aboutsummaryrefslogtreecommitdiffstats
path: root/test/CodeGen/X86/widen_shuffle-1.ll
diff options
context:
space:
mode:
authorChris Lattner <sabre@nondot.org>2010-08-25 22:49:25 +0000
committerChris Lattner <sabre@nondot.org>2010-08-25 22:49:25 +0000
commite6f7c267df11a44679c35dec79787fbc276839fb (patch)
tree831f622cb82ef17861f20320751316a0edf4fe9f /test/CodeGen/X86/widen_shuffle-1.ll
parente6e0018d3e6b5a7dae8b8ecf7ca3f31476e07800 (diff)
downloadexternal_llvm-e6f7c267df11a44679c35dec79787fbc276839fb.zip
external_llvm-e6f7c267df11a44679c35dec79787fbc276839fb.tar.gz
external_llvm-e6f7c267df11a44679c35dec79787fbc276839fb.tar.bz2
Change handling of illegal vector types to widen when possible instead of
expanding: e.g. <2 x float> -> <4 x float> instead of -> 2 floats. This affects two places in the code: handling cross block values and handling function return and arguments. Since vectors are already widened by legalizetypes, this gives us much better code and unblocks x86-64 abi and SPU abi work. For example, this (which is a silly example of a cross-block value): define <4 x float> @test2(<4 x float> %A) nounwind { %B = shufflevector <4 x float> %A, <4 x float> undef, <2 x i32> <i32 0, i32 1> %C = fadd <2 x float> %B, %B br label %BB BB: %D = fadd <2 x float> %C, %C %E = shufflevector <2 x float> %D, <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef> ret <4 x float> %E } Now compiles into: _test2: ## @test2 ## BB#0: addps %xmm0, %xmm0 addps %xmm0, %xmm0 ret previously it compiled into: _test2: ## @test2 ## BB#0: addps %xmm0, %xmm0 pshufd $1, %xmm0, %xmm1 ## kill: XMM0<def> XMM0<kill> XMM0<def> insertps $0, %xmm0, %xmm0 insertps $16, %xmm1, %xmm0 addps %xmm0, %xmm0 ret This implements rdar://8230384 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112101 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen/X86/widen_shuffle-1.ll')
-rw-r--r--test/CodeGen/X86/widen_shuffle-1.ll8
1 files changed, 5 insertions, 3 deletions
diff --git a/test/CodeGen/X86/widen_shuffle-1.ll b/test/CodeGen/X86/widen_shuffle-1.ll
index 25dde57..463f522 100644
--- a/test/CodeGen/X86/widen_shuffle-1.ll
+++ b/test/CodeGen/X86/widen_shuffle-1.ll
@@ -3,7 +3,8 @@
; widening shuffle v3float and then a add
define void @shuf(<3 x float>* %dst.addr, <3 x float> %src1,<3 x float> %src2) nounwind {
entry:
-; CHECK: insertps
+; CHECK: shuf:
+; CHECK: extractps
; CHECK: extractps
%x = shufflevector <3 x float> %src1, <3 x float> %src2, <3 x i32> < i32 0, i32 1, i32 2>
%val = fadd <3 x float> %x, %src2
@@ -15,7 +16,8 @@ entry:
; widening shuffle v3float with a different mask and then a add
define void @shuf2(<3 x float>* %dst.addr, <3 x float> %src1,<3 x float> %src2) nounwind {
entry:
-; CHECK: insertps
+; CHECK: shuf2:
+; CHECK: extractps
; CHECK: extractps
%x = shufflevector <3 x float> %src1, <3 x float> %src2, <3 x i32> < i32 0, i32 4, i32 2>
%val = fadd <3 x float> %x, %src2
@@ -26,7 +28,7 @@ entry:
; Example of when widening a v3float operation causes the DAG to replace a node
; with the operation that we are currently widening, i.e. when replacing
; opA with opB, the DAG will produce new operations with opA.
-define void @shuf3(<4 x float> %tmp10, <4 x float> %vecinit15, <4 x float>* %dst) {
+define void @shuf3(<4 x float> %tmp10, <4 x float> %vecinit15, <4 x float>* %dst) nounwind {
entry:
; CHECK: pshufd
%shuffle.i.i.i12 = shufflevector <4 x float> %tmp10, <4 x float> %vecinit15, <4 x i32> <i32 0, i32 1, i32 4, i32 5>