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
178 lines
9.2 KiB
LLVM
178 lines
9.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx1200 -global-isel=0 | FileCheck %s -check-prefix=GFX12-SDAG
|
|
; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx1200 -global-isel=1 -global-isel-abort=2 | FileCheck %s -check-prefix=GFX12-GISEL
|
|
|
|
declare <2 x half> @llvm.amdgcn.struct.buffer.atomic.fadd.v2f16(<2 x half>, <4 x i32>, i32, i32, i32, i32 immarg)
|
|
declare <2 x bfloat> @llvm.amdgcn.struct.buffer.atomic.fadd.v2bf16(<2 x bfloat>, <4 x i32>, i32, i32, i32, i32 immarg)
|
|
declare <2 x half> @llvm.amdgcn.raw.buffer.atomic.fadd.v2f16(<2 x half>, <4 x i32>, i32, i32, i32)
|
|
declare <2 x bfloat> @llvm.amdgcn.raw.buffer.atomic.fadd.v2bf16(<2 x bfloat> %val, <4 x i32> %rsrc, i32, i32, i32)
|
|
|
|
define amdgpu_ps void @raw_buffer_atomic_add_v2f16_noret_offset(<2 x half> %val, <4 x i32> inreg %rsrc, i32 %voffset, i32 inreg %soffset) {
|
|
; GFX12-SDAG-LABEL: raw_buffer_atomic_add_v2f16_noret_offset:
|
|
; GFX12-SDAG: ; %bb.0:
|
|
; GFX12-SDAG-NEXT: buffer_atomic_pk_add_f16 v0, off, s[0:3], s4 offset:92
|
|
; GFX12-SDAG-NEXT: s_endpgm
|
|
;
|
|
; GFX12-GISEL-LABEL: raw_buffer_atomic_add_v2f16_noret_offset:
|
|
; GFX12-GISEL: ; %bb.0:
|
|
; GFX12-GISEL-NEXT: buffer_atomic_pk_add_f16 v0, off, s[0:3], s4 offset:92
|
|
; GFX12-GISEL-NEXT: s_endpgm
|
|
%ret = call <2 x half> @llvm.amdgcn.raw.buffer.atomic.fadd.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 92, i32 %soffset, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @raw_buffer_atomic_add_v2f16_noret(<2 x half> %val, <4 x i32> inreg %rsrc, i32 %voffset, i32 inreg %soffset) {
|
|
; GFX12-SDAG-LABEL: raw_buffer_atomic_add_v2f16_noret:
|
|
; GFX12-SDAG: ; %bb.0:
|
|
; GFX12-SDAG-NEXT: buffer_atomic_pk_add_f16 v0, v1, s[0:3], s4 offen
|
|
; GFX12-SDAG-NEXT: s_endpgm
|
|
;
|
|
; GFX12-GISEL-LABEL: raw_buffer_atomic_add_v2f16_noret:
|
|
; GFX12-GISEL: ; %bb.0:
|
|
; GFX12-GISEL-NEXT: buffer_atomic_pk_add_f16 v0, v1, s[0:3], s4 offen
|
|
; GFX12-GISEL-NEXT: s_endpgm
|
|
%ret = call <2 x half> @llvm.amdgcn.raw.buffer.atomic.fadd.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps <2 x half> @raw_buffer_atomic_add_v2f16_ret_offset(<2 x half> %val, <4 x i32> inreg %rsrc, i32 %voffset, i32 inreg %soffset) {
|
|
; GFX12-SDAG-LABEL: raw_buffer_atomic_add_v2f16_ret_offset:
|
|
; GFX12-SDAG: ; %bb.0:
|
|
; GFX12-SDAG-NEXT: buffer_atomic_pk_add_f16 v0, off, s[0:3], s4 offset:92 th:TH_ATOMIC_RETURN
|
|
; GFX12-SDAG-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-SDAG-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX12-GISEL-LABEL: raw_buffer_atomic_add_v2f16_ret_offset:
|
|
; GFX12-GISEL: ; %bb.0:
|
|
; GFX12-GISEL-NEXT: buffer_atomic_pk_add_f16 v0, off, s[0:3], s4 offset:92 th:TH_ATOMIC_RETURN
|
|
; GFX12-GISEL-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-GISEL-NEXT: ; return to shader part epilog
|
|
%ret = call <2 x half> @llvm.amdgcn.raw.buffer.atomic.fadd.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 92, i32 %soffset, i32 0)
|
|
ret <2 x half> %ret
|
|
}
|
|
|
|
define amdgpu_ps <2 x half> @raw_buffer_atomic_add_v2f16_ret(<2 x half> %val, <4 x i32> inreg %rsrc, i32 %voffset, i32 inreg %soffset) {
|
|
; GFX12-SDAG-LABEL: raw_buffer_atomic_add_v2f16_ret:
|
|
; GFX12-SDAG: ; %bb.0:
|
|
; GFX12-SDAG-NEXT: buffer_atomic_pk_add_f16 v0, v1, s[0:3], s4 offen th:TH_ATOMIC_RETURN
|
|
; GFX12-SDAG-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-SDAG-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX12-GISEL-LABEL: raw_buffer_atomic_add_v2f16_ret:
|
|
; GFX12-GISEL: ; %bb.0:
|
|
; GFX12-GISEL-NEXT: buffer_atomic_pk_add_f16 v0, v1, s[0:3], s4 offen th:TH_ATOMIC_RETURN
|
|
; GFX12-GISEL-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-GISEL-NEXT: ; return to shader part epilog
|
|
%ret = call <2 x half> @llvm.amdgcn.raw.buffer.atomic.fadd.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
|
|
ret <2 x half> %ret
|
|
}
|
|
|
|
define amdgpu_ps float @struct_buffer_atomic_add_v2f16_ret(<2 x half> %val, <4 x i32> inreg %rsrc, i32 %vindex, i32 %voffset, i32 inreg %soffset) {
|
|
; GFX12-SDAG-LABEL: struct_buffer_atomic_add_v2f16_ret:
|
|
; GFX12-SDAG: ; %bb.0:
|
|
; GFX12-SDAG-NEXT: buffer_atomic_pk_add_f16 v0, v[1:2], s[0:3], s4 idxen offen th:TH_ATOMIC_RETURN
|
|
; GFX12-SDAG-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-SDAG-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX12-GISEL-LABEL: struct_buffer_atomic_add_v2f16_ret:
|
|
; GFX12-GISEL: ; %bb.0:
|
|
; GFX12-GISEL-NEXT: buffer_atomic_pk_add_f16 v0, v[1:2], s[0:3], s4 idxen offen th:TH_ATOMIC_RETURN
|
|
; GFX12-GISEL-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-GISEL-NEXT: ; return to shader part epilog
|
|
%orig = call <2 x half> @llvm.amdgcn.struct.buffer.atomic.fadd.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
|
|
%r = bitcast <2 x half> %orig to float
|
|
ret float %r
|
|
}
|
|
|
|
define amdgpu_ps void @struct_buffer_atomic_add_v2f16_noret(<2 x half> %val, <4 x i32> inreg %rsrc, i32 %vindex, i32 %voffset, i32 inreg %soffset) {
|
|
; GFX12-SDAG-LABEL: struct_buffer_atomic_add_v2f16_noret:
|
|
; GFX12-SDAG: ; %bb.0:
|
|
; GFX12-SDAG-NEXT: buffer_atomic_pk_add_f16 v0, v[1:2], s[0:3], s4 idxen offen
|
|
; GFX12-SDAG-NEXT: s_endpgm
|
|
;
|
|
; GFX12-GISEL-LABEL: struct_buffer_atomic_add_v2f16_noret:
|
|
; GFX12-GISEL: ; %bb.0:
|
|
; GFX12-GISEL-NEXT: buffer_atomic_pk_add_f16 v0, v[1:2], s[0:3], s4 idxen offen
|
|
; GFX12-GISEL-NEXT: s_endpgm
|
|
%orig = call <2 x half> @llvm.amdgcn.struct.buffer.atomic.fadd.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps float @struct_buffer_atomic_add_v2bf16_ret(<2 x bfloat> %val, <4 x i32> inreg %rsrc, i32 %vindex, i32 %voffset, i32 inreg %soffset) {
|
|
; GFX12-SDAG-LABEL: struct_buffer_atomic_add_v2bf16_ret:
|
|
; GFX12-SDAG: ; %bb.0:
|
|
; GFX12-SDAG-NEXT: buffer_atomic_pk_add_bf16 v0, v[1:2], s[0:3], s4 idxen offen th:TH_ATOMIC_RETURN
|
|
; GFX12-SDAG-NEXT: v_dual_mov_b32 v1, 0 :: v_dual_mov_b32 v2, 0
|
|
; GFX12-SDAG-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-SDAG-NEXT: flat_store_b32 v[1:2], v0
|
|
; GFX12-SDAG-NEXT: v_mov_b32_e32 v0, 1.0
|
|
; GFX12-SDAG-NEXT: s_wait_dscnt 0x0
|
|
; GFX12-SDAG-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX12-GISEL-LABEL: struct_buffer_atomic_add_v2bf16_ret:
|
|
; GFX12-GISEL: ; %bb.0:
|
|
; GFX12-GISEL-NEXT: buffer_atomic_pk_add_bf16 v0, v[1:2], s[0:3], s4 idxen offen th:TH_ATOMIC_RETURN
|
|
; GFX12-GISEL-NEXT: v_dual_mov_b32 v1, 0 :: v_dual_mov_b32 v2, 0
|
|
; GFX12-GISEL-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-GISEL-NEXT: flat_store_b32 v[1:2], v0
|
|
; GFX12-GISEL-NEXT: v_mov_b32_e32 v0, 1.0
|
|
; GFX12-GISEL-NEXT: s_wait_dscnt 0x0
|
|
; GFX12-GISEL-NEXT: ; return to shader part epilog
|
|
%orig = call <2 x bfloat> @llvm.amdgcn.struct.buffer.atomic.fadd.v2bf16(<2 x bfloat> %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
|
|
store <2 x bfloat> %orig, ptr null
|
|
ret float 1.0
|
|
}
|
|
|
|
define amdgpu_ps void @struct_buffer_atomic_add_v2bf16_noret(<2 x bfloat> %val, <4 x i32> inreg %rsrc, i32 %vindex, i32 %voffset, i32 inreg %soffset) {
|
|
; GFX12-SDAG-LABEL: struct_buffer_atomic_add_v2bf16_noret:
|
|
; GFX12-SDAG: ; %bb.0:
|
|
; GFX12-SDAG-NEXT: buffer_atomic_pk_add_bf16 v0, v[1:2], s[0:3], s4 idxen offen
|
|
; GFX12-SDAG-NEXT: s_endpgm
|
|
;
|
|
; GFX12-GISEL-LABEL: struct_buffer_atomic_add_v2bf16_noret:
|
|
; GFX12-GISEL: ; %bb.0:
|
|
; GFX12-GISEL-NEXT: buffer_atomic_pk_add_bf16 v0, v[1:2], s[0:3], s4 idxen offen
|
|
; GFX12-GISEL-NEXT: s_endpgm
|
|
%orig = call <2 x bfloat> @llvm.amdgcn.struct.buffer.atomic.fadd.v2bf16(<2 x bfloat> %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @raw_buffer_atomic_add_v2bf16(<2 x bfloat> %val, <4 x i32> inreg %rsrc, i32 %voffset, i32 inreg %soffset) {
|
|
; GFX12-SDAG-LABEL: raw_buffer_atomic_add_v2bf16:
|
|
; GFX12-SDAG: ; %bb.0:
|
|
; GFX12-SDAG-NEXT: buffer_atomic_pk_add_bf16 v0, v1, s[0:3], s4 offen
|
|
; GFX12-SDAG-NEXT: s_endpgm
|
|
;
|
|
; GFX12-GISEL-LABEL: raw_buffer_atomic_add_v2bf16:
|
|
; GFX12-GISEL: ; %bb.0:
|
|
; GFX12-GISEL-NEXT: buffer_atomic_pk_add_bf16 v0, v1, s[0:3], s4 offen
|
|
; GFX12-GISEL-NEXT: s_endpgm
|
|
%ret = call <2 x bfloat> @llvm.amdgcn.raw.buffer.atomic.fadd.v2bf16(<2 x bfloat> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps float @raw_buffer_atomic_add_v2bf16_ret(<2 x bfloat> %val, <4 x i32> inreg %rsrc, i32 %voffset, i32 inreg %soffset) {
|
|
; GFX12-SDAG-LABEL: raw_buffer_atomic_add_v2bf16_ret:
|
|
; GFX12-SDAG: ; %bb.0:
|
|
; GFX12-SDAG-NEXT: buffer_atomic_pk_add_bf16 v0, v1, s[0:3], s4 offen th:TH_ATOMIC_RETURN
|
|
; GFX12-SDAG-NEXT: v_dual_mov_b32 v1, 0 :: v_dual_mov_b32 v2, 0
|
|
; GFX12-SDAG-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-SDAG-NEXT: flat_store_b32 v[1:2], v0
|
|
; GFX12-SDAG-NEXT: v_mov_b32_e32 v0, 1.0
|
|
; GFX12-SDAG-NEXT: s_wait_dscnt 0x0
|
|
; GFX12-SDAG-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX12-GISEL-LABEL: raw_buffer_atomic_add_v2bf16_ret:
|
|
; GFX12-GISEL: ; %bb.0:
|
|
; GFX12-GISEL-NEXT: buffer_atomic_pk_add_bf16 v0, v1, s[0:3], s4 offen th:TH_ATOMIC_RETURN
|
|
; GFX12-GISEL-NEXT: v_dual_mov_b32 v1, 0 :: v_dual_mov_b32 v2, 0
|
|
; GFX12-GISEL-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-GISEL-NEXT: flat_store_b32 v[1:2], v0
|
|
; GFX12-GISEL-NEXT: v_mov_b32_e32 v0, 1.0
|
|
; GFX12-GISEL-NEXT: s_wait_dscnt 0x0
|
|
; GFX12-GISEL-NEXT: ; return to shader part epilog
|
|
%orig = call <2 x bfloat> @llvm.amdgcn.raw.buffer.atomic.fadd.v2bf16(<2 x bfloat> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
|
|
store <2 x bfloat> %orig, ptr null
|
|
ret float 1.0
|
|
}
|