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
65 lines
2.2 KiB
LLVM
65 lines
2.2 KiB
LLVM
; RUN: llc < %s -mtriple=amdgcn -mcpu=tahiti | FileCheck -check-prefix=GCN %s
|
|
; RUN: llc < %s -mtriple=amdgcn -mcpu=tonga | FileCheck -check-prefix=GCN %s
|
|
|
|
; GCN-LABEL: {{^}}select0:
|
|
; i64 select should be split into two i32 selects, and we shouldn't need
|
|
; to use a shfit to extract the hi dword of the input.
|
|
; GCN-NOT: s_lshr_b64
|
|
; GCN: s_cselect_b32
|
|
; GCN: s_cselect_b32
|
|
define amdgpu_kernel void @select0(ptr addrspace(1) %out, i32 %cond, i64 %in) {
|
|
entry:
|
|
%0 = icmp ugt i32 %cond, 5
|
|
%1 = select i1 %0, i64 0, i64 %in
|
|
store i64 %1, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}select_trunc_i64:
|
|
; GCN: s_cselect_b32
|
|
; GCN-NOT: s_cselect_b32
|
|
define amdgpu_kernel void @select_trunc_i64(ptr addrspace(1) %out, i32 %cond, i64 %in) nounwind {
|
|
%cmp = icmp ugt i32 %cond, 5
|
|
%sel = select i1 %cmp, i64 0, i64 %in
|
|
%trunc = trunc i64 %sel to i32
|
|
store i32 %trunc, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}select_trunc_i64_2:
|
|
; GCN: s_cselect_b32
|
|
; GCN-NOT: s_cselect_b32
|
|
define amdgpu_kernel void @select_trunc_i64_2(ptr addrspace(1) %out, i32 %cond, i64 %a, i64 %b) nounwind {
|
|
%cmp = icmp ugt i32 %cond, 5
|
|
%sel = select i1 %cmp, i64 %a, i64 %b
|
|
%trunc = trunc i64 %sel to i32
|
|
store i32 %trunc, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}v_select_trunc_i64_2:
|
|
; GCN: s_cselect_b32
|
|
; GCN-NOT: s_cselect_b32
|
|
define amdgpu_kernel void @v_select_trunc_i64_2(ptr addrspace(1) %out, i32 %cond, ptr addrspace(1) %aptr, ptr addrspace(4) %bptr) nounwind {
|
|
%cmp = icmp ugt i32 %cond, 5
|
|
%a = load i64, ptr addrspace(1) %aptr, align 8
|
|
%b = load i64, ptr addrspace(4) %bptr, align 8
|
|
%sel = select i1 %cmp, i64 %a, i64 %b
|
|
%trunc = trunc i64 %sel to i32
|
|
store i32 %trunc, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}v_select_i64_split_imm:
|
|
; GCN-DAG: s_cselect_b32
|
|
; GCN-DAG: s_cselect_b32
|
|
; GCN: s_endpgm
|
|
define amdgpu_kernel void @v_select_i64_split_imm(ptr addrspace(1) %out, i32 %cond, ptr addrspace(1) %aptr, ptr addrspace(1) %bptr) nounwind {
|
|
%cmp = icmp ugt i32 %cond, 5
|
|
%a = load i64, ptr addrspace(1) %aptr, align 8
|
|
%b = load i64, ptr addrspace(1) %bptr, align 8
|
|
%sel = select i1 %cmp, i64 %a, i64 270582939648 ; 63 << 32
|
|
store i64 %sel, ptr addrspace(1) %out, align 8
|
|
ret void
|
|
}
|