RUN: opt < %s -instcombine -S | FileCheck %s + +define void @mem() { +bb: + br label %bb6 + +bb6: + %.0 = phi i8** [ undef, %bb ], [ %t2, %bb6 ] + %tmp = load i8*, i8** %.0, align 8 + %bc = bitcast i8* %tmp to i8** + %t1 = load i8*, i8** %bc, align 8 + %t2 = bitcast i8* %t1 to i8** + br label %bb6 + +bb206: + ret void +; CHECK: phi +; CHECK: bitcast +; CHECK: load +} diff --git a/llvm/test/Transforms/InstCombine/pr27996.ll b/llvm/test/Transforms/InstCombine/pr27996.ll new file mode 100644 index 00000000000..3fefe6e7839 --- /dev/null +++ b/llvm/test/Transforms/InstCombine/pr27996.ll @@ -0,0 +1,41 @@ +; RUN: opt < %s -instcombine -S | FileCheck %s + + +@i = constant i32 1, align 4 +@f = constant float 0x3FF19999A0000000, align 4 +@cmp = common global i32 0, align 4 +@resf = common global float* null, align 8 +@resi = common global i32* null, align 8 + +define i32 @foo() { +entry: + br label %while.cond + +while.cond: + %res.0 = phi i32* [ null, %entry ], [ @i, %if.then ], [ bitcast (float* @f to i32*), %if.else ] + %0 = load i32, i32* @cmp, align 4 + %shr = ashr i32 %0, 1 + store i32 %shr, i32* @cmp, align 4 + %tobool = icmp ne i32 %shr, 0 + br i1 %tobool, label %while.body, label %while.end + +while.body: + %and = and i32 %shr, 1 + %tobool1 = icmp ne i32 %and, 0 + br i1 %tobool1, label %if.then, label %if.else + +if.then: + br label %while.cond + +if.else: + br label %while.cond + +while.end: + %1 = bitcast i32* %res.0 to float* + store float* %1, float** @resf, align 8 + store i32* %res.0, i32** @resi, align 8 + ret i32 0 + +; CHECK-NOT: bitcast i32 +} + |