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
82 lines
2.2 KiB
LLVM
82 lines
2.2 KiB
LLVM
; RUN: llc -mtriple=amdgcn < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=tonga -mattr=-flat-for-global < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -mtriple=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
|
|
|
|
|
|
; FUNC-LABEL: {{^}}test_a:
|
|
; EG-NOT: CND
|
|
; EG: SET{{[NEQGTL]+}}_DX10
|
|
|
|
define amdgpu_kernel void @test_a(ptr addrspace(1) %out, float %in) {
|
|
entry:
|
|
%0 = fcmp olt float %in, 0.000000e+00
|
|
%1 = select i1 %0, float 1.000000e+00, float 0.000000e+00
|
|
%2 = fneg float %1
|
|
%3 = fptosi float %2 to i32
|
|
%4 = bitcast i32 %3 to float
|
|
%5 = bitcast float %4 to i32
|
|
%6 = icmp ne i32 %5, 0
|
|
br i1 %6, label %IF, label %ENDIF
|
|
|
|
IF:
|
|
%7 = getelementptr i32, ptr addrspace(1) %out, i32 1
|
|
store i32 0, ptr addrspace(1) %7
|
|
br label %ENDIF
|
|
|
|
ENDIF:
|
|
store i32 0, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; Same as test_a, but the branch labels are swapped to produce the inverse cc
|
|
; for the icmp instruction
|
|
|
|
; EG-LABEL: {{^}}test_b:
|
|
; EG: SET{{[GTEQN]+}}_DX10
|
|
; EG-NEXT: 0(0.000000e+00), 0(0.000000e+00)
|
|
; EG-NEXT: PRED_
|
|
; EG-NEXT: ALU clause starting
|
|
define amdgpu_kernel void @test_b(ptr addrspace(1) %out, float %in) {
|
|
entry:
|
|
%0 = fcmp olt float %in, 0.0
|
|
%1 = select i1 %0, float 1.000000e+00, float 0.000000e+00
|
|
%2 = fneg float %1
|
|
%3 = fptosi float %2 to i32
|
|
%4 = bitcast i32 %3 to float
|
|
%5 = bitcast float %4 to i32
|
|
%6 = icmp ne i32 %5, 0
|
|
br i1 %6, label %ENDIF, label %IF
|
|
|
|
IF:
|
|
%7 = getelementptr i32, ptr addrspace(1) %out, i32 1
|
|
store i32 0, ptr addrspace(1) %7
|
|
br label %ENDIF
|
|
|
|
ENDIF:
|
|
store i32 0, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; Test a CND*_INT instruction with float true/false values
|
|
; EG-LABEL: {{^}}test_c:
|
|
; EG: CND{{[GTE]+}}_INT
|
|
define amdgpu_kernel void @test_c(ptr addrspace(1) %out, i32 %in) {
|
|
entry:
|
|
%0 = icmp sgt i32 %in, 0
|
|
%1 = select i1 %0, float 2.0, float 3.0
|
|
store float %1, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}selectcc_bool:
|
|
; SI: s_cmp_lg_u32
|
|
; SI: v_cndmask_b32_e64
|
|
; SI-NOT: cmp
|
|
; SI-NOT: cndmask
|
|
define amdgpu_kernel void @selectcc_bool(ptr addrspace(1) %out, i32 %a, i32 %b) nounwind {
|
|
%icmp0 = icmp ne i32 %a, %b
|
|
%ext = select i1 %icmp0, i32 -1, i32 0
|
|
store i32 %ext, ptr addrspace(1) %out
|
|
ret void
|
|
}
|