[X86] Adding a test for vector shuffle extractions.

When both the vector inputs of the shuffle vector is comprising of same vector or shuffle mask is accessing elements from only one operand vector (like in PR33758 test already present).

Committed on behalf of @jbhateja (Jatin Bhateja)

Differential Revision: https://reviews.llvm.org/D36271

llvm-svn: 309963

diff --git a/llvm/test/CodeGen/X86/shuffle-vs-trunc-512.ll b/llvm/test/CodeGen/X86/shuffle-vs-trunc-512.ll
index d1609f2..86e3fc1 100644 (file)
--- a/llvm/test/CodeGen/X86/shuffle-vs-trunc-512.ll
+++ b/llvm/test/CodeGen/X86/shuffle-vs-trunc-512.ll
@@ -227,3 +227,117 @@ define void @trunc_v8i64_to_v8i8(<64 x i8>* %L, <8 x i8>* %S) nounwind {
   store <8 x i8> %strided.vec, <8 x i8>* %S
   ret void
 }
+
+define <16 x i8> @trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62(<64 x i8> %x) {
+; AVX512F-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
+; AVX512F:       # BB#0:
+; AVX512F-NEXT:    vextracti128 $1, %ymm0, %xmm2
+; AVX512F-NEXT:    vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX512F-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
+; AVX512F-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
+; AVX512F-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; AVX512F-NEXT:    vextracti128 $1, %ymm1, %xmm2
+; AVX512F-NEXT:    vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
+; AVX512F-NEXT:    vpshufb {{.*#+}} xmm1 = xmm1[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
+; AVX512F-NEXT:    vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
+; AVX512F-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
+; AVX512F-NEXT:    vzeroupper
+; AVX512F-NEXT:    retq
+;
+; AVX512VL-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
+; AVX512VL:       # BB#0:
+; AVX512VL-NEXT:    vextracti128 $1, %ymm0, %xmm2
+; AVX512VL-NEXT:    vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX512VL-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
+; AVX512VL-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
+; AVX512VL-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; AVX512VL-NEXT:    vextracti128 $1, %ymm1, %xmm2
+; AVX512VL-NEXT:    vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
+; AVX512VL-NEXT:    vpshufb {{.*#+}} xmm1 = xmm1[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
+; AVX512VL-NEXT:    vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
+; AVX512VL-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
+; AVX512VL-NEXT:    vzeroupper
+; AVX512VL-NEXT:    retq
+;
+; AVX512BW-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
+; AVX512BW:       # BB#0:
+; AVX512BW-NEXT:    vpextrb $5, %xmm0, %eax
+; AVX512BW-NEXT:    vpextrb $1, %xmm0, %ecx
+; AVX512BW-NEXT:    vmovd %ecx, %xmm1
+; AVX512BW-NEXT:    vpinsrb $1, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $9, %xmm0, %eax
+; AVX512BW-NEXT:    vpinsrb $2, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $13, %xmm0, %eax
+; AVX512BW-NEXT:    vpinsrb $3, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vextracti32x4 $1, %zmm0, %xmm2
+; AVX512BW-NEXT:    vpextrb $1, %xmm2, %eax
+; AVX512BW-NEXT:    vpinsrb $4, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $5, %xmm2, %eax
+; AVX512BW-NEXT:    vpinsrb $5, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $9, %xmm2, %eax
+; AVX512BW-NEXT:    vpinsrb $6, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $13, %xmm2, %eax
+; AVX512BW-NEXT:    vpinsrb $7, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vextracti32x4 $2, %zmm0, %xmm2
+; AVX512BW-NEXT:    vpextrb $1, %xmm2, %eax
+; AVX512BW-NEXT:    vpinsrb $8, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $5, %xmm2, %eax
+; AVX512BW-NEXT:    vpinsrb $9, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $9, %xmm2, %eax
+; AVX512BW-NEXT:    vpinsrb $10, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $13, %xmm2, %eax
+; AVX512BW-NEXT:    vpinsrb $11, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vextracti32x4 $3, %zmm0, %xmm0
+; AVX512BW-NEXT:    vpextrb $1, %xmm0, %eax
+; AVX512BW-NEXT:    vpinsrb $12, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $5, %xmm0, %eax
+; AVX512BW-NEXT:    vpinsrb $13, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $9, %xmm0, %eax
+; AVX512BW-NEXT:    vpinsrb $14, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $14, %xmm0, %eax
+; AVX512BW-NEXT:    vpinsrb $15, %eax, %xmm1, %xmm0
+; AVX512BW-NEXT:    vzeroupper
+; AVX512BW-NEXT:    retq
+;
+; AVX512BWVL-LABEL: trunc_shuffle_v64i8_01_05_09_13_17_21_25_29_33_37_41_45_49_53_57_62:
+; AVX512BWVL:       # BB#0:
+; AVX512BWVL-NEXT:    vpextrb $5, %xmm0, %eax
+; AVX512BWVL-NEXT:    vpextrb $1, %xmm0, %ecx
+; AVX512BWVL-NEXT:    vmovd %ecx, %xmm1
+; AVX512BWVL-NEXT:    vpinsrb $1, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $9, %xmm0, %eax
+; AVX512BWVL-NEXT:    vpinsrb $2, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $13, %xmm0, %eax
+; AVX512BWVL-NEXT:    vpinsrb $3, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vextracti32x4 $1, %zmm0, %xmm2
+; AVX512BWVL-NEXT:    vpextrb $1, %xmm2, %eax
+; AVX512BWVL-NEXT:    vpinsrb $4, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $5, %xmm2, %eax
+; AVX512BWVL-NEXT:    vpinsrb $5, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $9, %xmm2, %eax
+; AVX512BWVL-NEXT:    vpinsrb $6, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $13, %xmm2, %eax
+; AVX512BWVL-NEXT:    vpinsrb $7, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vextracti32x4 $2, %zmm0, %xmm2
+; AVX512BWVL-NEXT:    vpextrb $1, %xmm2, %eax
+; AVX512BWVL-NEXT:    vpinsrb $8, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $5, %xmm2, %eax
+; AVX512BWVL-NEXT:    vpinsrb $9, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $9, %xmm2, %eax
+; AVX512BWVL-NEXT:    vpinsrb $10, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $13, %xmm2, %eax
+; AVX512BWVL-NEXT:    vpinsrb $11, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vextracti32x4 $3, %zmm0, %xmm0
+; AVX512BWVL-NEXT:    vpextrb $1, %xmm0, %eax
+; AVX512BWVL-NEXT:    vpinsrb $12, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $5, %xmm0, %eax
+; AVX512BWVL-NEXT:    vpinsrb $13, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $9, %xmm0, %eax
+; AVX512BWVL-NEXT:    vpinsrb $14, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $14, %xmm0, %eax
+; AVX512BWVL-NEXT:    vpinsrb $15, %eax, %xmm1, %xmm0
+; AVX512BWVL-NEXT:    vzeroupper
+; AVX512BWVL-NEXT:    retq
+  %res = shufflevector <64 x i8> %x, <64 x i8> %x, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 62>
+  ret <16 x i8> %res
+}