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
135 lines
5.9 KiB
LLVM
135 lines
5.9 KiB
LLVM
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=bonaire < %s | FileCheck -check-prefixes=GCN,FUNC %s
|
|
; RUN: llc -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=bonaire < %s | FileCheck -check-prefixes=GCN,FUNC %s
|
|
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=tonga < %s | FileCheck -check-prefixes=GCN,VIGFX9,FUNC %s
|
|
; RUN: llc -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=tonga < %s | FileCheck -check-prefixes=GCN,VIGFX9,FUNC %s
|
|
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN,VIGFX9,FUNC %s
|
|
; RUN: llc -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN,VIGFX9,FUNC %s
|
|
|
|
; FUNC-LABEL: {{^}}ds_ordered_add:
|
|
; GCN-DAG: v_mov_b32_e32 v[[INCR:[0-9]+]], 31
|
|
; GCN-DAG: s_mov_b32 m0,
|
|
; GCN: ds_ordered_count v{{[0-9]+}}, v[[INCR]] offset:772 gds
|
|
define amdgpu_kernel void @ds_ordered_add(ptr addrspace(2) inreg %gds, ptr addrspace(1) %out) {
|
|
%val = call i32@llvm.amdgcn.ds.ordered.add(ptr addrspace(2) %gds, i32 31, i32 0, i32 0, i1 false, i32 1, i1 true, i1 true)
|
|
store i32 %val, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; Below are various modifications of input operands and shader types.
|
|
|
|
; FUNC-LABEL: {{^}}ds_ordered_add_counter2:
|
|
; GCN-DAG: v_mov_b32_e32 v[[INCR:[0-9]+]], 31
|
|
; GCN-DAG: s_mov_b32 m0,
|
|
; GCN: ds_ordered_count v{{[0-9]+}}, v[[INCR]] offset:776 gds
|
|
define amdgpu_kernel void @ds_ordered_add_counter2(ptr addrspace(2) inreg %gds, ptr addrspace(1) %out) {
|
|
%val = call i32@llvm.amdgcn.ds.ordered.add(ptr addrspace(2) %gds, i32 31, i32 0, i32 0, i1 false, i32 2, i1 true, i1 true)
|
|
store i32 %val, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ds_ordered_add_nodone:
|
|
; GCN-DAG: v_mov_b32_e32 v[[INCR:[0-9]+]], 31
|
|
; GCN-DAG: s_mov_b32 m0,
|
|
; GCN: ds_ordered_count v{{[0-9]+}}, v[[INCR]] offset:260 gds
|
|
define amdgpu_kernel void @ds_ordered_add_nodone(ptr addrspace(2) inreg %gds, ptr addrspace(1) %out) {
|
|
%val = call i32@llvm.amdgcn.ds.ordered.add(ptr addrspace(2) %gds, i32 31, i32 0, i32 0, i1 false, i32 1, i1 true, i1 false)
|
|
store i32 %val, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ds_ordered_add_norelease:
|
|
; GCN-DAG: v_mov_b32_e32 v[[INCR:[0-9]+]], 31
|
|
; GCN-DAG: s_mov_b32 m0,
|
|
; GCN: ds_ordered_count v{{[0-9]+}}, v[[INCR]] offset:4 gds
|
|
define amdgpu_kernel void @ds_ordered_add_norelease(ptr addrspace(2) inreg %gds, ptr addrspace(1) %out) {
|
|
%val = call i32@llvm.amdgcn.ds.ordered.add(ptr addrspace(2) %gds, i32 31, i32 0, i32 0, i1 false, i32 1, i1 false, i1 false)
|
|
store i32 %val, ptr addrspace(1) %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ds_ordered_add_cs:
|
|
; GCN: v_mov_b32_e32 v[[INCR:[0-9]+]], 31
|
|
; GCN: s_mov_b32 m0, s0
|
|
; VIGFX9-NEXT: s_nop 0
|
|
; GCN-NEXT: ds_ordered_count v{{[0-9]+}}, v[[INCR]] offset:772 gds
|
|
; GCN-NEXT: s_waitcnt expcnt(0) lgkmcnt(0)
|
|
define amdgpu_cs float @ds_ordered_add_cs(ptr addrspace(2) inreg %gds) {
|
|
%val = call i32@llvm.amdgcn.ds.ordered.add(ptr addrspace(2) %gds, i32 31, i32 0, i32 0, i1 false, i32 1, i1 true, i1 true)
|
|
%r = bitcast i32 %val to float
|
|
ret float %r
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ds_ordered_add_default_cc:
|
|
; GCN: v_mov_b32_e32 v[[INCR:[0-9]+]], 31
|
|
; GCN: s_mov_b32 m0, 0{{$}}
|
|
; VIGFX9-NEXT: s_nop 0
|
|
; GCN-NEXT: ds_ordered_count v{{[0-9]+}}, v[[INCR]] offset:772 gds
|
|
; GCN-NEXT: s_waitcnt expcnt(0) lgkmcnt(0)
|
|
define float @ds_ordered_add_default_cc() {
|
|
%val = call i32 @llvm.amdgcn.ds.ordered.add(ptr addrspace(2) zeroinitializer, i32 31, i32 0, i32 0, i1 false, i32 1, i1 true, i1 true)
|
|
%r = bitcast i32 %val to float
|
|
ret float %r
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ds_ordered_add_fastcc:
|
|
; GCN: v_mov_b32_e32 v[[INCR:[0-9]+]], 31
|
|
; GCN: s_mov_b32 m0, 0{{$}}
|
|
; VIGFX9-NEXT: s_nop 0
|
|
; GCN-NEXT: ds_ordered_count v{{[0-9]+}}, v[[INCR]] offset:772 gds
|
|
; GCN-NEXT: s_waitcnt expcnt(0) lgkmcnt(0)
|
|
define fastcc float @ds_ordered_add_fastcc() {
|
|
%val = call i32 @llvm.amdgcn.ds.ordered.add(ptr addrspace(2) zeroinitializer, i32 31, i32 0, i32 0, i1 false, i32 1, i1 true, i1 true)
|
|
%r = bitcast i32 %val to float
|
|
ret float %r
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ds_ordered_add_func:
|
|
; GCN: v_mov_b32_e32 v[[INCR:[0-9]+]], 31
|
|
; GCN: s_mov_b32 m0, 0{{$}}
|
|
; VIGFX9-NEXT: s_nop 0
|
|
; GCN-NEXT: ds_ordered_count v{{[0-9]+}}, v[[INCR]] offset:772 gds
|
|
; GCN-NEXT: s_waitcnt expcnt(0) lgkmcnt(0)
|
|
define float @ds_ordered_add_func() {
|
|
%val = call i32@llvm.amdgcn.ds.ordered.add(ptr addrspace(2) zeroinitializer, i32 31, i32 0, i32 0, i1 false, i32 1, i1 true, i1 true)
|
|
%r = bitcast i32 %val to float
|
|
ret float %r
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ds_ordered_add_ps:
|
|
; GCN: v_mov_b32_e32 v[[INCR:[0-9]+]], 31
|
|
; GCN: s_mov_b32 m0, s0
|
|
; VIGFX9-NEXT: s_nop 0
|
|
; GCN-NEXT: ds_ordered_count v{{[0-9]+}}, v[[INCR]] offset:1796 gds
|
|
; GCN-NEXT: s_waitcnt expcnt(0) lgkmcnt(0)
|
|
define amdgpu_ps float @ds_ordered_add_ps(ptr addrspace(2) inreg %gds) {
|
|
%val = call i32@llvm.amdgcn.ds.ordered.add(ptr addrspace(2) %gds, i32 31, i32 0, i32 0, i1 false, i32 1, i1 true, i1 true)
|
|
%r = bitcast i32 %val to float
|
|
ret float %r
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ds_ordered_add_vs:
|
|
; GCN: v_mov_b32_e32 v[[INCR:[0-9]+]], 31
|
|
; GCN: s_mov_b32 m0, s0
|
|
; VIGFX9-NEXT: s_nop 0
|
|
; GCN-NEXT: ds_ordered_count v{{[0-9]+}}, v[[INCR]] offset:2820 gds
|
|
; GCN-NEXT: s_waitcnt expcnt(0) lgkmcnt(0)
|
|
define amdgpu_vs float @ds_ordered_add_vs(ptr addrspace(2) inreg %gds) {
|
|
%val = call i32@llvm.amdgcn.ds.ordered.add(ptr addrspace(2) %gds, i32 31, i32 0, i32 0, i1 false, i32 1, i1 true, i1 true)
|
|
%r = bitcast i32 %val to float
|
|
ret float %r
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ds_ordered_add_gs:
|
|
; GCN: v_mov_b32_e32 v[[INCR:[0-9]+]], 31
|
|
; GCN: s_mov_b32 m0, s0
|
|
; VIGFX9-NEXT: s_nop 0
|
|
; GCN-NEXT: ds_ordered_count v{{[0-9]+}}, v[[INCR]] offset:3844 gds
|
|
; GCN-NEXT: s_waitcnt expcnt(0) lgkmcnt(0)
|
|
define amdgpu_gs float @ds_ordered_add_gs(ptr addrspace(2) inreg %gds) {
|
|
%val = call i32@llvm.amdgcn.ds.ordered.add(ptr addrspace(2) %gds, i32 31, i32 0, i32 0, i1 false, i32 1, i1 true, i1 true)
|
|
%r = bitcast i32 %val to float
|
|
ret float %r
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.ds.ordered.add(ptr addrspace(2) nocapture, i32, i32, i32, i1, i32, i1, i1)
|