mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-24 13:33:37 +02:00
8d1918703c
AVX is available, and generally tidy up things surrounding UNPCK formation. Originally, I was thinking that the only advantage of PSHUFD over UNPCK instruction variants was its free copy, and otherwise we should use the shorter encoding UNPCK instructions. This isn't right though, there is a larger advantage of being able to fold a load into the operand of a PSHUFD. For UNPCK, the operand *must* be in a register so it can be the second input. This removes the UNPCK formation in the target-specific DAG combine for v4i32 shuffles. It also lifts the v8 and v16 cases out of the AVX-specific check as they are potentially replacing multiple instructions with a single instruction and so should always be valuable. The floating point checks are simplified accordingly. This also adjusts the formation of PSHUFD instructions to attempt to match the shuffle mask to one which would fit an UNPCK instruction variant. This was originally motivated to allow it to match the UNPCK instructions in the combiner, but clearly won't now. Eventually, we should add a MachineCombiner pass that can form UNPCK instructions post-RA when the operand is known to be in a register and thus there is no loss. llvm-svn: 217755
99 lines
3.9 KiB
LLVM
99 lines
3.9 KiB
LLVM
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck %s
|
|
|
|
|
|
; CHECK: vpshufb {{.*}} ## xmm0 = xmm0[5,5,5,5,5,5,5,5,5,5,5,5,5,5,5,5]
|
|
; CHECK-NEXT: vinsertf128 $1
|
|
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: vpshufd $85
|
|
; CHECK-NEXT: vinsertf128 $1
|
|
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: vmovq
|
|
; 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: vunpcklpd %xmm
|
|
; 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 turns into a broadcast:
|
|
; shuffle (scalar_to_vector (load (ptr + 4))), undef, <0, 0, 0, 0>
|
|
;
|
|
; CHECK: vbroadcastss
|
|
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: vpshufd $0
|
|
; CHECK-NEXT: vinsertf128 $1
|
|
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: vpshufd $0
|
|
; CHECK-NEXT: vinsertf128 $1
|
|
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: vpshufd
|
|
; CHECK-NEXT: vinsertf128 $1
|
|
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
|
|
}
|
|
|