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
57 lines
2.3 KiB
LLVM
57 lines
2.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx700 < %s | FileCheck -check-prefixes=GFX7 %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx803 < %s | FileCheck -check-prefixes=GFX8 %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx1100 < %s | FileCheck -check-prefixes=GFX11 %s
|
|
|
|
define amdgpu_kernel void @fcmp_uniform_select(float %a, i32 %b, i32 %c, ptr addrspace(1) %out) {
|
|
; GFX7-LABEL: fcmp_uniform_select:
|
|
; GFX7: ; %bb.0:
|
|
; GFX7-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x9
|
|
; GFX7-NEXT: s_load_dword s3, s[4:5], 0xb
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0xd
|
|
; GFX7-NEXT: s_mov_b32 s2, -1
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_cmp_eq_f32_e64 s[4:5], s6, 0
|
|
; GFX7-NEXT: s_or_b64 s[4:5], s[4:5], s[4:5]
|
|
; GFX7-NEXT: s_cselect_b32 s3, s7, s3
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s3
|
|
; GFX7-NEXT: s_mov_b32 s3, 0xf000
|
|
; GFX7-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX8-LABEL: fcmp_uniform_select:
|
|
; GFX8: ; %bb.0:
|
|
; GFX8-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x24
|
|
; GFX8-NEXT: s_load_dword s6, s[4:5], 0x2c
|
|
; GFX8-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x34
|
|
; GFX8-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX8-NEXT: v_cmp_eq_f32_e64 s[4:5], s0, 0
|
|
; GFX8-NEXT: s_cmp_lg_u64 s[4:5], 0
|
|
; GFX8-NEXT: s_cselect_b32 s0, s1, s6
|
|
; GFX8-NEXT: v_mov_b32_e32 v0, s2
|
|
; GFX8-NEXT: v_mov_b32_e32 v2, s0
|
|
; GFX8-NEXT: v_mov_b32_e32 v1, s3
|
|
; GFX8-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX8-NEXT: s_endpgm
|
|
;
|
|
; GFX11-LABEL: fcmp_uniform_select:
|
|
; GFX11: ; %bb.0:
|
|
; GFX11-NEXT: s_clause 0x2
|
|
; GFX11-NEXT: s_load_b64 s[0:1], s[4:5], 0x24
|
|
; GFX11-NEXT: s_load_b32 s6, s[4:5], 0x2c
|
|
; GFX11-NEXT: s_load_b64 s[2:3], s[4:5], 0x34
|
|
; GFX11-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX11-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX11-NEXT: v_cmp_eq_f32_e64 s0, s0, 0
|
|
; GFX11-NEXT: s_cmp_lg_u32 s0, 0
|
|
; GFX11-NEXT: s_cselect_b32 s0, s1, s6
|
|
; GFX11-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
|
|
; GFX11-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX11-NEXT: global_store_b32 v1, v0, s[2:3]
|
|
; GFX11-NEXT: s_endpgm
|
|
%cmp = fcmp oeq float %a, 0.0
|
|
%sel = select i1 %cmp, i32 %b, i32 %c
|
|
store i32 %sel, ptr addrspace(1) %out
|
|
ret void
|
|
}
|