maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/2011-10-27-tstore.ll

17 lines
376 B
LLVM
Raw Normal View History

Add a new DAGCombine optimization for BUILD_VECTOR. If all of the inputs are zero/any_extended, create a new simple BV which can be further optimized by other BV optimizations. llvm-svn: 143297
2011-10-30 05:23:04 +08:00
; RUN: llc < %s -march=x86-64 -mcpu=corei7 | FileCheck %s
target triple = "x86_64-unknown-linux-gnu"
;CHECK: ltstore
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 llvm-svn: 153848
2012-04-02 03:31:22 +08:00
;CHECK: movq
1. Remove the part of r153848 which optimizes shuffle-of-shuffle into a new shuffle node because it could introduce new shuffle nodes that were not supported efficiently by the target. 2. Add a more restrictive shuffle-of-shuffle optimization for cases where the second shuffle reverses the transformation of the first shuffle. llvm-svn: 154266
2012-04-08 05:19:08 +08:00
;CHECK: movq
;CHECK: ret
define void @ltstore(<4 x i32>* %pA, <2 x i32>* %pB) {
Add a new DAGCombine optimization for BUILD_VECTOR. If all of the inputs are zero/any_extended, create a new simple BV which can be further optimized by other BV optimizations. llvm-svn: 143297
2011-10-30 05:23:04 +08:00
entry:
1. Remove the part of r153848 which optimizes shuffle-of-shuffle into a new shuffle node because it could introduce new shuffle nodes that were not supported efficiently by the target. 2. Add a more restrictive shuffle-of-shuffle optimization for cases where the second shuffle reverses the transformation of the first shuffle. llvm-svn: 154266
2012-04-08 05:19:08 +08:00
%in = load <4 x i32>* %pA
Add a new DAGCombine optimization for BUILD_VECTOR. If all of the inputs are zero/any_extended, create a new simple BV which can be further optimized by other BV optimizations. llvm-svn: 143297
2011-10-30 05:23:04 +08:00
%j = shufflevector <4 x i32> %in, <4 x i32> undef, <2 x i32> <i32 0, i32 1>
1. Remove the part of r153848 which optimizes shuffle-of-shuffle into a new shuffle node because it could introduce new shuffle nodes that were not supported efficiently by the target. 2. Add a more restrictive shuffle-of-shuffle optimization for cases where the second shuffle reverses the transformation of the first shuffle. llvm-svn: 154266
2012-04-08 05:19:08 +08:00
store <2 x i32> %j, <2 x i32>* %pB
Add a new DAGCombine optimization for BUILD_VECTOR. If all of the inputs are zero/any_extended, create a new simple BV which can be further optimized by other BV optimizations. llvm-svn: 143297
2011-10-30 05:23:04 +08:00
ret void
}