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
43 lines
2.0 KiB
LLVM
43 lines
2.0 KiB
LLVM
; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -show-mc-encoding < %s | FileCheck -check-prefixes=GCN,GFX10 %s
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -show-mc-encoding < %s | FileCheck -check-prefixes=GCN,GFX11 %s
|
|
|
|
; GCN-LABEL: {{^}}smrd_imm_dlc:
|
|
; GFX10: s_buffer_load_dword s0, s[0:3], 0x0 dlc ; encoding: [0x00,0x40,0x20,0xf4,0x00,0x00,0x00,0xfa]
|
|
; GFX11: s_buffer_load_b32 s0, s[0:3], 0x0 dlc ; encoding: [0x00,0x20,0x20,0xf4,0x00,0x00,0x00,0xf8]
|
|
define amdgpu_ps float @smrd_imm_dlc(<4 x i32> inreg %desc) #0 {
|
|
main_body:
|
|
%r = call float @llvm.amdgcn.s.buffer.load.f32(<4 x i32> %desc, i32 0, i32 4)
|
|
ret float %r
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}smrd_sgpr_dlc:
|
|
; GFX10: s_buffer_load_dword s0, s[0:3], s4 offset:0x0 dlc ; encoding: [0x00,0x40,0x20,0xf4,0x00,0x00,0x00,0x08]
|
|
; GFX11: s_buffer_load_b32 s0, s[0:3], s4 offset:0x0 dlc ; encoding: [0x00,0x20,0x20,0xf4,0x00,0x00,0x00,0x08]
|
|
define amdgpu_ps float @smrd_sgpr_dlc(<4 x i32> inreg %desc, i32 inreg %offset) #0 {
|
|
main_body:
|
|
%r = call float @llvm.amdgcn.s.buffer.load.f32(<4 x i32> %desc, i32 %offset, i32 4)
|
|
ret float %r
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}smrd_imm_glc_dlc:
|
|
; GFX10: s_buffer_load_dword s0, s[0:3], 0x0 glc dlc ; encoding: [0x00,0x40,0x21,0xf4,0x00,0x00,0x00,0xfa]
|
|
; GFX11: s_buffer_load_b32 s0, s[0:3], 0x0 glc dlc ; encoding: [0x00,0x60,0x20,0xf4,0x00,0x00,0x00,0xf8]
|
|
define amdgpu_ps float @smrd_imm_glc_dlc(<4 x i32> inreg %desc) #0 {
|
|
main_body:
|
|
%r = call float @llvm.amdgcn.s.buffer.load.f32(<4 x i32> %desc, i32 0, i32 5)
|
|
ret float %r
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}smrd_sgpr_glc_dlc:
|
|
; GFX10: s_buffer_load_dword s0, s[0:3], s4 offset:0x0 glc dlc ; encoding: [0x00,0x40,0x21,0xf4,0x00,0x00,0x00,0x08]
|
|
; GFX11: s_buffer_load_b32 s0, s[0:3], s4 offset:0x0 glc dlc ; encoding: [0x00,0x60,0x20,0xf4,0x00,0x00,0x00,0x08]
|
|
define amdgpu_ps float @smrd_sgpr_glc_dlc(<4 x i32> inreg %desc, i32 inreg %offset) #0 {
|
|
main_body:
|
|
%r = call float @llvm.amdgcn.s.buffer.load.f32(<4 x i32> %desc, i32 %offset, i32 5)
|
|
ret float %r
|
|
}
|
|
|
|
declare float @llvm.amdgcn.s.buffer.load.f32(<4 x i32>, i32, i32)
|
|
|
|
!0 = !{}
|