llvm-6502/test/CodeGen/X86/vec_shuffle-37.ll
Nadav Rotem 4ac9081c71 This commit contains a few changes that had to go in together.
1. Simplify xor/and/or (bitcast(A), bitcast(B)) -> bitcast(op (A,B))
   (and also scalar_to_vector).

2. Xor/and/or are indifferent to the swizzle operation (shuffle of one src).
   Simplify xor/and/or (shuff(A), shuff(B)) -> shuff(op (A, B))

3. Optimize swizzles of shuffles:  shuff(shuff(x, y), undef) -> shuff(x, y).

4. Fix an X86ISelLowering optimization which was very bitcast-sensitive.

Code which was previously compiled to this:

movd    (%rsi), %xmm0
movdqa  .LCPI0_0(%rip), %xmm2
pshufb  %xmm2, %xmm0
movd    (%rdi), %xmm1
pshufb  %xmm2, %xmm1
pxor    %xmm0, %xmm1
pshufb  .LCPI0_1(%rip), %xmm1
movd    %xmm1, (%rdi)
ret

Now compiles to this:

movl    (%rsi), %eax
xorl    %eax, (%rdi)
ret




git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153848 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-01 19:31:22 +00:00

48 lines
1.6 KiB
LLVM

; RUN: llc < %s -mtriple=x86_64-linux | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-win32 | FileCheck %s
; RUN: llc -O0 < %s -march=x86 -mcpu=core2 | FileCheck %s --check-prefix=CHECK_O0
define <4 x i32> @t00(<4 x i32>* %a0) nounwind ssp {
entry:
; CHECK: movaps ({{%rdi|%rcx}}), %xmm0
; CHECK: movaps %xmm0, %xmm1
; CHECK-NEXT: movss %xmm2, %xmm1
; CHECK-NEXT: shufps $36, %xmm1, %xmm0
%0 = load <4 x i32>* undef, align 16
%1 = load <4 x i32>* %a0, align 16
%2 = shufflevector <4 x i32> %1, <4 x i32> %0, <4 x i32> <i32 0, i32 1, i32 2, i32 4>
ret <4 x i32> %2
}
define void @t01(double* %a0) nounwind ssp {
entry:
; CHECK_O0: movsd (%eax), %xmm0
; CHECK_O0: unpcklpd %xmm0, %xmm0
%tmp93 = load double* %a0, align 8
%vecinit94 = insertelement <2 x double> undef, double %tmp93, i32 1
store <2 x double> %vecinit94, <2 x double>* undef
ret void
}
define void @t02(<8 x i32>* %source, <2 x i32>* %dest) nounwind noinline {
entry:
; CHECK: t02
; CHECK: mov
; CHECK-NEXT: mov
; CHECK-NEXT: mov
; CHECK-NEXT: mov
; CHECK-NEXT: ret
%0 = bitcast <8 x i32>* %source to <4 x i32>*
%arrayidx = getelementptr inbounds <4 x i32>* %0, i64 3
%tmp2 = load <4 x i32>* %arrayidx, align 16
%tmp3 = extractelement <4 x i32> %tmp2, i32 0
%tmp5 = insertelement <2 x i32> <i32 undef, i32 0>, i32 %tmp3, i32 0
%arrayidx7 = getelementptr inbounds <8 x i32>* %source, i64 1
%1 = bitcast <8 x i32>* %arrayidx7 to <4 x i32>*
%tmp8 = load <4 x i32>* %1, align 16
%tmp9 = extractelement <4 x i32> %tmp8, i32 1
%tmp11 = insertelement <2 x i32> %tmp5, i32 %tmp9, i32 1
store <2 x i32> %tmp11, <2 x i32>* %dest, align 8
ret void
}