diff options
author | Benjamin Kramer <benny.kra@googlemail.com> | 2013-02-04 15:19:18 +0000 |
---|---|---|
committer | Benjamin Kramer <benny.kra@googlemail.com> | 2013-02-04 15:19:18 +0000 |
commit | 4969310052f45b1e2e5d21735e38641a20be0e21 (patch) | |
tree | 04e90cfba49332cd63f2bb6fbf495761d54f5a5c /test/CodeGen | |
parent | 17174e59004d4df12f9037f0dc99ae530d71eab9 (diff) | |
download | llvm-4969310052f45b1e2e5d21735e38641a20be0e21.tar.gz llvm-4969310052f45b1e2e5d21735e38641a20be0e21.tar.bz2 llvm-4969310052f45b1e2e5d21735e38641a20be0e21.tar.xz |
SelectionDAG: Teach FoldConstantArithmetic how to deal with vectors.
This required disabling a PowerPC optimization that did the following:
input:
x = BUILD_VECTOR <i32 16, i32 16, i32 16, i32 16>
lowered to:
tmp = BUILD_VECTOR <i32 8, i32 8, i32 8, i32 8>
x = ADD tmp, tmp
The add now gets folded immediately and we're back at the BUILD_VECTOR we
started from. I don't see a way to fix this currently so I left it disabled
for now.
Fix some trivially foldable X86 tests too.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@174325 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen')
-rw-r--r-- | test/CodeGen/PowerPC/2008-07-10-SplatMiscompile.ll | 1 | ||||
-rw-r--r-- | test/CodeGen/X86/2011-11-30-or.ll | 4 | ||||
-rw-r--r-- | test/CodeGen/X86/blend-msb.ll | 6 | ||||
-rw-r--r-- | test/CodeGen/X86/vector-gep.ll | 3 |
4 files changed, 7 insertions, 7 deletions
diff --git a/test/CodeGen/PowerPC/2008-07-10-SplatMiscompile.ll b/test/CodeGen/PowerPC/2008-07-10-SplatMiscompile.ll index 8802b97d2a..00a402e0e4 100644 --- a/test/CodeGen/PowerPC/2008-07-10-SplatMiscompile.ll +++ b/test/CodeGen/PowerPC/2008-07-10-SplatMiscompile.ll @@ -1,5 +1,6 @@ ; RUN: llc < %s -march=ppc32 -mcpu=g5 | grep vadduhm ; RUN: llc < %s -march=ppc32 -mcpu=g5 | grep vsubuhm +; XFAIL: * define <4 x i32> @test() nounwind { ret <4 x i32> < i32 4293066722, i32 4293066722, i32 4293066722, i32 4293066722> diff --git a/test/CodeGen/X86/2011-11-30-or.ll b/test/CodeGen/X86/2011-11-30-or.ll index f66248bc5a..8ac4632329 100644 --- a/test/CodeGen/X86/2011-11-30-or.ll +++ b/test/CodeGen/X86/2011-11-30-or.ll @@ -8,9 +8,9 @@ target triple = "x86_64-apple-macosx10.6.6" ; CHECK: pblendvb %xmm1, %xmm2 ; CHECK: ret -define void @select_func() { +define void @select_func(<8 x i16> %in) { entry: - %c.lobit.i.i.i = ashr <8 x i16> <i16 17, i16 5, i16 1, i16 15, i16 19, i16 15, i16 4, i16 1> , <i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15> + %c.lobit.i.i.i = ashr <8 x i16> %in, <i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15> %and.i56.i.i.i = and <8 x i16> %c.lobit.i.i.i, <i16 25, i16 8, i16 65, i16 25, i16 8, i16 95, i16 15, i16 45> %and.i5.i.i.i = bitcast <8 x i16> %and.i56.i.i.i to <2 x i64> %neg.i.i.i.i = xor <8 x i16> %c.lobit.i.i.i, <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1> diff --git a/test/CodeGen/X86/blend-msb.ll b/test/CodeGen/X86/blend-msb.ll index 34445428ea..2b6b9ef8f3 100644 --- a/test/CodeGen/X86/blend-msb.ll +++ b/test/CodeGen/X86/blend-msb.ll @@ -5,7 +5,8 @@ ; shifting the needed bit to the MSB, and not using shl+sra. ;CHECK: vsel_float -;CHECK: pslld +;CHECK: movl $-2147483648 +;CHECK-NEXT: movd ;CHECK-NEXT: blendvps ;CHECK: ret define <4 x float> @vsel_float(<4 x float> %v1, <4 x float> %v2) { @@ -14,7 +15,8 @@ define <4 x float> @vsel_float(<4 x float> %v1, <4 x float> %v2) { } ;CHECK: vsel_4xi8 -;CHECK: pslld +;CHECK: movl $-2147483648 +;CHECK-NEXT: movd ;CHECK-NEXT: blendvps ;CHECK: ret define <4 x i8> @vsel_4xi8(<4 x i8> %v1, <4 x i8> %v2) { diff --git a/test/CodeGen/X86/vector-gep.ll b/test/CodeGen/X86/vector-gep.ll index d08e2a0746..ec93ce0761 100644 --- a/test/CodeGen/X86/vector-gep.ll +++ b/test/CodeGen/X86/vector-gep.ll @@ -8,10 +8,8 @@ entry: %vecinit2.i = insertelement <4 x i32*> %vecinit.i, i32* %ptr, i32 1 %vecinit4.i = insertelement <4 x i32*> %vecinit2.i, i32* %ptr, i32 2 %vecinit6.i = insertelement <4 x i32*> %vecinit4.i, i32* %ptr, i32 3 -;CHECK: pslld $2 ;CHECK: padd %A2 = getelementptr <4 x i32*> %vecinit6.i, <4 x i32> <i32 1, i32 2, i32 3, i32 4> -;CHECK: pslld $2 ;CHECK: padd %A3 = getelementptr <4 x i32*> %A2, <4 x i32> <i32 10, i32 14, i32 19, i32 233> ret <4 x i32*> %A3 @@ -21,7 +19,6 @@ entry: ;CHECK: AGEP1: define i32 @AGEP1(<4 x i32*> %param) nounwind { entry: -;CHECK: pslld $2 ;CHECK: padd %A2 = getelementptr <4 x i32*> %param, <4 x i32> <i32 1, i32 2, i32 3, i32 4> %k = extractelement <4 x i32*> %A2, i32 3 |