From 9e71ceeaf94da094506ad3c9bdd5aae4f0a68359 Mon Sep 17 00:00:00 2001 From: Simon Pilgrim Date: Thu, 2 Feb 2017 17:23:57 +0000 Subject: [PATCH] [X86][SSE] Add test case for PR18344 llvm-svn: 293907 --- llvm/test/CodeGen/X86/pr18344.ll | 89 ++++++++++++++++++++++++++++++++ 1 file changed, 89 insertions(+) create mode 100644 llvm/test/CodeGen/X86/pr18344.ll diff --git a/llvm/test/CodeGen/X86/pr18344.ll b/llvm/test/CodeGen/X86/pr18344.ll new file mode 100644 index 000000000000..15bf91031ee8 --- /dev/null +++ b/llvm/test/CodeGen/X86/pr18344.ll @@ -0,0 +1,89 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=X86 +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=X64 + +%v4_varying_complex = type { <4 x float>, <4 x float> } + +define void @FFT(%v4_varying_complex* noalias nocapture %destination, float* noalias %re, <4 x i32>* noalias nocapture %ptr_cast_for_load) nounwind { +; X86-LABEL: FFT: +; X86: # BB#0: # %begin +; X86-NEXT: pushl %ebx +; X86-NEXT: pushl %edi +; X86-NEXT: pushl %esi +; X86-NEXT: movl {{[0-9]+}}(%esp), %eax +; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx +; X86-NEXT: movl {{[0-9]+}}(%esp), %edx +; X86-NEXT: movdqu (%edx), %xmm0 +; X86-NEXT: pslld $4, %xmm0 +; X86-NEXT: movd %xmm0, %edx +; X86-NEXT: pextrd $1, %xmm0, %esi +; X86-NEXT: pextrd $2, %xmm0, %edi +; X86-NEXT: pextrd $3, %xmm0, %ebx +; X86-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero +; X86-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero +; X86-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero +; X86-NEXT: movss {{.*#+}} xmm3 = mem[0],zero,zero,zero +; X86-NEXT: movss %xmm0, 128(%eax) +; X86-NEXT: movss %xmm1, 164(%eax) +; X86-NEXT: movss %xmm2, 200(%eax) +; X86-NEXT: movss %xmm3, 236(%eax) +; X86-NEXT: popl %esi +; X86-NEXT: popl %edi +; X86-NEXT: popl %ebx +; X86-NEXT: retl +; +; X64-LABEL: FFT: +; X64: # BB#0: # %begin +; X64-NEXT: movdqu (%rdx), %xmm0 +; X64-NEXT: pslld $4, %xmm0 +; X64-NEXT: movd %xmm0, %rax +; X64-NEXT: movslq %eax, %r8 +; X64-NEXT: sarq $32, %rax +; X64-NEXT: pextrq $1, %xmm0, %rdx +; X64-NEXT: movslq %edx, %rcx +; X64-NEXT: sarq $32, %rdx +; X64-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero +; X64-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero +; X64-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero +; X64-NEXT: movss {{.*#+}} xmm3 = mem[0],zero,zero,zero +; X64-NEXT: movss %xmm0, 128(%rdi) +; X64-NEXT: movss %xmm1, 164(%rdi) +; X64-NEXT: movss %xmm2, 200(%rdi) +; X64-NEXT: movss %xmm3, 236(%rdi) +; X64-NEXT: retq +begin: + %ptr_masked_load79 = load <4 x i32>, <4 x i32>* %ptr_cast_for_load, align 4 + %mul__bitReversedProgramIndex_load = shl <4 x i32> %ptr_masked_load79, + + %offset32_1 = extractelement <4 x i32> %mul__bitReversedProgramIndex_load, i32 0 + %ptroffset_1 = sext i32 %offset32_1 to i64 + %offset32_2 = extractelement <4 x i32> %mul__bitReversedProgramIndex_load, i32 1 + %ptroffset_2 = sext i32 %offset32_2 to i64 + %offset32_3 = extractelement <4 x i32> %mul__bitReversedProgramIndex_load, i32 2 + %ptroffset_3 = sext i32 %offset32_3 to i64 + %offset32_4 = extractelement <4 x i32> %mul__bitReversedProgramIndex_load, i32 3 + %ptroffset_4 = sext i32 %offset32_4 to i64 + + %ptrcast_1 = getelementptr float, float* %re, i64 %ptroffset_1 + %val_1 = load float, float* %ptrcast_1, align 4 + %ptrcast_2 = getelementptr float, float* %re, i64 %ptroffset_2 + %val_2 = load float, float* %ptrcast_2, align 4 + %ptrcast_3 = getelementptr float, float* %re, i64 %ptroffset_3 + %val_3 = load float, float* %ptrcast_3, align 4 + %ptrcast_4 = getelementptr float, float* %re, i64 %ptroffset_4 + %val_4 = load float, float* %ptrcast_4, align 4 + + %destination_load_ptr2int_2void = bitcast %v4_varying_complex* %destination to i8* + %ptrcast1_1 = getelementptr inbounds %v4_varying_complex, %v4_varying_complex* %destination, i64 4, i32 0, i64 0 + store float %val_1, float* %ptrcast1_1, align 4 + %finalptr_2 = getelementptr i8, i8* %destination_load_ptr2int_2void, i64 164 + %ptrcast1_2 = bitcast i8* %finalptr_2 to float* + store float %val_2, float* %ptrcast1_2, align 4 + %finalptr_3 = getelementptr i8, i8* %destination_load_ptr2int_2void, i64 200 + %ptrcast1_3 = bitcast i8* %finalptr_3 to float* + store float %val_3, float* %ptrcast1_3, align 4 + %finalptr_4 = getelementptr i8, i8* %destination_load_ptr2int_2void, i64 236 + %ptrcast1_4 = bitcast i8* %finalptr_4 to float* + store float %val_4, float* %ptrcast1_4, align 4 + ret void +}