| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py |
| ; RUN: llc < %s -fast-isel -mtriple=x86_64-unknown-unknown -mattr=+sse | FileCheck %s --check-prefixes=CHECK,SSE |
| ; RUN: llc < %s -fast-isel -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1 |
| ; RUN: llc < %s -fast-isel -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw,+avx512dq,+avx512vl | FileCheck %s --check-prefixes=CHECK,AVX,AVX512 |
| |
| ; NOTE: This should use IR equivalent to what is generated by clang/test/CodeGen/sse-builtins.c |
| |
| define <4 x float> @test_mm_cvtsi64_ss(<4 x float> %a0, i64 %a1) nounwind { |
| ; SSE-LABEL: test_mm_cvtsi64_ss: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: cvtsi2ssq %rdi, %xmm0 |
| ; SSE-NEXT: retq |
| ; |
| ; AVX-LABEL: test_mm_cvtsi64_ss: |
| ; AVX: # %bb.0: |
| ; AVX-NEXT: vcvtsi2ssq %rdi, %xmm0, %xmm0 |
| ; AVX-NEXT: retq |
| %res = call <4 x float> @llvm.x86.sse.cvtsi642ss(<4 x float> %a0, i64 %a1) |
| ret <4 x float> %res |
| } |
| declare <4 x float> @llvm.x86.sse.cvtsi642ss(<4 x float>, i64) nounwind readnone |
| |
| define i64 @test_mm_cvtss_si64(<4 x float> %a0) nounwind { |
| ; SSE-LABEL: test_mm_cvtss_si64: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: cvtss2si %xmm0, %rax |
| ; SSE-NEXT: retq |
| ; |
| ; AVX-LABEL: test_mm_cvtss_si64: |
| ; AVX: # %bb.0: |
| ; AVX-NEXT: vcvtss2si %xmm0, %rax |
| ; AVX-NEXT: retq |
| %res = call i64 @llvm.x86.sse.cvtss2si64(<4 x float> %a0) |
| ret i64 %res |
| } |
| declare i64 @llvm.x86.sse.cvtss2si64(<4 x float>) nounwind readnone |
| |
| define i64 @test_mm_cvttss_si64(<4 x float> %a0) nounwind { |
| ; SSE-LABEL: test_mm_cvttss_si64: |
| ; SSE: # %bb.0: |
| ; SSE-NEXT: cvttss2si %xmm0, %rax |
| ; SSE-NEXT: retq |
| ; |
| ; AVX-LABEL: test_mm_cvttss_si64: |
| ; AVX: # %bb.0: |
| ; AVX-NEXT: vcvttss2si %xmm0, %rax |
| ; AVX-NEXT: retq |
| %res = call i64 @llvm.x86.sse.cvttss2si64(<4 x float> %a0) |
| ret i64 %res |
| } |
| declare i64 @llvm.x86.sse.cvttss2si64(<4 x float>) nounwind readnone |