derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
59 lines
2.2 KiB
LLVM
59 lines
2.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-- -mattr=avx | FileCheck %s --check-prefix=AVX
|
|
; RUN: llc < %s -mtriple=x86_64-- -mattr=avx512f,avx512vl | FileCheck %s --check-prefix=AVX
|
|
|
|
; PR37751 - https://bugs.llvm.org/show_bug.cgi?id=37751
|
|
; We can't combine into 'round' instructions because the behavior is different for out-of-range values.
|
|
|
|
declare <8 x i32> @llvm.x86.avx.cvtt.ps2dq.256(<8 x float>)
|
|
declare <4 x i32> @llvm.x86.avx.cvtt.pd2dq.256(<4 x double>)
|
|
|
|
define <8 x float> @float_to_int_to_float_mem_v8f32(ptr %p) #0 {
|
|
; AVX-LABEL: float_to_int_to_float_mem_v8f32:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vcvttps2dq (%rdi), %ymm0
|
|
; AVX-NEXT: vcvtdq2ps %ymm0, %ymm0
|
|
; AVX-NEXT: retq
|
|
%x = load <8 x float>, ptr %p, align 16
|
|
%fptosi = tail call <8 x i32> @llvm.x86.avx.cvtt.ps2dq.256(<8 x float> %x)
|
|
%sitofp = sitofp <8 x i32> %fptosi to <8 x float>
|
|
ret <8 x float> %sitofp
|
|
}
|
|
|
|
define <8 x float> @float_to_int_to_float_reg_v8f32(<8 x float> %x) #0 {
|
|
; AVX-LABEL: float_to_int_to_float_reg_v8f32:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vcvttps2dq %ymm0, %ymm0
|
|
; AVX-NEXT: vcvtdq2ps %ymm0, %ymm0
|
|
; AVX-NEXT: retq
|
|
%fptosi = tail call <8 x i32> @llvm.x86.avx.cvtt.ps2dq.256(<8 x float> %x)
|
|
%sitofp = sitofp <8 x i32> %fptosi to <8 x float>
|
|
ret <8 x float> %sitofp
|
|
}
|
|
|
|
define <4 x double> @float_to_int_to_float_mem_v4f64(ptr %p) #0 {
|
|
; AVX-LABEL: float_to_int_to_float_mem_v4f64:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vcvttpd2dqy (%rdi), %xmm0
|
|
; AVX-NEXT: vcvtdq2pd %xmm0, %ymm0
|
|
; AVX-NEXT: retq
|
|
%x = load <4 x double>, ptr %p, align 16
|
|
%fptosi = tail call <4 x i32> @llvm.x86.avx.cvtt.pd2dq.256(<4 x double> %x)
|
|
%sitofp = sitofp <4 x i32> %fptosi to <4 x double>
|
|
ret <4 x double> %sitofp
|
|
}
|
|
|
|
define <4 x double> @float_to_int_to_float_reg_v4f64(<4 x double> %x) #0 {
|
|
; AVX-LABEL: float_to_int_to_float_reg_v4f64:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vcvttpd2dq %ymm0, %xmm0
|
|
; AVX-NEXT: vcvtdq2pd %xmm0, %ymm0
|
|
; AVX-NEXT: retq
|
|
%fptosi = tail call <4 x i32> @llvm.x86.avx.cvtt.pd2dq.256(<4 x double> %x)
|
|
%sitofp = sitofp <4 x i32> %fptosi to <4 x double>
|
|
ret <4 x double> %sitofp
|
|
}
|
|
|
|
attributes #0 = { "no-signed-zeros-fp-math"="true" }
|
|
|