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
150 lines
6.4 KiB
LLVM
150 lines
6.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn-mesa-mesa3d -mcpu=tonga -o - %s | FileCheck -check-prefix=UNPACKED %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx810 -o - %s | FileCheck -check-prefix=GFX81 %s
|
|
; FIXME: llc -global-isel -new-reg-bank-select -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 -o - %s | FileCheck -check-prefix=GFX9 %s
|
|
; FIXME: llc -global-isel -new-reg-bank-select -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -o - %s | FileCheck -check-prefix=GFX10 %s
|
|
; FIXME: llc -global-isel -new-reg-bank-select -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1100 -o - %s | FileCheck -check-prefix=GFX11 %s
|
|
; FIXME: llc -global-isel -new-reg-bank-select -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1200 -o - %s | FileCheck -check-prefix=GFX12 %s
|
|
|
|
define amdgpu_ps void @image_store_f16(<8 x i32> inreg %rsrc, i32 %s, i32 %t, half %data) {
|
|
; UNPACKED-LABEL: image_store_f16:
|
|
; UNPACKED: ; %bb.0:
|
|
; UNPACKED-NEXT: s_mov_b32 s0, s2
|
|
; UNPACKED-NEXT: s_mov_b32 s1, s3
|
|
; UNPACKED-NEXT: s_mov_b32 s2, s4
|
|
; UNPACKED-NEXT: s_mov_b32 s3, s5
|
|
; UNPACKED-NEXT: s_mov_b32 s4, s6
|
|
; UNPACKED-NEXT: s_mov_b32 s5, s7
|
|
; UNPACKED-NEXT: s_mov_b32 s6, s8
|
|
; UNPACKED-NEXT: s_mov_b32 s7, s9
|
|
; UNPACKED-NEXT: image_store v2, v[0:1], s[0:7] dmask:0x1 unorm d16
|
|
; UNPACKED-NEXT: s_endpgm
|
|
;
|
|
; GFX81-LABEL: image_store_f16:
|
|
; GFX81: ; %bb.0:
|
|
; GFX81-NEXT: s_mov_b32 s0, s2
|
|
; GFX81-NEXT: s_mov_b32 s1, s3
|
|
; GFX81-NEXT: s_mov_b32 s2, s4
|
|
; GFX81-NEXT: s_mov_b32 s3, s5
|
|
; GFX81-NEXT: s_mov_b32 s4, s6
|
|
; GFX81-NEXT: s_mov_b32 s5, s7
|
|
; GFX81-NEXT: s_mov_b32 s6, s8
|
|
; GFX81-NEXT: s_mov_b32 s7, s9
|
|
; GFX81-NEXT: image_store v2, v[0:1], s[0:7] dmask:0x1 unorm d16
|
|
; GFX81-NEXT: s_endpgm
|
|
call void @llvm.amdgcn.image.store.2d.f16.i32(half %data, i32 1, i32 %s, i32 %t, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @image_store_v2f16(<8 x i32> inreg %rsrc, i32 %s, i32 %t, <2 x half> %in) {
|
|
; UNPACKED-LABEL: image_store_v2f16:
|
|
; UNPACKED: ; %bb.0:
|
|
; UNPACKED-NEXT: s_mov_b32 s0, s2
|
|
; UNPACKED-NEXT: s_mov_b32 s1, s3
|
|
; UNPACKED-NEXT: s_mov_b32 s2, s4
|
|
; UNPACKED-NEXT: s_mov_b32 s3, s5
|
|
; UNPACKED-NEXT: s_mov_b32 s4, s6
|
|
; UNPACKED-NEXT: s_mov_b32 s5, s7
|
|
; UNPACKED-NEXT: s_mov_b32 s6, s8
|
|
; UNPACKED-NEXT: s_mov_b32 s7, s9
|
|
; UNPACKED-NEXT: v_lshrrev_b32_e32 v3, 16, v2
|
|
; UNPACKED-NEXT: image_store v[2:3], v[0:1], s[0:7] dmask:0x3 unorm d16
|
|
; UNPACKED-NEXT: s_endpgm
|
|
;
|
|
; GFX81-LABEL: image_store_v2f16:
|
|
; GFX81: ; %bb.0:
|
|
; GFX81-NEXT: s_mov_b32 s0, s2
|
|
; GFX81-NEXT: s_mov_b32 s1, s3
|
|
; GFX81-NEXT: s_mov_b32 s2, s4
|
|
; GFX81-NEXT: s_mov_b32 s3, s5
|
|
; GFX81-NEXT: s_mov_b32 s4, s6
|
|
; GFX81-NEXT: s_mov_b32 s5, s7
|
|
; GFX81-NEXT: s_mov_b32 s6, s8
|
|
; GFX81-NEXT: s_mov_b32 s7, s9
|
|
; GFX81-NEXT: image_store v[2:3], v[0:1], s[0:7] dmask:0x3 unorm d16
|
|
; GFX81-NEXT: s_endpgm
|
|
call void @llvm.amdgcn.image.store.2d.v2f16.i32(<2 x half> %in, i32 3, i32 %s, i32 %t, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @image_store_v3f16(<8 x i32> inreg %rsrc, i32 %s, i32 %t, <3 x half> %in) {
|
|
; UNPACKED-LABEL: image_store_v3f16:
|
|
; UNPACKED: ; %bb.0:
|
|
; UNPACKED-NEXT: v_mov_b32_e32 v5, v1
|
|
; UNPACKED-NEXT: v_mov_b32_e32 v1, v2
|
|
; UNPACKED-NEXT: s_mov_b32 s0, s2
|
|
; UNPACKED-NEXT: s_mov_b32 s1, s3
|
|
; UNPACKED-NEXT: s_mov_b32 s2, s4
|
|
; UNPACKED-NEXT: s_mov_b32 s3, s5
|
|
; UNPACKED-NEXT: s_mov_b32 s4, s6
|
|
; UNPACKED-NEXT: s_mov_b32 s5, s7
|
|
; UNPACKED-NEXT: s_mov_b32 s6, s8
|
|
; UNPACKED-NEXT: s_mov_b32 s7, s9
|
|
; UNPACKED-NEXT: v_mov_b32_e32 v4, v0
|
|
; UNPACKED-NEXT: v_lshrrev_b32_e32 v2, 16, v1
|
|
; UNPACKED-NEXT: image_store v[1:3], v[4:5], s[0:7] dmask:0x7 unorm d16
|
|
; UNPACKED-NEXT: s_endpgm
|
|
;
|
|
; GFX81-LABEL: image_store_v3f16:
|
|
; GFX81: ; %bb.0:
|
|
; GFX81-NEXT: v_lshrrev_b32_e32 v4, 16, v2
|
|
; GFX81-NEXT: v_lshlrev_b32_e32 v4, 16, v4
|
|
; GFX81-NEXT: s_mov_b32 s0, s2
|
|
; GFX81-NEXT: s_mov_b32 s1, s3
|
|
; GFX81-NEXT: s_mov_b32 s2, s4
|
|
; GFX81-NEXT: s_mov_b32 s3, s5
|
|
; GFX81-NEXT: s_mov_b32 s4, s6
|
|
; GFX81-NEXT: s_mov_b32 s5, s7
|
|
; GFX81-NEXT: s_mov_b32 s6, s8
|
|
; GFX81-NEXT: s_mov_b32 s7, s9
|
|
; GFX81-NEXT: v_or_b32_sdwa v2, v2, v4 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_0 src1_sel:DWORD
|
|
; GFX81-NEXT: v_and_b32_e32 v3, 0xffff, v3
|
|
; GFX81-NEXT: v_mov_b32_e32 v4, 0
|
|
; GFX81-NEXT: image_store v[2:4], v[0:1], s[0:7] dmask:0x7 unorm d16
|
|
; GFX81-NEXT: s_endpgm
|
|
call void @llvm.amdgcn.image.store.2d.v3f16.i32(<3 x half> %in, i32 7, i32 %s, i32 %t, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @image_store_v4f16(<8 x i32> inreg %rsrc, i32 %s, i32 %t, <4 x half> %in) {
|
|
; UNPACKED-LABEL: image_store_v4f16:
|
|
; UNPACKED: ; %bb.0:
|
|
; UNPACKED-NEXT: v_mov_b32_e32 v6, v1
|
|
; UNPACKED-NEXT: v_mov_b32_e32 v1, v2
|
|
; UNPACKED-NEXT: s_mov_b32 s0, s2
|
|
; UNPACKED-NEXT: s_mov_b32 s1, s3
|
|
; UNPACKED-NEXT: s_mov_b32 s2, s4
|
|
; UNPACKED-NEXT: s_mov_b32 s3, s5
|
|
; UNPACKED-NEXT: s_mov_b32 s4, s6
|
|
; UNPACKED-NEXT: s_mov_b32 s5, s7
|
|
; UNPACKED-NEXT: s_mov_b32 s6, s8
|
|
; UNPACKED-NEXT: s_mov_b32 s7, s9
|
|
; UNPACKED-NEXT: v_mov_b32_e32 v5, v0
|
|
; UNPACKED-NEXT: v_lshrrev_b32_e32 v2, 16, v1
|
|
; UNPACKED-NEXT: v_lshrrev_b32_e32 v4, 16, v3
|
|
; UNPACKED-NEXT: image_store v[1:4], v[5:6], s[0:7] dmask:0xf unorm d16
|
|
; UNPACKED-NEXT: s_endpgm
|
|
;
|
|
; GFX81-LABEL: image_store_v4f16:
|
|
; GFX81: ; %bb.0:
|
|
; GFX81-NEXT: s_mov_b32 s0, s2
|
|
; GFX81-NEXT: s_mov_b32 s1, s3
|
|
; GFX81-NEXT: s_mov_b32 s2, s4
|
|
; GFX81-NEXT: s_mov_b32 s3, s5
|
|
; GFX81-NEXT: s_mov_b32 s4, s6
|
|
; GFX81-NEXT: s_mov_b32 s5, s7
|
|
; GFX81-NEXT: s_mov_b32 s6, s8
|
|
; GFX81-NEXT: s_mov_b32 s7, s9
|
|
; GFX81-NEXT: image_store v[2:5], v[0:1], s[0:7] dmask:0xf unorm d16
|
|
; GFX81-NEXT: s_endpgm
|
|
call void @llvm.amdgcn.image.store.2d.v4f16.i32(<4 x half> %in, i32 15, i32 %s, i32 %t, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.amdgcn.image.store.2d.f16.i32(half, i32 immarg, i32, i32, <8 x i32>, i32 immarg, i32 immarg) #0
|
|
declare void @llvm.amdgcn.image.store.2d.v2f16.i32(<2 x half>, i32 immarg, i32, i32, <8 x i32>, i32 immarg, i32 immarg) #0
|
|
declare void @llvm.amdgcn.image.store.2d.v3f16.i32(<3 x half>, i32 immarg, i32, i32, <8 x i32>, i32 immarg, i32 immarg) #0
|
|
declare void @llvm.amdgcn.image.store.2d.v4f16.i32(<4 x half>, i32 immarg, i32, i32, <8 x i32>, i32 immarg, i32 immarg) #0
|
|
|
|
attributes #0 = { nounwind writeonly }
|