[X86] Add test case for v8i64->v8i8 truncate with avx512 and prefer-vector-width...

With vpmovqb, we should be able to do better here until we get
AVX512VBMI on Cannonlake/Icelake.

llvm-svn: 373569

diff --git a/llvm/test/CodeGen/X86/min-legal-vector-width.ll b/llvm/test/CodeGen/X86/min-legal-vector-width.ll
index deb2611..d0bc67a 100644 (file)
--- a/llvm/test/CodeGen/X86/min-legal-vector-width.ll
+++ b/llvm/test/CodeGen/X86/min-legal-vector-width.ll
@@ -828,6 +828,37 @@ define <16 x i8> @trunc_v16i32_v16i8(<16 x i32>* %x) nounwind "min-legal-vector-
   ret <16 x i8> %b
 }
 
+define <8 x i8> @trunc_v8i64_v8i8(<8 x i64>* %x) nounwind "min-legal-vector-width"="256" {
+; CHECK-AVX512-LABEL: trunc_v8i64_v8i8:
+; CHECK-AVX512:       # %bb.0:
+; CHECK-AVX512-NEXT:    vmovdqa (%rdi), %xmm0
+; CHECK-AVX512-NEXT:    vmovdqa 16(%rdi), %xmm1
+; CHECK-AVX512-NEXT:    vmovdqa 32(%rdi), %xmm2
+; CHECK-AVX512-NEXT:    vmovdqa 48(%rdi), %xmm3
+; CHECK-AVX512-NEXT:    vmovdqa {{.*#+}} xmm4 = <u,u,0,8,u,u,u,u,u,u,u,u,u,u,u,u>
+; CHECK-AVX512-NEXT:    vpshufb %xmm4, %xmm3, %xmm3
+; CHECK-AVX512-NEXT:    vpshufb %xmm4, %xmm2, %xmm2
+; CHECK-AVX512-NEXT:    vpunpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
+; CHECK-AVX512-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,8,u,u,u,u,u,u,u,u,u,u,u,u,u,u>
+; CHECK-AVX512-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
+; CHECK-AVX512-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
+; CHECK-AVX512-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; CHECK-AVX512-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2,3]
+; CHECK-AVX512-NEXT:    retq
+;
+; CHECK-VBMI-LABEL: trunc_v8i64_v8i8:
+; CHECK-VBMI:       # %bb.0:
+; CHECK-VBMI-NEXT:    vmovdqa (%rdi), %ymm1
+; CHECK-VBMI-NEXT:    vpbroadcastq {{.*#+}} ymm0 = [4048780183313844224,4048780183313844224,4048780183313844224,4048780183313844224]
+; CHECK-VBMI-NEXT:    vpermi2b 32(%rdi), %ymm1, %ymm0
+; CHECK-VBMI-NEXT:    # kill: def $xmm0 killed $xmm0 killed $ymm0
+; CHECK-VBMI-NEXT:    vzeroupper
+; CHECK-VBMI-NEXT:    retq
+  %a = load <8 x i64>, <8 x i64>* %x
+  %b = trunc <8 x i64> %a to <8 x i8>
+  ret <8 x i8> %b
+}
+
 define <8 x i16> @trunc_v8i64_v8i16(<8 x i64>* %x) nounwind "min-legal-vector-width"="256" {
 ; CHECK-LABEL: trunc_v8i64_v8i16:
 ; CHECK:       # %bb.0: