mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-08-12 16:29:31 +00:00
df4b35e3dd
This also enables domain swizzling for AVX code which required a few trivial test changes. The pass will be moved to lib/CodeGen shortly. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@140659 91177308-0d34-0410-b5e6-96231b3b80d8
104 lines
4.0 KiB
LLVM
104 lines
4.0 KiB
LLVM
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck %s
|
|
|
|
|
|
; CHECK: vpunpcklbw %xmm
|
|
; CHECK-NEXT: vpunpckhbw %xmm
|
|
; CHECK-NEXT: vinsertf128 $1
|
|
; CHECK-NEXT: vpermilps $85
|
|
define <32 x i8> @funcA(<32 x i8> %a) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle = shufflevector <32 x i8> %a, <32 x i8> undef, <32 x i32> <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
|
|
ret <32 x i8> %shuffle
|
|
}
|
|
|
|
; CHECK: vpunpckhwd %xmm
|
|
; CHECK-NEXT: vinsertf128 $1
|
|
; CHECK-NEXT: vpermilps $85
|
|
define <16 x i16> @funcB(<16 x i16> %a) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle = shufflevector <16 x i16> %a, <16 x i16> undef, <16 x i32> <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
|
|
ret <16 x i16> %shuffle
|
|
}
|
|
|
|
; CHECK: vmovd
|
|
; CHECK-NEXT: vmovlhps %xmm
|
|
; CHECK-NEXT: vinsertf128 $1
|
|
define <4 x i64> @funcC(i64 %q) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%vecinit.i = insertelement <4 x i64> undef, i64 %q, i32 0
|
|
%vecinit2.i = insertelement <4 x i64> %vecinit.i, i64 %q, i32 1
|
|
%vecinit4.i = insertelement <4 x i64> %vecinit2.i, i64 %q, i32 2
|
|
%vecinit6.i = insertelement <4 x i64> %vecinit4.i, i64 %q, i32 3
|
|
ret <4 x i64> %vecinit6.i
|
|
}
|
|
|
|
; CHECK: vshufpd $0
|
|
; CHECK-NEXT: vinsertf128 $1
|
|
define <4 x double> @funcD(double %q) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%vecinit.i = insertelement <4 x double> undef, double %q, i32 0
|
|
%vecinit2.i = insertelement <4 x double> %vecinit.i, double %q, i32 1
|
|
%vecinit4.i = insertelement <4 x double> %vecinit2.i, double %q, i32 2
|
|
%vecinit6.i = insertelement <4 x double> %vecinit4.i, double %q, i32 3
|
|
ret <4 x double> %vecinit6.i
|
|
}
|
|
|
|
; Test this simple opt:
|
|
; shuffle (scalar_to_vector (load (ptr + 4))), undef, <0, 0, 0, 0>
|
|
; To:
|
|
; shuffle (vload ptr)), undef, <1, 1, 1, 1>
|
|
; CHECK: vmovdqa
|
|
; CHECK-NEXT: vinsertf128 $1
|
|
; CHECK-NEXT: vpermilps $-1
|
|
define <8 x float> @funcE() nounwind {
|
|
allocas:
|
|
%udx495 = alloca [18 x [18 x float]], align 32
|
|
br label %for_test505.preheader
|
|
|
|
for_test505.preheader: ; preds = %for_test505.preheader, %allocas
|
|
br i1 undef, label %for_exit499, label %for_test505.preheader
|
|
|
|
for_exit499: ; preds = %for_test505.preheader
|
|
br i1 undef, label %__load_and_broadcast_32.exit1249, label %load.i1247
|
|
|
|
load.i1247: ; preds = %for_exit499
|
|
%ptr1227 = getelementptr [18 x [18 x float]]* %udx495, i64 0, i64 1, i64 1
|
|
%ptr.i1237 = bitcast float* %ptr1227 to i32*
|
|
%val.i1238 = load i32* %ptr.i1237, align 4
|
|
%ret6.i1245 = insertelement <8 x i32> undef, i32 %val.i1238, i32 6
|
|
%ret7.i1246 = insertelement <8 x i32> %ret6.i1245, i32 %val.i1238, i32 7
|
|
%phitmp = bitcast <8 x i32> %ret7.i1246 to <8 x float>
|
|
br label %__load_and_broadcast_32.exit1249
|
|
|
|
__load_and_broadcast_32.exit1249: ; preds = %load.i1247, %for_exit499
|
|
%load_broadcast12281250 = phi <8 x float> [ %phitmp, %load.i1247 ], [ undef, %for_exit499 ]
|
|
ret <8 x float> %load_broadcast12281250
|
|
}
|
|
|
|
; CHECK: vinsertf128 $1
|
|
; CHECK-NEXT: vpermilps $0
|
|
define <8 x float> @funcF(i32 %val) nounwind {
|
|
%ret6 = insertelement <8 x i32> undef, i32 %val, i32 6
|
|
%ret7 = insertelement <8 x i32> %ret6, i32 %val, i32 7
|
|
%tmp = bitcast <8 x i32> %ret7 to <8 x float>
|
|
ret <8 x float> %tmp
|
|
}
|
|
|
|
; CHECK: vinsertf128 $1
|
|
; CHECK-NEXT: vpermilps $0
|
|
define <8 x float> @funcG(<8 x float> %a) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle = shufflevector <8 x float> %a, <8 x float> undef, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
|
|
ret <8 x float> %shuffle
|
|
}
|
|
|
|
; CHECK: vextractf128 $1
|
|
; CHECK-NEXT: vinsertf128 $1
|
|
; CHECK-NEXT: vpermilps $85
|
|
define <8 x float> @funcH(<8 x float> %a) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle = shufflevector <8 x float> %a, <8 x float> undef, <8 x i32> <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
|
|
ret <8 x float> %shuffle
|
|
}
|
|
|