[llvm] r314385 - [X86] Adding more cases to horizontal [f]add/[f]sub for avx512.
Jatin Bhateja via llvm-commits
llvm-commits at lists.llvm.org
Thu Sep 28 00:40:53 PDT 2017
Author: jbhateja
Date: Thu Sep 28 00:40:52 2017
New Revision: 314385
URL: http://llvm.org/viewvc/llvm-project?rev=314385&view=rev
Log:
[X86] Adding more cases to horizontal [f]add/[f]sub for avx512.
Reviewers: jbhateja
Reviewed By: jbhateja
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D38344
Modified:
llvm/trunk/test/CodeGen/X86/avx512-hadd-hsub.ll
Modified: llvm/trunk/test/CodeGen/X86/avx512-hadd-hsub.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/avx512-hadd-hsub.ll?rev=314385&r1=314384&r2=314385&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/avx512-hadd-hsub.ll (original)
+++ llvm/trunk/test/CodeGen/X86/avx512-hadd-hsub.ll Thu Sep 28 00:40:52 2017
@@ -111,10 +111,6 @@ define float @fhsub_16(<16 x float> %x22
}
define <16 x i32> @hadd_16_3(<16 x i32> %x225, <16 x i32> %x227) {
-; CHECK-LABEL: hadd_16_3:
-; CHECK: # BB#0:
-; CHECK-NEXT: vphaddd %ymm1, %ymm0, %ymm0
-; CHECK-NEXT: retq
; KNL-LABEL: hadd_16_3:
; KNL: # BB#0:
; KNL-NEXT: vshufps {{.*#+}} ymm2 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
@@ -138,10 +134,6 @@ define <16 x i32> @hadd_16_3(<16 x i32>
}
define <16 x float> @fhadd_16_3(<16 x float> %x225, <16 x float> %x227) {
-; CHECK-LABEL: fhadd_16_3:
-; CHECK: # BB#0:
-; CHECK-NEXT: vhaddps %ymm1, %ymm0, %ymm0
-; CHECK-NEXT: retq
; KNL-LABEL: fhadd_16_3:
; KNL: # BB#0:
; KNL-NEXT: vshufps {{.*#+}} ymm2 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
@@ -164,14 +156,6 @@ define <16 x float> @fhadd_16_3(<16 x fl
}
define <8 x double> @fhadd_16_4(<8 x double> %x225, <8 x double> %x227) {
-; CHECK-LABEL: fhadd_16_4:
-; CHECK: # BB#0:
-; CHECK-NEXT: vunpcklpd {{.*#+}} ymm2 = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
-; CHECK-NEXT: vpermpd {{.*#+}} ymm2 = ymm2[0,2,1,3]
-; CHECK-NEXT: vunpckhpd {{.*#+}} ymm0 = ymm0[1],ymm1[1],ymm0[3],ymm1[3]
-; CHECK-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
-; CHECK-NEXT: vaddpd %zmm0, %zmm2, %zmm0
-; CHECK-NEXT: retq
; KNL-LABEL: fhadd_16_4:
; KNL: # BB#0:
; KNL-NEXT: vunpcklpd {{.*#+}} ymm2 = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
@@ -190,3 +174,130 @@ define <8 x double> @fhadd_16_4(<8 x dou
%x229 = fadd <8 x double> %x226, %x228
ret <8 x double> %x229
}
+
+define <4 x double> @fadd_noundef_low(<8 x double> %x225, <8 x double> %x227) {
+; KNL-LABEL: fadd_noundef_low:
+; KNL: # BB#0:
+; KNL-NEXT: vunpcklpd {{.*#+}} zmm2 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6]
+; KNL-NEXT: vunpckhpd {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7]
+; KNL-NEXT: vaddpd %zmm0, %zmm2, %zmm0
+; KNL-NEXT: # kill: %YMM0<def> %YMM0<kill> %ZMM0<kill>
+; KNL-NEXT: retq
+;
+; SKX-LABEL: fadd_noundef_low:
+; SKX: # BB#0:
+; SKX-NEXT: vunpcklpd {{.*#+}} zmm2 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6]
+; SKX-NEXT: vunpckhpd {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7]
+; SKX-NEXT: vaddpd %zmm0, %zmm2, %zmm0
+; SKX-NEXT: # kill: %YMM0<def> %YMM0<kill> %ZMM0<kill>
+; SKX-NEXT: retq
+ %x226 = shufflevector <8 x double> %x225, <8 x double> %x227, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+ %x228 = shufflevector <8 x double> %x225, <8 x double> %x227, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5 ,i32 13, i32 7, i32 15>
+ %x229 = fadd <8 x double> %x226, %x228
+ %x230 = shufflevector <8 x double> %x229, <8 x double> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
+ ret <4 x double> %x230
+}
+
+define <4 x double> @fadd_noundef_high(<8 x double> %x225, <8 x double> %x227) {
+; KNL-LABEL: fadd_noundef_high:
+; KNL: # BB#0:
+; KNL-NEXT: vunpcklpd {{.*#+}} zmm2 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6]
+; KNL-NEXT: vunpckhpd {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7]
+; KNL-NEXT: vaddpd %zmm0, %zmm2, %zmm0
+; KNL-NEXT: vextractf64x4 $1, %zmm0, %ymm0
+; KNL-NEXT: retq
+;
+; SKX-LABEL: fadd_noundef_high:
+; SKX: # BB#0:
+; SKX-NEXT: vunpcklpd {{.*#+}} zmm2 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6]
+; SKX-NEXT: vunpckhpd {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7]
+; SKX-NEXT: vaddpd %zmm0, %zmm2, %zmm0
+; SKX-NEXT: vextractf64x4 $1, %zmm0, %ymm0
+; SKX-NEXT: retq
+ %x226 = shufflevector <8 x double> %x225, <8 x double> %x227, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+ %x228 = shufflevector <8 x double> %x225, <8 x double> %x227, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5 ,i32 13, i32 7, i32 15>
+ %x229 = fadd <8 x double> %x226, %x228
+ %x230 = shufflevector <8 x double> %x229, <8 x double> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
+ ret <4 x double> %x230
+}
+
+
+define <8 x i32> @hadd_16_3_sv(<16 x i32> %x225, <16 x i32> %x227) {
+; KNL-LABEL: hadd_16_3_sv:
+; KNL: # BB#0:
+; KNL-NEXT: vshufps {{.*#+}} zmm2 = zmm0[0,2],zmm1[0,2],zmm0[4,6],zmm1[4,6],zmm0[8,10],zmm1[8,10],zmm0[12,14],zmm1[12,14]
+; KNL-NEXT: vshufps {{.*#+}} zmm0 = zmm0[1,3],zmm1[1,3],zmm0[5,7],zmm1[5,7],zmm0[9,11],zmm1[9,11],zmm0[13,15],zmm1[13,15]
+; KNL-NEXT: vpaddd %zmm0, %zmm2, %zmm0
+; KNL-NEXT: # kill: %YMM0<def> %YMM0<kill> %ZMM0<kill>
+; KNL-NEXT: retq
+;
+; SKX-LABEL: hadd_16_3_sv:
+; SKX: # BB#0:
+; SKX-NEXT: vshufps {{.*#+}} zmm2 = zmm0[0,2],zmm1[0,2],zmm0[4,6],zmm1[4,6],zmm0[8,10],zmm1[8,10],zmm0[12,14],zmm1[12,14]
+; SKX-NEXT: vshufps {{.*#+}} zmm0 = zmm0[1,3],zmm1[1,3],zmm0[5,7],zmm1[5,7],zmm0[9,11],zmm1[9,11],zmm0[13,15],zmm1[13,15]
+; SKX-NEXT: vpaddd %zmm0, %zmm2, %zmm0
+; SKX-NEXT: # kill: %YMM0<def> %YMM0<kill> %ZMM0<kill>
+; SKX-NEXT: retq
+ %x226 = shufflevector <16 x i32> %x225, <16 x i32> %x227, <16 x i32> <i32 0, i32 2, i32 16, i32 18
+, i32 4, i32 6, i32 20, i32 22, i32 8, i32 10, i32 24, i32 26, i32 12, i32 14, i32 28, i32 30>
+ %x228 = shufflevector <16 x i32> %x225, <16 x i32> %x227, <16 x i32> <i32 1, i32 3, i32 17, i32 19
+, i32 5 , i32 7, i32 21, i32 23, i32 9, i32 11, i32 25, i32 27, i32 13, i32 15,
+ i32 29, i32 31>
+ %x229 = add <16 x i32> %x226, %x228
+ %x230 = shufflevector <16 x i32> %x229, <16 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4 ,i32 5, i32 6, i32 7>
+ ret <8 x i32> %x230
+}
+
+
+define double @fadd_noundef_eel(<8 x double> %x225, <8 x double> %x227) {
+; KNL-LABEL: fadd_noundef_eel:
+; KNL: # BB#0:
+; KNL-NEXT: vunpcklpd {{.*#+}} zmm2 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6]
+; KNL-NEXT: vunpckhpd {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7]
+; KNL-NEXT: vaddpd %zmm0, %zmm2, %zmm0
+; KNL-NEXT: # kill: %XMM0<def> %XMM0<kill> %ZMM0<kill>
+; KNL-NEXT: retq
+;
+; SKX-LABEL: fadd_noundef_eel:
+; SKX: # BB#0:
+; SKX-NEXT: vunpcklpd {{.*#+}} zmm2 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6]
+; SKX-NEXT: vunpckhpd {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7]
+; SKX-NEXT: vaddpd %zmm0, %zmm2, %zmm0
+; SKX-NEXT: # kill: %XMM0<def> %XMM0<kill> %ZMM0<kill>
+; SKX-NEXT: vzeroupper
+; SKX-NEXT: retq
+ %x226 = shufflevector <8 x double> %x225, <8 x double> %x227, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+ %x228 = shufflevector <8 x double> %x225, <8 x double> %x227, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5 ,i32 13, i32 7, i32 15>
+ %x229 = fadd <8 x double> %x226, %x228
+ %x230 = extractelement <8 x double> %x229, i32 0
+ ret double %x230
+}
+
+
+
+define double @fsub_noundef_ee (<8 x double> %x225, <8 x double> %x227) {
+; KNL-LABEL: fsub_noundef_ee:
+; KNL: # BB#0:
+; KNL-NEXT: vunpcklpd {{.*#+}} zmm2 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6]
+; KNL-NEXT: vunpckhpd {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7]
+; KNL-NEXT: vsubpd %zmm0, %zmm2, %zmm0
+; KNL-NEXT: vextractf32x4 $2, %zmm0, %xmm0
+; KNL-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
+; KNL-NEXT: retq
+;
+; SKX-LABEL: fsub_noundef_ee:
+; SKX: # BB#0:
+; SKX-NEXT: vunpcklpd {{.*#+}} zmm2 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6]
+; SKX-NEXT: vunpckhpd {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7]
+; SKX-NEXT: vsubpd %zmm0, %zmm2, %zmm0
+; SKX-NEXT: vextractf32x4 $2, %zmm0, %xmm0
+; SKX-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
+; SKX-NEXT: vzeroupper
+; SKX-NEXT: retq
+ %x226 = shufflevector <8 x double> %x225, <8 x double> %x227, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
+ %x228 = shufflevector <8 x double> %x225, <8 x double> %x227, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5 ,i32 13, i32 7, i32 15>
+ %x229 = fsub <8 x double> %x226, %x228
+ %x230 = extractelement <8 x double> %x229, i32 5
+ ret double %x230
+}
+
More information about the llvm-commits
mailing list