maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86] Don't generate vbroadcasti128 for v4i64 splats from memory. 

We used to erroneously match:
    (v4i64 shuffle (v2i64 load), <0,0,0,0>)

Whereas vbroadcasti128 is more like:
    (v4i64 shuffle (v2i64 load), <0,1,0,1>)

This problem doesn't exist for vbroadcastf128, which kept matching
the intrinsic after r231182.  We should perhaps re-introduce the
intrinsic here as well, but that's a separate issue still being
discussed.

While there, add some proper vbroadcastf128 tests.  We don't currently
match those, like for loading vbroadcastsd/ss on AVX (the reg-reg
broadcasts where added in AVX2).

Fixes PR23886.

llvm-svn: 240488
This commit is contained in:
Ahmed Bougacha 2015-06-24 00:07:16 +00:00
parent c7b685d997
commit dd5da3e7ed
2 changed files with 59 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
llvm/lib/Target/X86/X86InstrSSE.td
View File

@ -7860,10 +7860,11 @@ def VBROADCASTSDYrr : avx2_broadcast_reg<0x19, "vbroadcastsd", VR256,
int_x86_avx2_vbroadcast_sd_pd_256,
WriteFShuffle256>, VEX_L;
let Predicates = [HasAVX2] in
def VBROADCASTI128 : avx_broadcast_no_int<0x5A, "vbroadcasti128", VR256,
i128mem, v4i64, loadv2i64,
WriteLoad>, VEX_L;
let mayLoad = 1, Predicates = [HasAVX2] in
def VBROADCASTI128 : AVX8I<0x5A, MRMSrcMem, (outs VR256:$dst),
(ins i128mem:$src),
"vbroadcasti128\t{$src, $dst|$dst, $src}", []>,
Sched<[WriteLoad]>, VEX, VEX_L;
let Predicates = [HasAVX] in
def : Pat<(int_x86_avx_vbroadcastf128_ps_256 addr:$src),

54
llvm/test/CodeGen/X86/vector-shuffle-256-v4.ll
View File

@ -900,6 +900,60 @@ define <4 x double> @splat_v4f64(<2 x double> %r) {
ret <4 x double> %1
}
define <4 x i64> @splat_mem_v4i64_from_v2i64(<2 x i64>* %ptr) {
; AVX1-LABEL: splat_mem_v4i64_from_v2i64:
; AVX1: # BB#0:
; AVX1-NEXT: vmovddup {{.*#+}} xmm0 = mem[0,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: splat_mem_v4i64_from_v2i64:
; AVX2: # BB#0:
; AVX2-NEXT: vbroadcastsd (%rdi), %ymm0
; AVX2-NEXT: retq
%v = load <2 x i64>, <2 x i64>* %ptr
%shuffle = shufflevector <2 x i64> %v, <2 x i64> undef, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
ret <4 x i64> %shuffle
}
define <4 x double> @splat_mem_v4f64_from_v2f64(<2 x double>* %ptr) {
; AVX1-LABEL: splat_mem_v4f64_from_v2f64:
; AVX1: # BB#0:
; AVX1-NEXT: vmovddup {{.*#+}} xmm0 = mem[0,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: splat_mem_v4f64_from_v2f64:
; AVX2: # BB#0:
; AVX2-NEXT: vbroadcastsd (%rdi), %ymm0
; AVX2-NEXT: retq
%v = load <2 x double>, <2 x double>* %ptr
%shuffle = shufflevector <2 x double> %v, <2 x double> undef, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
ret <4 x double> %shuffle
}
define <4 x i64> @splat128_mem_v4i64_from_v2i64(<2 x i64>* %ptr) {
; ALL-LABEL: splat128_mem_v4i64_from_v2i64:
; ALL: # BB#0:
; ALL-NEXT: vmovaps (%rdi), %xmm0
; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; ALL-NEXT: retq
%v = load <2 x i64>, <2 x i64>* %ptr
%shuffle = shufflevector <2 x i64> %v, <2 x i64> undef, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
ret <4 x i64> %shuffle
}
define <4 x double> @splat128_mem_v4f64_from_v2f64(<2 x double>* %ptr) {
; ALL-LABEL: splat128_mem_v4f64_from_v2f64:
; ALL: # BB#0:
; ALL-NEXT: vmovaps (%rdi), %xmm0
; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; ALL-NEXT: retq
%v = load <2 x double>, <2 x double>* %ptr
%shuffle = shufflevector <2 x double> %v, <2 x double> undef, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
ret <4 x double> %shuffle
}
define <4 x double> @bitcast_v4f64_0426(<4 x double> %a, <4 x double> %b) {
; AVX1-LABEL: bitcast_v4f64_0426:
; AVX1: # BB#0: