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
169 lines
9.0 KiB
LLVM
169 lines
9.0 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
|
|
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx950 < %s | FileCheck -check-prefixes=GFX950 %s
|
|
; RUN: llc -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx950 < %s | FileCheck -check-prefixes=GFX950 %s
|
|
; RUN: not --crash llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx942 -filetype=null < %s 2>&1 | FileCheck -check-prefix=ERR-SDAG %s
|
|
; RUN: not llc -global-isel=1 -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx942 -filetype=null < %s 2>&1 | FileCheck -check-prefix=ERR-GISEL %s
|
|
|
|
; ERR-SDAG: LLVM ERROR: Do not know how to expand this operator's operand!
|
|
; ERR-GISEL: LLVM ERROR: cannot select: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.amdgcn.struct.ptr.buffer.load.lds),
|
|
|
|
declare void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) nocapture, i32 %size, i32 %vindex, i32 %voffset, i32 %soffset, i32 %offset, i32 %aux)
|
|
|
|
;---------------------------------------------------------------------y
|
|
; dwordx3
|
|
;---------------------------------------------------------------------
|
|
|
|
define amdgpu_ps float @buffer_load_lds_dwordx3(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds) {
|
|
; GFX950-LABEL: buffer_load_lds_dwordx3:
|
|
; GFX950: ; %bb.0:
|
|
; GFX950-NEXT: s_mov_b32 m0, s4
|
|
; GFX950-NEXT: v_mov_b32_e32 v0, 8
|
|
; GFX950-NEXT: buffer_load_dwordx3 v0, s[0:3], 0 idxen lds
|
|
; GFX950-NEXT: buffer_load_dwordx3 v0, s[0:3], 0 idxen offset:4 sc0 lds
|
|
; GFX950-NEXT: buffer_load_dwordx3 v0, s[0:3], 0 idxen offset:8 nt lds
|
|
; GFX950-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX950-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX950-NEXT: ds_read_b32 v0, v0
|
|
; GFX950-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX950-NEXT: ; return to shader part epilog
|
|
call void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 12, i32 8, i32 0, i32 0, i32 0, i32 0)
|
|
call void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 12, i32 8, i32 0, i32 0, i32 4, i32 1)
|
|
call void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 12, i32 8, i32 0, i32 0, i32 8, i32 2)
|
|
%res = load float, ptr addrspace(3) %lds
|
|
ret float %res
|
|
}
|
|
|
|
define amdgpu_ps void @buffer_load_lds_dwordx3_imm_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 %vindex) {
|
|
; GFX950-LABEL: buffer_load_lds_dwordx3_imm_offset:
|
|
; GFX950: ; %bb.0:
|
|
; GFX950-NEXT: s_mov_b32 m0, s4
|
|
; GFX950-NEXT: s_nop 0
|
|
; GFX950-NEXT: buffer_load_dwordx3 v0, s[0:3], 0 idxen offset:2048 lds
|
|
; GFX950-NEXT: s_endpgm
|
|
call void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 12, i32 %vindex, i32 0, i32 0, i32 2048, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @buffer_load_lds_dwordx3_v_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 %vindex, i32 %voffset) {
|
|
; GFX950-LABEL: buffer_load_lds_dwordx3_v_offset:
|
|
; GFX950: ; %bb.0:
|
|
; GFX950-NEXT: s_mov_b32 m0, s4
|
|
; GFX950-NEXT: s_nop 0
|
|
; GFX950-NEXT: buffer_load_dwordx3 v[0:1], s[0:3], 0 idxen offen lds
|
|
; GFX950-NEXT: s_endpgm
|
|
call void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 12, i32 %vindex, i32 %voffset, i32 0, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @buffer_load_lds_dwordx3_s_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 %vindex, i32 inreg %soffset) {
|
|
; GFX950-LABEL: buffer_load_lds_dwordx3_s_offset:
|
|
; GFX950: ; %bb.0:
|
|
; GFX950-NEXT: s_mov_b32 m0, s4
|
|
; GFX950-NEXT: s_nop 0
|
|
; GFX950-NEXT: buffer_load_dwordx3 v0, s[0:3], s5 idxen lds
|
|
; GFX950-NEXT: s_endpgm
|
|
call void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 12, i32 %vindex, i32 0, i32 %soffset, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @buffer_load_lds_dwordx3_vs_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 %vindex, i32 %voffset, i32 inreg %soffset) {
|
|
; GFX950-LABEL: buffer_load_lds_dwordx3_vs_offset:
|
|
; GFX950: ; %bb.0:
|
|
; GFX950-NEXT: s_mov_b32 m0, s4
|
|
; GFX950-NEXT: s_nop 0
|
|
; GFX950-NEXT: buffer_load_dwordx3 v[0:1], s[0:3], s5 idxen offen lds
|
|
; GFX950-NEXT: s_endpgm
|
|
call void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 12, i32 %vindex, i32 %voffset, i32 %soffset, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @buffer_load_lds_dwordx3_vs_imm_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 %vindex, i32 %voffset, i32 inreg %soffset) {
|
|
; GFX950-LABEL: buffer_load_lds_dwordx3_vs_imm_offset:
|
|
; GFX950: ; %bb.0:
|
|
; GFX950-NEXT: s_mov_b32 m0, s4
|
|
; GFX950-NEXT: s_nop 0
|
|
; GFX950-NEXT: buffer_load_dwordx3 v[0:1], s[0:3], s5 idxen offen offset:2048 lds
|
|
; GFX950-NEXT: s_endpgm
|
|
call void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 12, i32 %vindex, i32 %voffset, i32 %soffset, i32 2048, i32 0)
|
|
ret void
|
|
}
|
|
|
|
;---------------------------------------------------------------------y
|
|
; dwordx4
|
|
;---------------------------------------------------------------------
|
|
|
|
define amdgpu_ps float @buffer_load_lds_dwordx4(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds) {
|
|
; GFX950-LABEL: buffer_load_lds_dwordx4:
|
|
; GFX950: ; %bb.0:
|
|
; GFX950-NEXT: s_mov_b32 m0, s4
|
|
; GFX950-NEXT: v_mov_b32_e32 v0, 8
|
|
; GFX950-NEXT: buffer_load_dwordx4 v0, s[0:3], 0 idxen lds
|
|
; GFX950-NEXT: buffer_load_dwordx4 v0, s[0:3], 0 idxen offset:4 sc0 lds
|
|
; GFX950-NEXT: buffer_load_dwordx4 v0, s[0:3], 0 idxen offset:8 nt lds
|
|
; GFX950-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX950-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX950-NEXT: ds_read_b32 v0, v0
|
|
; GFX950-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX950-NEXT: ; return to shader part epilog
|
|
call void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 16, i32 8, i32 0, i32 0, i32 0, i32 0)
|
|
call void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 16, i32 8, i32 0, i32 0, i32 4, i32 1)
|
|
call void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 16, i32 8, i32 0, i32 0, i32 8, i32 2)
|
|
%res = load float, ptr addrspace(3) %lds
|
|
ret float %res
|
|
}
|
|
|
|
define amdgpu_ps void @buffer_load_lds_dwordx4_imm_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 %vindex) {
|
|
; GFX950-LABEL: buffer_load_lds_dwordx4_imm_offset:
|
|
; GFX950: ; %bb.0:
|
|
; GFX950-NEXT: s_mov_b32 m0, s4
|
|
; GFX950-NEXT: s_nop 0
|
|
; GFX950-NEXT: buffer_load_dwordx4 v0, s[0:3], 0 idxen offset:2048 lds
|
|
; GFX950-NEXT: s_endpgm
|
|
call void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 16, i32 %vindex, i32 0, i32 0, i32 2048, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @buffer_load_lds_dwordx4_v_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 %vindex, i32 %voffset) {
|
|
; GFX950-LABEL: buffer_load_lds_dwordx4_v_offset:
|
|
; GFX950: ; %bb.0:
|
|
; GFX950-NEXT: s_mov_b32 m0, s4
|
|
; GFX950-NEXT: s_nop 0
|
|
; GFX950-NEXT: buffer_load_dwordx4 v[0:1], s[0:3], 0 idxen offen lds
|
|
; GFX950-NEXT: s_endpgm
|
|
call void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 16, i32 %vindex, i32 %voffset, i32 0, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @buffer_load_lds_dwordx4_s_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 %vindex, i32 inreg %soffset) {
|
|
; GFX950-LABEL: buffer_load_lds_dwordx4_s_offset:
|
|
; GFX950: ; %bb.0:
|
|
; GFX950-NEXT: s_mov_b32 m0, s4
|
|
; GFX950-NEXT: s_nop 0
|
|
; GFX950-NEXT: buffer_load_dwordx4 v0, s[0:3], s5 idxen lds
|
|
; GFX950-NEXT: s_endpgm
|
|
call void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 16, i32 %vindex, i32 0, i32 %soffset, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @buffer_load_lds_dwordx4_vs_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 %vindex, i32 %voffset, i32 inreg %soffset) {
|
|
; GFX950-LABEL: buffer_load_lds_dwordx4_vs_offset:
|
|
; GFX950: ; %bb.0:
|
|
; GFX950-NEXT: s_mov_b32 m0, s4
|
|
; GFX950-NEXT: s_nop 0
|
|
; GFX950-NEXT: buffer_load_dwordx4 v[0:1], s[0:3], s5 idxen offen lds
|
|
; GFX950-NEXT: s_endpgm
|
|
call void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 16, i32 %vindex, i32 %voffset, i32 %soffset, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @buffer_load_lds_dwordx4_vs_imm_offset(ptr addrspace(8) inreg %rsrc, ptr addrspace(3) inreg %lds, i32 %vindex, i32 %voffset, i32 inreg %soffset) {
|
|
; GFX950-LABEL: buffer_load_lds_dwordx4_vs_imm_offset:
|
|
; GFX950: ; %bb.0:
|
|
; GFX950-NEXT: s_mov_b32 m0, s4
|
|
; GFX950-NEXT: s_nop 0
|
|
; GFX950-NEXT: buffer_load_dwordx4 v[0:1], s[0:3], s5 idxen offen offset:2048 lds
|
|
; GFX950-NEXT: s_endpgm
|
|
call void @llvm.amdgcn.struct.ptr.buffer.load.lds(ptr addrspace(8) %rsrc, ptr addrspace(3) %lds, i32 16, i32 %vindex, i32 %voffset, i32 %soffset, i32 2048, i32 0)
|
|
ret void
|
|
}
|