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
83 lines
3.7 KiB
LLVM
83 lines
3.7 KiB
LLVM
; RUN: mlir-translate -import-llvm -split-input-file %s | FileCheck %s
|
|
|
|
; CHECK-LABEL: @fastmath_inst
|
|
define void @fastmath_inst(float %arg1, float %arg2, i1 %arg3) {
|
|
; CHECK: llvm.fadd %{{.*}}, %{{.*}} {fastmathFlags = #llvm.fastmath<nnan, ninf>} : f32
|
|
%1 = fadd nnan ninf float %arg1, %arg2
|
|
; CHECK: llvm.fsub %{{.*}}, %{{.*}} {fastmathFlags = #llvm.fastmath<nsz>} : f32
|
|
%2 = fsub nsz float %arg1, %arg2
|
|
; CHECK: llvm.fmul %{{.*}}, %{{.*}} {fastmathFlags = #llvm.fastmath<arcp, contract>} : f32
|
|
%3 = fmul arcp contract float %arg1, %arg2
|
|
; CHECK: llvm.fdiv %{{.*}}, %{{.*}} {fastmathFlags = #llvm.fastmath<afn, reassoc>} : f32
|
|
%4 = fdiv afn reassoc float %arg1, %arg2
|
|
; CHECK: llvm.fneg %{{.*}} {fastmathFlags = #llvm.fastmath<fast>} : f32
|
|
%5 = fneg fast float %arg1
|
|
; CHECK: llvm.select %{{.*}}, %{{.*}}, %{{.*}} {fastmathFlags = #llvm.fastmath<contract>} : i1, f32
|
|
%6 = select contract i1 %arg3, float %arg1, float %arg2
|
|
ret void
|
|
}
|
|
|
|
; // -----
|
|
|
|
; CHECK-LABEL: @fastmath_cast
|
|
define void @fastmath_cast(float %arg1) {
|
|
; CHECK: llvm.fpext %{{.*}} fastmath<nnan> : f32 to f64
|
|
%1 = fpext nnan float %arg1 to double
|
|
; CHECK: llvm.fptrunc %{{.*}} fastmath<fast> : f32 to f16
|
|
%2 = fptrunc fast float %arg1 to half
|
|
ret void
|
|
}
|
|
|
|
; // -----
|
|
|
|
; CHECK-LABEL: @fastmath_fcmp
|
|
define void @fastmath_fcmp(float %arg1, float %arg2) {
|
|
; CHECK: llvm.fcmp "oge" %{{.*}}, %{{.*}} {fastmathFlags = #llvm.fastmath<nsz>} : f32
|
|
%1 = fcmp nsz oge float %arg1, %arg2
|
|
ret void
|
|
}
|
|
|
|
; // -----
|
|
|
|
declare float @fn(float)
|
|
|
|
; CHECK-LABEL: @fastmath_call
|
|
define void @fastmath_call(float %arg1) {
|
|
; CHECK: llvm.call @fn(%{{.*}}) {fastmathFlags = #llvm.fastmath<ninf>} : (f32) -> f32
|
|
%1 = call ninf float @fn(float %arg1)
|
|
ret void
|
|
}
|
|
|
|
; // -----
|
|
|
|
declare float @llvm.exp.f32(float)
|
|
declare float @llvm.powi.f32.i32(float, i32)
|
|
declare float @llvm.pow.f32(float, float)
|
|
declare float @llvm.fmuladd.f32(float, float, float)
|
|
declare float @llvm.vector.reduce.fmin.v2f32(<2 x float>)
|
|
declare float @llvm.vector.reduce.fmax.v2f32(<2 x float>)
|
|
declare float @llvm.vector.reduce.fminimum.v2f32(<2 x float>)
|
|
declare float @llvm.vector.reduce.fmaximum.v2f32(<2 x float>)
|
|
|
|
; CHECK-LABEL: @fastmath_intr
|
|
define void @fastmath_intr(float %arg1, i32 %arg2, <2 x float> %arg3) {
|
|
; CHECK: llvm.intr.exp(%{{.*}}) {fastmathFlags = #llvm.fastmath<nnan, ninf>} : (f32) -> f32
|
|
%1 = call nnan ninf float @llvm.exp.f32(float %arg1)
|
|
; CHECK: llvm.intr.powi(%{{.*}}, %{{.*}}) {fastmathFlags = #llvm.fastmath<fast>} : (f32, i32) -> f32
|
|
%2 = call fast float @llvm.powi.f32.i32(float %arg1, i32 %arg2)
|
|
; CHECK: llvm.intr.pow(%{{.*}}, %{{.*}}) {fastmathFlags = #llvm.fastmath<fast>} : (f32, f32) -> f32
|
|
%3 = call fast float @llvm.pow.f32(float %arg1, float %arg1)
|
|
; CHECK: llvm.intr.fmuladd(%{{.*}}, %{{.*}}, %{{.*}}) {fastmathFlags = #llvm.fastmath<fast>} : (f32, f32, f32) -> f32
|
|
%4 = call fast float @llvm.fmuladd.f32(float %arg1, float %arg1, float %arg1)
|
|
; CHECK: %{{.*}} = llvm.intr.vector.reduce.fmin({{.*}}) {fastmathFlags = #llvm.fastmath<nnan>} : (vector<2xf32>) -> f32
|
|
%5 = call nnan float @llvm.vector.reduce.fmin.v2f32(<2 x float> %arg3)
|
|
; CHECK: %{{.*}} = llvm.intr.vector.reduce.fmax({{.*}}) {fastmathFlags = #llvm.fastmath<nnan>} : (vector<2xf32>) -> f32
|
|
%6 = call nnan float @llvm.vector.reduce.fmax.v2f32(<2 x float> %arg3)
|
|
; CHECK: %{{.*}} = llvm.intr.vector.reduce.fminimum({{.*}}) {fastmathFlags = #llvm.fastmath<nnan>} : (vector<2xf32>) -> f32
|
|
%7 = call nnan float @llvm.vector.reduce.fminimum.v2f32(<2 x float> %arg3)
|
|
; CHECK: %{{.*}} = llvm.intr.vector.reduce.fmaximum({{.*}}) {fastmathFlags = #llvm.fastmath<nnan>} : (vector<2xf32>) -> f32
|
|
%8 = call nnan float @llvm.vector.reduce.fmaximum.v2f32(<2 x float> %arg3)
|
|
|
|
ret void
|
|
}
|