diff options
Diffstat (limited to 'test/CodeGen/X86/merge-consecutive-loads-128.ll')
| -rw-r--r-- | test/CodeGen/X86/merge-consecutive-loads-128.ll | 50 |
1 files changed, 44 insertions, 6 deletions
diff --git a/test/CodeGen/X86/merge-consecutive-loads-128.ll b/test/CodeGen/X86/merge-consecutive-loads-128.ll index 003e2e60521b..71417694b0d4 100644 --- a/test/CodeGen/X86/merge-consecutive-loads-128.ll +++ b/test/CodeGen/X86/merge-consecutive-loads-128.ll @@ -1037,12 +1037,12 @@ define <2 x i64> @merge_2i64_i64_12_volatile(i64* %ptr) nounwind uwtable noinlin define <4 x float> @merge_4f32_f32_2345_volatile(float* %ptr) nounwind uwtable noinline ssp { ; SSE2-LABEL: merge_4f32_f32_2345_volatile: ; SSE2: # BB#0: -; SSE2-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero ; SSE2-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero +; SSE2-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero ; SSE2-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero -; SSE2-NEXT: movss {{.*#+}} xmm3 = mem[0],zero,zero,zero ; SSE2-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1] -; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1] +; SSE2-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero +; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1] ; SSE2-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1] ; SSE2-NEXT: retq ; @@ -1065,12 +1065,12 @@ define <4 x float> @merge_4f32_f32_2345_volatile(float* %ptr) nounwind uwtable n ; X32-SSE1-LABEL: merge_4f32_f32_2345_volatile: ; X32-SSE1: # BB#0: ; X32-SSE1-NEXT: movl {{[0-9]+}}(%esp), %eax -; X32-SSE1-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero ; X32-SSE1-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero +; X32-SSE1-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero ; X32-SSE1-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero -; X32-SSE1-NEXT: movss {{.*#+}} xmm3 = mem[0],zero,zero,zero ; X32-SSE1-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1] -; X32-SSE1-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1] +; X32-SSE1-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero +; X32-SSE1-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1] ; X32-SSE1-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1] ; X32-SSE1-NEXT: retl ; @@ -1132,3 +1132,41 @@ define <4 x float> @merge_4f32_f32_X0YY(float* %ptr0, float* %ptr1) nounwind uwt %res3 = insertelement <4 x float> %res2, float %val1, i32 3 ret <4 x float> %res3 } + +; +; Extension tests. +; + +; PR31309 +define <4 x i32> @load_i32_zext_i128_v4i32(i32* %ptr) { +; SSE-LABEL: load_i32_zext_i128_v4i32: +; SSE: # BB#0: +; SSE-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero +; SSE-NEXT: retq +; +; AVX-LABEL: load_i32_zext_i128_v4i32: +; AVX: # BB#0: +; AVX-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero +; AVX-NEXT: retq +; +; X32-SSE1-LABEL: load_i32_zext_i128_v4i32: +; X32-SSE1: # BB#0: +; X32-SSE1-NEXT: movl {{[0-9]+}}(%esp), %eax +; X32-SSE1-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X32-SSE1-NEXT: movl (%ecx), %ecx +; X32-SSE1-NEXT: movl %ecx, (%eax) +; X32-SSE1-NEXT: movl $0, 12(%eax) +; X32-SSE1-NEXT: movl $0, 8(%eax) +; X32-SSE1-NEXT: movl $0, 4(%eax) +; X32-SSE1-NEXT: retl $4 +; +; X32-SSE41-LABEL: load_i32_zext_i128_v4i32: +; X32-SSE41: # BB#0: +; X32-SSE41-NEXT: movl {{[0-9]+}}(%esp), %eax +; X32-SSE41-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero +; X32-SSE41-NEXT: retl + %1 = load i32, i32* %ptr + %2 = zext i32 %1 to i128 + %3 = bitcast i128 %2 to <4 x i32> + ret <4 x i32> %3 +} |