[X86] Add tests for replacing `{v}unpck{l|h}pd` -> `{v}shufps`; NFC

llvm/test/CodeGen/X86/unpckpd-to-faster-alternative.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=skylake-avx512  | FileCheck %s --check-prefixes=CHECK,CHECK-512,CHECK-SKX
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=skylake  | FileCheck %s --check-prefixes=CHECK,CHECK-SKL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=icelake-server  | FileCheck %s --check-prefixes=CHECK,CHECK-512,CHECK-ICX
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64-v4  | FileCheck %s --check-prefixes=CHECK,CHECK-512,CHECK-V4
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=znver4  | FileCheck %s --check-prefixes=CHECK,CHECK-512,CHECK-ZNVER4
+
+define <16 x float> @transform_VUNPCKLPDZrr(<16 x float> %a, <16 x float> %b) nounwind {
+; CHECK-512-LABEL: transform_VUNPCKLPDZrr:
+; CHECK-512:       # %bb.0:
+; CHECK-512-NEXT:    vunpcklpd {{.*#+}} zmm0 = zmm0[0],zmm1[0],zmm0[2],zmm1[2],zmm0[4],zmm1[4],zmm0[6],zmm1[6]
+; CHECK-512-NEXT:    retq
+;
+; CHECK-SKL-LABEL: transform_VUNPCKLPDZrr:
+; CHECK-SKL:       # %bb.0:
+; CHECK-SKL-NEXT:    vunpcklpd {{.*#+}} ymm0 = ymm0[0],ymm2[0],ymm0[2],ymm2[2]
+; CHECK-SKL-NEXT:    vunpcklpd {{.*#+}} ymm1 = ymm1[0],ymm3[0],ymm1[2],ymm3[2]
+; CHECK-SKL-NEXT:    retq
+  %shufp = shufflevector <16 x float> %a, <16 x float> %b, <16 x i32> <i32 0, i32 1, i32 16, i32 17, i32 4, i32 5, i32 20, i32 21, i32 8, i32 9, i32 24, i32 25, i32 12, i32 13, i32 28, i32 29>
+  ret <16 x float> %shufp
+}
+
+define <16 x float> @transform_VUNPCKHPDZrr(<16 x float> %a, <16 x float> %b) nounwind {
+; CHECK-512-LABEL: transform_VUNPCKHPDZrr:
+; CHECK-512:       # %bb.0:
+; CHECK-512-NEXT:    vunpckhpd {{.*#+}} zmm0 = zmm0[1],zmm1[1],zmm0[3],zmm1[3],zmm0[5],zmm1[5],zmm0[7],zmm1[7]
+; CHECK-512-NEXT:    retq
+;
+; CHECK-SKL-LABEL: transform_VUNPCKHPDZrr:
+; CHECK-SKL:       # %bb.0:
+; CHECK-SKL-NEXT:    vunpckhpd {{.*#+}} ymm0 = ymm0[1],ymm2[1],ymm0[3],ymm2[3]
+; CHECK-SKL-NEXT:    vunpckhpd {{.*#+}} ymm1 = ymm1[1],ymm3[1],ymm1[3],ymm3[3]
+; CHECK-SKL-NEXT:    retq
+  %shufp = shufflevector <16 x float> %a, <16 x float> %b, <16 x i32> <i32 2, i32 3, i32 18, i32 19, i32 6, i32 7, i32 22, i32 23, i32 10, i32 11, i32 26, i32 27, i32 14, i32 15, i32 30, i32 31>
+  ret <16 x float> %shufp
+}
+
+define <8 x float> @transform_VUNPCKLPDYrr(<8 x float> %a, <8 x float> %b) nounwind {
+; CHECK-LABEL: transform_VUNPCKLPDYrr:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vunpcklpd {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
+; CHECK-NEXT:    retq
+; -LABEL: transform_VUNPCKLPDYrr:
+; :       # %bb.0:
+; -NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,1],ymm1[0,1],ymm0[4,5],ymm1[4,5]
+; -NEXT:    retq
+  %shufp = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 1, i32 8, i32 9, i32 4, i32 5, i32 12, i32 13>
+  ret <8 x float> %shufp
+}
+
+define <8 x float> @transform_VUNPCKHPDYrr(<8 x float> %a, <8 x float> %b) nounwind {
+; CHECK-LABEL: transform_VUNPCKHPDYrr:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vunpckhpd {{.*#+}} ymm0 = ymm0[1],ymm1[1],ymm0[3],ymm1[3]
+; CHECK-NEXT:    retq
+; -LABEL: transform_VUNPCKHPDYrr:
+; :       # %bb.0:
+; -NEXT:    vshufps {{.*#+}} ymm0 = ymm0[2,3],ymm1[2,3],ymm0[6,7],ymm1[6,7]
+; -NEXT:    retq
+  %shufp = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 2, i32 3, i32 10, i32 11, i32 6, i32 7, i32 14, i32 15>
+  ret <8 x float> %shufp
+}
+
+define <4 x float> @transform_VUNPCKLPDrr(<4 x float> %a, <4 x float> %b) nounwind {
+; CHECK-LABEL: transform_VUNPCKLPDrr:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vmovlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; CHECK-NEXT:    retq
+; -LABEL: transform_VUNPCKLPDrr:
+; :       # %bb.0:
+; -NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,1]
+; -NEXT:    retq
+  %shufp = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
+  ret <4 x float> %shufp
+}
+
+define <4 x float> @transform_VUNPCKHPDrr(<4 x float> %a, <4 x float> %b) nounwind {
+; CHECK-LABEL: transform_VUNPCKHPDrr:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vunpckhpd {{.*#+}} xmm0 = xmm0[1],xmm1[1]
+; CHECK-NEXT:    retq
+; -LABEL: transform_VUNPCKHPDrr:
+; :       # %bb.0:
+; -NEXT:    vshufps {{.*#+}} xmm0 = xmm0[2,3],xmm1[2,3]
+; -NEXT:    retq
+  %shufp = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 2, i32 3, i32 6, i32 7>
+  ret <4 x float> %shufp
+}
+;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
+; CHECK-ICX: {{.*}}
+; CHECK-SKX: {{.*}}
+; CHECK-V4: {{.*}}
+; CHECK-ZNVER4: {{.*}}