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
110 lines
4.2 KiB
LLVM
110 lines
4.2 KiB
LLVM
; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx600 <%s | FileCheck -enable-var-scope -check-prefixes=GCN,SICI,SI %s
|
|
; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx700 <%s | FileCheck -enable-var-scope -check-prefixes=GCN,SICI,CI %s
|
|
|
|
; Check that an addrspace(1) (const) load with various combinations of
|
|
; uniform, nonuniform and constant address components all load with an
|
|
; addr64 mubuf with no readfirstlane.
|
|
|
|
@indexable = internal unnamed_addr addrspace(1) constant [6 x <3 x float>] [<3 x float> <float 1.000000e+00, float 0.000000e+00, float 0.000000e+00>, <3 x float> <float 0.000000e+00, float 1.000000e+00, float 0.000000e+00>, <3 x float> <float 0.000000e+00, float 0.000000e+00, float 1.000000e+00>, <3 x float> <float 0.000000e+00, float 1.000000e+00, float 1.000000e+00>, <3 x float> <float 1.000000e+00, float 0.000000e+00, float 1.000000e+00>, <3 x float> <float 1.000000e+00, float 1.000000e+00, float 0.000000e+00>]
|
|
|
|
; GCN-LABEL: {{^}}nonuniform_uniform:
|
|
; GCN-NOT: readfirstlane
|
|
; SI: buffer_load_dwordx4 {{.*}} addr64
|
|
; CI: buffer_load_dwordx3 {{.*}} addr64
|
|
|
|
define amdgpu_ps float @nonuniform_uniform(i32 %arg18) {
|
|
.entry:
|
|
%tmp31 = sext i32 %arg18 to i64
|
|
%tmp32 = getelementptr [6 x <3 x float>], ptr addrspace(1) @indexable, i64 0, i64 %tmp31
|
|
%tmp33 = load <3 x float>, ptr addrspace(1) %tmp32, align 16
|
|
%tmp34 = extractelement <3 x float> %tmp33, i32 0
|
|
ret float %tmp34
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}uniform_nonuniform:
|
|
; GCN-NOT: readfirstlane
|
|
; SI: buffer_load_dwordx4 {{.*}} addr64
|
|
; CI: buffer_load_dwordx3 {{.*}} addr64
|
|
|
|
define amdgpu_ps float @uniform_nonuniform(i32 inreg %offset, i32 %arg18) {
|
|
.entry:
|
|
%tmp1 = zext i32 %arg18 to i64
|
|
%tmp2 = inttoptr i64 %tmp1 to ptr addrspace(1)
|
|
%tmp32 = getelementptr [6 x <3 x float>], ptr addrspace(1) %tmp2, i32 0, i32 %offset
|
|
%tmp33 = load <3 x float>, ptr addrspace(1) %tmp32, align 16
|
|
%tmp34 = extractelement <3 x float> %tmp33, i32 0
|
|
ret float %tmp34
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}const_nonuniform:
|
|
; GCN-NOT: readfirstlane
|
|
; SI: buffer_load_dwordx4 {{.*}} addr64
|
|
; CI: buffer_load_dwordx3 {{.*}} addr64
|
|
|
|
define amdgpu_ps float @const_nonuniform(i32 %arg18) {
|
|
.entry:
|
|
%tmp1 = zext i32 %arg18 to i64
|
|
%tmp2 = inttoptr i64 %tmp1 to ptr addrspace(1)
|
|
%tmp32 = getelementptr [6 x <3 x float>], ptr addrspace(1) %tmp2, i32 0, i32 1
|
|
%tmp33 = load <3 x float>, ptr addrspace(1) %tmp32, align 16
|
|
%tmp34 = extractelement <3 x float> %tmp33, i32 0
|
|
ret float %tmp34
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}nonuniform_nonuniform:
|
|
; GCN-NOT: readfirstlane
|
|
; SI: buffer_load_dwordx4 {{.*}} addr64
|
|
; CI: buffer_load_dwordx3 {{.*}} addr64
|
|
|
|
define amdgpu_ps float @nonuniform_nonuniform(i32 %offset, i32 %arg18) {
|
|
.entry:
|
|
%tmp1 = zext i32 %arg18 to i64
|
|
%tmp2 = inttoptr i64 %tmp1 to ptr addrspace(1)
|
|
%tmp32 = getelementptr [6 x <3 x float>], ptr addrspace(1) %tmp2, i32 0, i32 %offset
|
|
%tmp33 = load <3 x float>, ptr addrspace(1) %tmp32, align 16
|
|
%tmp34 = extractelement <3 x float> %tmp33, i32 0
|
|
ret float %tmp34
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}nonuniform_uniform_const:
|
|
; GCN-NOT: readfirstlane
|
|
; SICI: buffer_load_dword {{.*}} addr64
|
|
|
|
define amdgpu_ps float @nonuniform_uniform_const(i32 %arg18) {
|
|
.entry:
|
|
%tmp31 = sext i32 %arg18 to i64
|
|
%tmp32 = getelementptr [6 x <3 x float>], ptr addrspace(1) @indexable, i64 0, i64 %tmp31, i64 1
|
|
%tmp33 = load float, ptr addrspace(1) %tmp32, align 4
|
|
ret float %tmp33
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}uniform_nonuniform_const:
|
|
; GCN-NOT: readfirstlane
|
|
; SICI: buffer_load_dword {{.*}} addr64
|
|
|
|
define amdgpu_ps float @uniform_nonuniform_const(i32 inreg %offset, i32 %arg18) {
|
|
.entry:
|
|
%tmp1 = zext i32 %arg18 to i64
|
|
%tmp2 = inttoptr i64 %tmp1 to ptr addrspace(1)
|
|
%tmp32 = getelementptr [6 x <3 x float>], ptr addrspace(1) %tmp2, i32 0, i32 %offset, i32 1
|
|
%tmp33 = load float, ptr addrspace(1) %tmp32, align 4
|
|
ret float %tmp33
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}nonuniform_nonuniform_const:
|
|
; GCN-NOT: readfirstlane
|
|
; SICI: buffer_load_dword {{.*}} addr64
|
|
|
|
define amdgpu_ps float @nonuniform_nonuniform_const(i32 %offset, i32 %arg18) {
|
|
.entry:
|
|
%tmp1 = zext i32 %arg18 to i64
|
|
%tmp2 = inttoptr i64 %tmp1 to ptr addrspace(1)
|
|
%tmp32 = getelementptr [6 x <3 x float>], ptr addrspace(1) %tmp2, i32 0, i32 %offset, i32 1
|
|
%tmp33 = load float, ptr addrspace(1) %tmp32, align 4
|
|
ret float %tmp33
|
|
}
|
|
|
|
|
|
|
|
|