[PATCH] D37183: [X86] Adding a test for horizontal [f]add/[f]sub for avx512 vector type 16x32.

[Jatin Bhateja via Phabricator via llvm-commits]

jbhateja updated this revision to Diff 112821.
jbhateja added a comment.

[X86] Adding more test points for horizontal add/sub for integers/floating avx512 vector types.


https://reviews.llvm.org/D37183

Files:
  test/CodeGen/X86/avx512-hadd-hsub.ll


Index: test/CodeGen/X86/avx512-hadd-hsub.ll
===================================================================
--- test/CodeGen/X86/avx512-hadd-hsub.ll
+++ test/CodeGen/X86/avx512-hadd-hsub.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-;RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl | FileCheck %s --check-prefix=CHECK --check-prefix=KNL
-;RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=skx | FileCheck %s --check-prefix=CHECK --check-prefix=SKX
+;RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl | FileCheck %s --check-prefix=KNL
+;RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=skx | FileCheck %s --check-prefix=SKX
 
 define i32 @hadd_16(<16 x i32> %x225) {
 ; KNL-LABEL: hadd_16:
@@ -110,3 +110,83 @@
   ret float %x230
 }
 
+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]
+; KNL-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm1[1,3],ymm0[5,7],ymm1[5,7]
+; KNL-NEXT:    vpaddd %zmm0, %zmm2, %zmm0
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: hadd_16_3:
+; SKX:       # BB#0:
+; SKX-NEXT:    vshufps {{.*#+}} ymm2 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; SKX-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm1[1,3],ymm0[5,7],ymm1[5,7]
+; SKX-NEXT:    vpaddd %zmm0, %zmm2, %zmm0
+; 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 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+  %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 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef,
+ i32 undef, i32 undef>
+  %x229 = add <16 x i32> %x226, %x228
+  ret <16 x i32> %x229
+}
+
+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]
+; KNL-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm1[1,3],ymm0[5,7],ymm1[5,7]
+; KNL-NEXT:    vaddps %zmm0, %zmm2, %zmm0
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: fhadd_16_3:
+; SKX:       # BB#0:
+; SKX-NEXT:    vshufps {{.*#+}} ymm2 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; SKX-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm1[1,3],ymm0[5,7],ymm1[5,7]
+; SKX-NEXT:    vaddps %zmm0, %zmm2, %zmm0
+; SKX-NEXT:    retq
+  %x226 = shufflevector <16 x float> %x225, <16 x float> %x227, <16 x i32> <i32 0, i32 2, i32 16, i32 18
+, i32 4, i32 6, i32 20, i32 22, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+  %x228 = shufflevector <16 x float> %x225, <16 x float> %x227, <16 x i32> <i32 1, i32 3, i32 17, i32 19
+, i32 5 , i32 7, i32 21,   i32 23, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
+  %x229 = fadd <16 x float> %x226, %x228
+  ret <16 x float> %x229
+}
+
+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]
+; KNL-NEXT:    vunpckhpd {{.*#+}} ymm0 = ymm0[1],ymm1[1],ymm0[3],ymm1[3]
+; KNL-NEXT:    vaddpd %zmm0, %zmm2, %zmm0
+; KNL-NEXT:    retq
+;
+; SKX-LABEL: fhadd_16_4:
+; SKX:       # BB#0:
+; SKX-NEXT:    vunpcklpd {{.*#+}} ymm2 = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
+; SKX-NEXT:    vunpckhpd {{.*#+}} ymm0 = ymm0[1],ymm1[1],ymm0[3],ymm1[3]
+; SKX-NEXT:    vaddpd %zmm0, %zmm2, %zmm0
+; 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 undef, i32 undef, i32 undef, i32 undef>
+  %x228 = shufflevector <8 x double> %x225, <8 x double> %x227, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 undef ,i32 undef, i32 undef, i32 undef>
+  %x229 = fadd <8 x double> %x226, %x228
+  ret <8 x double> %x229
+}


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D37183.112821.patch
Type: text/x-patch
Size: 4686 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170827/33708039/attachment.bin>