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
105 lines
3.5 KiB
LLVM
105 lines
3.5 KiB
LLVM
; RUN: llc -mtriple=amdgcn--amdhsa -mattr=+dx10-clamp-and-ieee-mode < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; GCN-LABEL: {{^}}test_default_ci:
|
|
; GCN: .amdhsa_dx10_clamp 1
|
|
; GCN: .amdhsa_ieee_mode 1
|
|
; GCN: FloatMode: 240
|
|
define amdgpu_kernel void @test_default_ci(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #0 {
|
|
store float 0.0, ptr addrspace(1) %out0
|
|
store double 0.0, ptr addrspace(1) %out1
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}test_default_vi:
|
|
; GCN: .amdhsa_dx10_clamp 1
|
|
; GCN: .amdhsa_ieee_mode 1
|
|
; GCN: FloatMode: 240
|
|
define amdgpu_kernel void @test_default_vi(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #1 {
|
|
store float 0.0, ptr addrspace(1) %out0
|
|
store double 0.0, ptr addrspace(1) %out1
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}test_f64_denormals:
|
|
; GCN: .amdhsa_dx10_clamp 1
|
|
; GCN: .amdhsa_ieee_mode 1
|
|
; GCN: FloatMode: 192
|
|
define amdgpu_kernel void @test_f64_denormals(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #2 {
|
|
store float 0.0, ptr addrspace(1) %out0
|
|
store double 0.0, ptr addrspace(1) %out1
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}test_f32_denormals:
|
|
; GCN: .amdhsa_dx10_clamp 1
|
|
; GCN: .amdhsa_ieee_mode 1
|
|
; GCN: FloatMode: 48
|
|
define amdgpu_kernel void @test_f32_denormals(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #3 {
|
|
store float 0.0, ptr addrspace(1) %out0
|
|
store double 0.0, ptr addrspace(1) %out1
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}test_f32_f64_denormals:
|
|
; GCN: .amdhsa_dx10_clamp 1
|
|
; GCN: .amdhsa_ieee_mode 1
|
|
; GCN: FloatMode: 240
|
|
define amdgpu_kernel void @test_f32_f64_denormals(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #4 {
|
|
store float 0.0, ptr addrspace(1) %out0
|
|
store double 0.0, ptr addrspace(1) %out1
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}test_no_denormals:
|
|
; GCN: .amdhsa_dx10_clamp 1
|
|
; GCN: .amdhsa_ieee_mode 1
|
|
; GCN: FloatMode: 0
|
|
define amdgpu_kernel void @test_no_denormals(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #5 {
|
|
store float 0.0, ptr addrspace(1) %out0
|
|
store double 0.0, ptr addrspace(1) %out1
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}test_no_dx10_clamp_vi:
|
|
; GCN: .amdhsa_dx10_clamp 0
|
|
; GCN: .amdhsa_ieee_mode 1
|
|
; GCN: FloatMode: 240
|
|
define amdgpu_kernel void @test_no_dx10_clamp_vi(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #6 {
|
|
store float 0.0, ptr addrspace(1) %out0
|
|
store double 0.0, ptr addrspace(1) %out1
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}test_no_ieee_mode_vi:
|
|
; GCN: .amdhsa_dx10_clamp 1
|
|
; GCN: .amdhsa_ieee_mode 0
|
|
; GCN: FloatMode: 240
|
|
define amdgpu_kernel void @test_no_ieee_mode_vi(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #7 {
|
|
store float 0.0, ptr addrspace(1) %out0
|
|
store double 0.0, ptr addrspace(1) %out1
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}test_no_ieee_mode_no_dx10_clamp_vi:
|
|
; GCN: .amdhsa_dx10_clamp 0
|
|
; GCN: .amdhsa_ieee_mode 0
|
|
; GCN: FloatMode: 240
|
|
define amdgpu_kernel void @test_no_ieee_mode_no_dx10_clamp_vi(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #8 {
|
|
store float 0.0, ptr addrspace(1) %out0
|
|
store double 0.0, ptr addrspace(1) %out1
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind "target-cpu"="kaveri" }
|
|
attributes #1 = { nounwind "target-cpu"="fiji" }
|
|
attributes #2 = { nounwind denormal_fpenv(float: preservesign) }
|
|
attributes #3 = { nounwind denormal_fpenv(preservesign, float: ieee) }
|
|
attributes #4 = { nounwind denormal_fpenv(ieee) }
|
|
attributes #5 = { nounwind denormal_fpenv(preservesign) }
|
|
attributes #6 = { nounwind "amdgpu-dx10-clamp"="false" "target-cpu"="fiji" }
|
|
attributes #7 = { nounwind "amdgpu-ieee"="false" "target-cpu"="fiji" }
|
|
attributes #8 = { nounwind "amdgpu-dx10-clamp"="false" "amdgpu-ieee"="false" "target-cpu"="fiji" }
|
|
|
|
!llvm.module.flags = !{!0}
|
|
!0 = !{i32 1, !"amdhsa_code_object_version", i32 400}
|