forked from OSchip/llvm-project
[X86][SSE] Add SSE2/AVX2 vector rotate tests
Now that we're custom lowering vector rotates for SSE in general we should be testing the combines with them as well. llvm-svn: 334290
This commit is contained in:
Simon Pilgrim
parent
a6afa310c9
commit
eab9d20424
|
|
@ -1,14 +1,39 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+xop | FileCheck %s --check-prefix=XOP
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vl | FileCheck %s --check-prefix=AVX512
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE2
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+xop | FileCheck %s --check-prefixes=CHECK,XOP
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX2
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512vl | FileCheck %s --check-prefixes=CHECK,AVX512
|
||||
|
||||
; fold (rot (rot x, c1), c2) -> rot x, c1+c2
|
||||
define <4 x i32> @combine_vec_rot_rot(<4 x i32> %x) {
|
||||
; SSE2-LABEL: combine_vec_rot_rot:
|
||||
; SSE2: # %bb.0:
|
||||
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [524288,131072,32768,8192]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
|
||||
; SSE2-NEXT: pmuludq %xmm1, %xmm0
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,3,2,3]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
|
||||
; SSE2-NEXT: pmuludq %xmm2, %xmm1
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,3,2,3]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
||||
; SSE2-NEXT: por %xmm3, %xmm0
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; XOP-LABEL: combine_vec_rot_rot:
|
||||
; XOP: # %bb.0:
|
||||
; XOP-NEXT: vprotd {{.*}}(%rip), %xmm0, %xmm0
|
||||
; XOP-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: combine_vec_rot_rot:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpsrlvd {{.*}}(%rip), %xmm0, %xmm1
|
||||
; AVX2-NEXT: vpsllvd {{.*}}(%rip), %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: combine_vec_rot_rot:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vprolvd {{.*}}(%rip), %xmm0, %xmm0
|
||||
|
|
@ -23,11 +48,26 @@ define <4 x i32> @combine_vec_rot_rot(<4 x i32> %x) {
|
|||
}
|
||||
|
||||
define <4 x i32> @combine_vec_rot_rot_splat(<4 x i32> %x) {
|
||||
; SSE2-LABEL: combine_vec_rot_rot_splat:
|
||||
; SSE2: # %bb.0:
|
||||
; SSE2-NEXT: movdqa %xmm0, %xmm1
|
||||
; SSE2-NEXT: psrld $25, %xmm1
|
||||
; SSE2-NEXT: pslld $7, %xmm0
|
||||
; SSE2-NEXT: por %xmm1, %xmm0
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; XOP-LABEL: combine_vec_rot_rot_splat:
|
||||
; XOP: # %bb.0:
|
||||
; XOP-NEXT: vprotd $7, %xmm0, %xmm0
|
||||
; XOP-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: combine_vec_rot_rot_splat:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpsrld $25, %xmm0, %xmm1
|
||||
; AVX2-NEXT: vpslld $7, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpor %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: combine_vec_rot_rot_splat:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vprold $7, %xmm0, %xmm0
|
||||
|
|
@ -42,13 +82,9 @@ define <4 x i32> @combine_vec_rot_rot_splat(<4 x i32> %x) {
|
|||
}
|
||||
|
||||
define <4 x i32> @combine_vec_rot_rot_splat_zero(<4 x i32> %x) {
|
||||
; XOP-LABEL: combine_vec_rot_rot_splat_zero:
|
||||
; XOP: # %bb.0:
|
||||
; XOP-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: combine_vec_rot_rot_splat_zero:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: retq
|
||||
; CHECK-LABEL: combine_vec_rot_rot_splat_zero:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: retq
|
||||
%1 = lshr <4 x i32> %x, <i32 1, i32 1, i32 1, i32 1>
|
||||
%2 = shl <4 x i32> %x, <i32 31, i32 31, i32 31, i32 31>
|
||||
%3 = or <4 x i32> %1, %2
|
||||
|
|
@ -59,12 +95,42 @@ define <4 x i32> @combine_vec_rot_rot_splat_zero(<4 x i32> %x) {
|
|||
}
|
||||
|
||||
define <4 x i32> @rotate_demanded_bits(<4 x i32>, <4 x i32>) {
|
||||
; SSE2-LABEL: rotate_demanded_bits:
|
||||
; SSE2: # %bb.0:
|
||||
; SSE2-NEXT: pand {{.*}}(%rip), %xmm1
|
||||
; SSE2-NEXT: pslld $23, %xmm1
|
||||
; SSE2-NEXT: paddd {{.*}}(%rip), %xmm1
|
||||
; SSE2-NEXT: cvttps2dq %xmm1, %xmm1
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
|
||||
; SSE2-NEXT: pmuludq %xmm1, %xmm0
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,3,2,3]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
|
||||
; SSE2-NEXT: pmuludq %xmm2, %xmm1
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,3,2,3]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
||||
; SSE2-NEXT: por %xmm3, %xmm0
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; XOP-LABEL: rotate_demanded_bits:
|
||||
; XOP: # %bb.0:
|
||||
; XOP-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
|
||||
; XOP-NEXT: vprotd %xmm1, %xmm0, %xmm0
|
||||
; XOP-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: rotate_demanded_bits:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpbroadcastd {{.*#+}} xmm2 = [30,30,30,30]
|
||||
; AVX2-NEXT: vpand %xmm2, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vpsllvd %xmm1, %xmm0, %xmm2
|
||||
; AVX2-NEXT: vpbroadcastd {{.*#+}} xmm3 = [32,32,32,32]
|
||||
; AVX2-NEXT: vpsubd %xmm1, %xmm3, %xmm1
|
||||
; AVX2-NEXT: vpsrlvd %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpor %xmm0, %xmm2, %xmm0
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: rotate_demanded_bits:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpandd {{.*}}(%rip){1to4}, %xmm1, %xmm1
|
||||
|
|
@ -80,12 +146,42 @@ define <4 x i32> @rotate_demanded_bits(<4 x i32>, <4 x i32>) {
|
|||
}
|
||||
|
||||
define <4 x i32> @rotate_demanded_bits_2(<4 x i32>, <4 x i32>) {
|
||||
; SSE2-LABEL: rotate_demanded_bits_2:
|
||||
; SSE2: # %bb.0:
|
||||
; SSE2-NEXT: pand {{.*}}(%rip), %xmm1
|
||||
; SSE2-NEXT: pslld $23, %xmm1
|
||||
; SSE2-NEXT: paddd {{.*}}(%rip), %xmm1
|
||||
; SSE2-NEXT: cvttps2dq %xmm1, %xmm1
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
|
||||
; SSE2-NEXT: pmuludq %xmm1, %xmm0
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,3,2,3]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
|
||||
; SSE2-NEXT: pmuludq %xmm2, %xmm1
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,3,2,3]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
||||
; SSE2-NEXT: por %xmm3, %xmm0
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; XOP-LABEL: rotate_demanded_bits_2:
|
||||
; XOP: # %bb.0:
|
||||
; XOP-NEXT: vpand {{.*}}(%rip), %xmm1, %xmm1
|
||||
; XOP-NEXT: vprotd %xmm1, %xmm0, %xmm0
|
||||
; XOP-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: rotate_demanded_bits_2:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpbroadcastd {{.*#+}} xmm2 = [23,23,23,23]
|
||||
; AVX2-NEXT: vpand %xmm2, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vpsllvd %xmm1, %xmm0, %xmm2
|
||||
; AVX2-NEXT: vpbroadcastd {{.*#+}} xmm3 = [32,32,32,32]
|
||||
; AVX2-NEXT: vpsubd %xmm1, %xmm3, %xmm1
|
||||
; AVX2-NEXT: vpsrlvd %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpor %xmm0, %xmm2, %xmm0
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: rotate_demanded_bits_2:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpandd {{.*}}(%rip){1to4}, %xmm1, %xmm1
|
||||
|
|
@ -101,6 +197,26 @@ define <4 x i32> @rotate_demanded_bits_2(<4 x i32>, <4 x i32>) {
|
|||
}
|
||||
|
||||
define <4 x i32> @rotate_demanded_bits_3(<4 x i32>, <4 x i32>) {
|
||||
; SSE2-LABEL: rotate_demanded_bits_3:
|
||||
; SSE2: # %bb.0:
|
||||
; SSE2-NEXT: paddd %xmm1, %xmm1
|
||||
; SSE2-NEXT: pand {{.*}}(%rip), %xmm1
|
||||
; SSE2-NEXT: pslld $23, %xmm1
|
||||
; SSE2-NEXT: paddd {{.*}}(%rip), %xmm1
|
||||
; SSE2-NEXT: cvttps2dq %xmm1, %xmm1
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
|
||||
; SSE2-NEXT: pmuludq %xmm1, %xmm0
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm0[1,3,2,3]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[1,1,3,3]
|
||||
; SSE2-NEXT: pmuludq %xmm2, %xmm1
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,3,2,3]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
||||
; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
|
||||
; SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
||||
; SSE2-NEXT: por %xmm3, %xmm0
|
||||
; SSE2-NEXT: retq
|
||||
;
|
||||
; XOP-LABEL: rotate_demanded_bits_3:
|
||||
; XOP: # %bb.0:
|
||||
; XOP-NEXT: vpaddd %xmm1, %xmm1, %xmm1
|
||||
|
|
@ -108,6 +224,18 @@ define <4 x i32> @rotate_demanded_bits_3(<4 x i32>, <4 x i32>) {
|
|||
; XOP-NEXT: vprotd %xmm1, %xmm0, %xmm0
|
||||
; XOP-NEXT: retq
|
||||
;
|
||||
; AVX2-LABEL: rotate_demanded_bits_3:
|
||||
; AVX2: # %bb.0:
|
||||
; AVX2-NEXT: vpaddd %xmm1, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vpbroadcastd {{.*#+}} xmm2 = [30,30,30,30]
|
||||
; AVX2-NEXT: vpand %xmm2, %xmm1, %xmm1
|
||||
; AVX2-NEXT: vpsllvd %xmm1, %xmm0, %xmm2
|
||||
; AVX2-NEXT: vpbroadcastd {{.*#+}} xmm3 = [32,32,32,32]
|
||||
; AVX2-NEXT: vpsubd %xmm1, %xmm3, %xmm1
|
||||
; AVX2-NEXT: vpsrlvd %xmm1, %xmm0, %xmm0
|
||||
; AVX2-NEXT: vpor %xmm0, %xmm2, %xmm0
|
||||
; AVX2-NEXT: retq
|
||||
;
|
||||
; AVX512-LABEL: rotate_demanded_bits_3:
|
||||
; AVX512: # %bb.0:
|
||||
; AVX512-NEXT: vpaddd %xmm1, %xmm1, %xmm1
|
||||
|
|
|
|||
Loading…
Reference in New Issue