c22dc71b12
I had manually removed unused prefixes from CodeGen/X86 directory for more than 100 tests. I checked the change history for each of them at the beginning, and then I mainly focused on the format since I found all of the unused prefixes were result from either insensible copy or residuum after functional update. I think it's OK to remove the remaining X86 tests by script now. I wrote a rough script which works for me in most tests. I put it in llvm/utils temporarily for review and hope it may help other components owners. The tests in this patch are all generated by the tool and checked by update tool for the autogenerated tests. I skimmed them and checked about 30 tests and didn't find any unexpected changes. Reviewed By: mtrofin, MaskRay Differential Revision: https://reviews.llvm.org/D91496
71 lines
2.6 KiB
LLVM
71 lines
2.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx | FileCheck %s --check-prefix=AVX
|
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx2 | FileCheck %s --check-prefix=AVX
|
|
|
|
; Prefer a blend instruction to a vinsert128 instruction because blends
|
|
; are simpler (no lane changes) and therefore will have equal or better
|
|
; performance.
|
|
|
|
define <8 x float> @castA(<4 x float> %m) nounwind uwtable readnone ssp {
|
|
; AVX-LABEL: castA:
|
|
; AVX: ## %bb.0:
|
|
; AVX-NEXT: vmovaps %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
%shuffle.i = shufflevector <4 x float> %m, <4 x float> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 4, i32 4, i32 4>
|
|
ret <8 x float> %shuffle.i
|
|
}
|
|
|
|
define <4 x double> @castB(<2 x double> %m) nounwind uwtable readnone ssp {
|
|
; AVX-LABEL: castB:
|
|
; AVX: ## %bb.0:
|
|
; AVX-NEXT: vmovaps %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
%shuffle.i = shufflevector <2 x double> %m, <2 x double> zeroinitializer, <4 x i32> <i32 0, i32 1, i32 2, i32 2>
|
|
ret <4 x double> %shuffle.i
|
|
}
|
|
|
|
; AVX2 is needed for integer types.
|
|
|
|
define <4 x i64> @castC(<2 x i64> %m) nounwind uwtable readnone ssp {
|
|
; AVX-LABEL: castC:
|
|
; AVX: ## %bb.0:
|
|
; AVX-NEXT: vmovaps %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
%shuffle.i = shufflevector <2 x i64> %m, <2 x i64> zeroinitializer, <4 x i32> <i32 0, i32 1, i32 2, i32 2>
|
|
ret <4 x i64> %shuffle.i
|
|
}
|
|
|
|
; The next three tests don't need any shuffling. There may or may not be a
|
|
; vzeroupper before the return, so just check for the absence of shuffles.
|
|
|
|
define <4 x float> @castD(<8 x float> %m) nounwind uwtable readnone ssp {
|
|
; AVX-LABEL: castD:
|
|
; AVX: ## %bb.0:
|
|
; AVX-NEXT: ## kill: def $xmm0 killed $xmm0 killed $ymm0
|
|
; AVX-NEXT: vzeroupper
|
|
; AVX-NEXT: retq
|
|
%shuffle.i = shufflevector <8 x float> %m, <8 x float> %m, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
ret <4 x float> %shuffle.i
|
|
}
|
|
|
|
define <2 x i64> @castE(<4 x i64> %m) nounwind uwtable readnone ssp {
|
|
; AVX-LABEL: castE:
|
|
; AVX: ## %bb.0:
|
|
; AVX-NEXT: ## kill: def $xmm0 killed $xmm0 killed $ymm0
|
|
; AVX-NEXT: vzeroupper
|
|
; AVX-NEXT: retq
|
|
%shuffle.i = shufflevector <4 x i64> %m, <4 x i64> %m, <2 x i32> <i32 0, i32 1>
|
|
ret <2 x i64> %shuffle.i
|
|
}
|
|
|
|
define <2 x double> @castF(<4 x double> %m) nounwind uwtable readnone ssp {
|
|
; AVX-LABEL: castF:
|
|
; AVX: ## %bb.0:
|
|
; AVX-NEXT: ## kill: def $xmm0 killed $xmm0 killed $ymm0
|
|
; AVX-NEXT: vzeroupper
|
|
; AVX-NEXT: retq
|
|
%shuffle.i = shufflevector <4 x double> %m, <4 x double> %m, <2 x i32> <i32 0, i32 1>
|
|
ret <2 x double> %shuffle.i
|
|
}
|
|
|