mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-02-06 06:33:24 +00:00
0d1978b813
This patch improves support for commutative instructions in the x86 memory folding implementation by attempting to fold a commuted version of the instruction if the original folding fails - if that folding fails as well the instruction is 're-commuted' back to its original order before returning. Updated version of r219584 (reverted in r219595) - the commutation attempt now explicitly ensures that neither of the commuted source operands are tied to the destination operand / register, which was the source of all the regressions that occurred with the original patch attempt. Added additional regression test case provided by Joerg Sonnenberger. Differential Revision: http://reviews.llvm.org/D5818 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@220239 91177308-0d34-0410-b5e6-96231b3b80d8
17 lines
664 B
LLVM
17 lines
664 B
LLVM
; RUN: llc -O3 -disable-peephole -mcpu=corei7-avx -mattr=+avx < %s | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-unknown"
|
|
|
|
; Function Attrs: nounwind readonly uwtable
|
|
define <32 x double> @_Z14vstack_foldDv32_dS_(<32 x double> %a, <32 x double> %b) #0 {
|
|
%1 = fadd <32 x double> %a, %b
|
|
%2 = fsub <32 x double> %a, %b
|
|
%3 = fmul <32 x double> %1, %2
|
|
ret <32 x double> %3
|
|
|
|
;CHECK-NOT: vmovapd {{.*#+}} 32-byte Reload
|
|
;CHECK: vmulpd {{[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}}, {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
|
|
;CHECK-NOT: vmovapd {{.*#+}} 32-byte Reload
|
|
}
|