[X86][AVX] Add PR45808 test case for badly promoted comparison mask arithmetic

diff --git a/llvm/test/CodeGen/X86/promote-cmp.ll b/llvm/test/CodeGen/X86/promote-cmp.ll
new file mode 100644 (file)
index 0000000..c2d0c91
--- /dev/null
+++ b/llvm/test/CodeGen/X86/promote-cmp.ll
@@ -0,0 +1,99 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-- -mattr=+sse2   | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
+; RUN: llc < %s -mtriple=x86_64-- -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE4
+; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx    | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
+; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx2   | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
+
+define <4 x i64> @PR45808(<4 x i64> %0, <4 x i64> %1) {
+; SSE2-LABEL: PR45808:
+; SSE2:       # %bb.0:
+; SSE2-NEXT:    movdqa {{.*#+}} xmm4 = [2147483648,2147483648]
+; SSE2-NEXT:    movdqa %xmm3, %xmm5
+; SSE2-NEXT:    pxor %xmm4, %xmm5
+; SSE2-NEXT:    movdqa %xmm1, %xmm6
+; SSE2-NEXT:    pxor %xmm4, %xmm6
+; SSE2-NEXT:    movdqa %xmm6, %xmm7
+; SSE2-NEXT:    pcmpgtd %xmm5, %xmm7
+; SSE2-NEXT:    pcmpeqd %xmm5, %xmm6
+; SSE2-NEXT:    pshufd {{.*#+}} xmm5 = xmm6[1,1,3,3]
+; SSE2-NEXT:    pand %xmm7, %xmm5
+; SSE2-NEXT:    pshufd {{.*#+}} xmm6 = xmm7[1,1,3,3]
+; SSE2-NEXT:    por %xmm5, %xmm6
+; SSE2-NEXT:    movdqa %xmm2, %xmm5
+; SSE2-NEXT:    pxor %xmm4, %xmm5
+; SSE2-NEXT:    pxor %xmm0, %xmm4
+; SSE2-NEXT:    movdqa %xmm4, %xmm7
+; SSE2-NEXT:    pcmpgtd %xmm5, %xmm7
+; SSE2-NEXT:    pcmpeqd %xmm5, %xmm4
+; SSE2-NEXT:    pshufd {{.*#+}} xmm4 = xmm4[1,1,3,3]
+; SSE2-NEXT:    pand %xmm7, %xmm4
+; SSE2-NEXT:    pshufd {{.*#+}} xmm5 = xmm7[1,1,3,3]
+; SSE2-NEXT:    por %xmm4, %xmm5
+; SSE2-NEXT:    shufps {{.*#+}} xmm5 = xmm5[0,2],xmm6[0,2]
+; SSE2-NEXT:    movaps {{.*#+}} xmm4 = <1,1,u,u>
+; SSE2-NEXT:    xorps %xmm5, %xmm4
+; SSE2-NEXT:    shufps {{.*#+}} xmm5 = xmm5[2,1,3,3]
+; SSE2-NEXT:    psllq $63, %xmm5
+; SSE2-NEXT:    psrad $31, %xmm5
+; SSE2-NEXT:    pshufd {{.*#+}} xmm5 = xmm5[1,1,3,3]
+; SSE2-NEXT:    pand %xmm5, %xmm1
+; SSE2-NEXT:    pandn %xmm3, %xmm5
+; SSE2-NEXT:    por %xmm5, %xmm1
+; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm4[0,1,1,3]
+; SSE2-NEXT:    psllq $63, %xmm3
+; SSE2-NEXT:    psrad $31, %xmm3
+; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[1,1,3,3]
+; SSE2-NEXT:    pand %xmm3, %xmm0
+; SSE2-NEXT:    pandn %xmm2, %xmm3
+; SSE2-NEXT:    por %xmm3, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSE4-LABEL: PR45808:
+; SSE4:       # %bb.0:
+; SSE4-NEXT:    movdqa %xmm0, %xmm4
+; SSE4-NEXT:    movdqa %xmm1, %xmm0
+; SSE4-NEXT:    pcmpgtq %xmm3, %xmm0
+; SSE4-NEXT:    movdqa %xmm4, %xmm5
+; SSE4-NEXT:    pcmpgtq %xmm2, %xmm5
+; SSE4-NEXT:    pshufd {{.*#+}} xmm5 = xmm5[0,2,2,3]
+; SSE4-NEXT:    pxor {{.*}}(%rip), %xmm5
+; SSE4-NEXT:    psllq $63, %xmm0
+; SSE4-NEXT:    blendvpd %xmm0, %xmm1, %xmm3
+; SSE4-NEXT:    pmovzxdq {{.*#+}} xmm0 = xmm5[0],zero,xmm5[1],zero
+; SSE4-NEXT:    psllq $63, %xmm0
+; SSE4-NEXT:    blendvpd %xmm0, %xmm4, %xmm2
+; SSE4-NEXT:    movapd %xmm2, %xmm0
+; SSE4-NEXT:    movapd %xmm3, %xmm1
+; SSE4-NEXT:    retq
+;
+; AVX1-LABEL: PR45808:
+; AVX1:       # %bb.0:
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
+; AVX1-NEXT:    vpcmpgtq %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpcmpgtq %xmm1, %xmm0, %xmm3
+; AVX1-NEXT:    vpackssdw %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vpxor {{.*}}(%rip), %xmm2, %xmm2
+; AVX1-NEXT:    vpslld $31, %xmm2, %xmm2
+; AVX1-NEXT:    vpmovsxdq %xmm2, %xmm3
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm2[2,3,0,1]
+; AVX1-NEXT:    vpmovsxdq %xmm2, %xmm2
+; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm3, %ymm2
+; AVX1-NEXT:    vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: PR45808:
+; AVX2:       # %bb.0:
+; AVX2-NEXT:    vpcmpgtq %ymm1, %ymm0, %ymm2
+; AVX2-NEXT:    vextracti128 $1, %ymm2, %xmm3
+; AVX2-NEXT:    vpackssdw %xmm3, %xmm2, %xmm2
+; AVX2-NEXT:    vpxor {{.*}}(%rip), %xmm2, %xmm2
+; AVX2-NEXT:    vpslld $31, %xmm2, %xmm2
+; AVX2-NEXT:    vpmovsxdq %xmm2, %ymm2
+; AVX2-NEXT:    vblendvpd %ymm2, %ymm0, %ymm1, %ymm0
+; AVX2-NEXT:    retq
+  %3 = icmp sgt <4 x i64> %0, %1
+  %4 = xor <4 x i1> %3, <i1 true, i1 true, i1 false, i1 false>
+  %5 = select <4 x i1> %4, <4 x i64> %0, <4 x i64> %1
+  ret <4 x i64> %5
+}