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
2418 lines
83 KiB
LLVM
2418 lines
83 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx600 < %s | FileCheck --check-prefixes=GFX6 %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx700 < %s | FileCheck --check-prefixes=GFX7 %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1010 < %s | FileCheck --check-prefixes=GFX10-WGP %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1010 -mattr=+cumode < %s | FileCheck --check-prefixes=GFX10-CU %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdpal -O0 -mcpu=gfx700 -amdgcn-skip-cache-invalidations < %s | FileCheck --check-prefixes=SKIP-CACHE-INV %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx90a < %s | FileCheck -check-prefixes=GFX90A-NOTTGSPLIT %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx90a -mattr=+tgsplit < %s | FileCheck -check-prefixes=GFX90A-TGSPLIT %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx942 < %s | FileCheck -check-prefixes=GFX942-NOTTGSPLIT %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx942 -mattr=+tgsplit < %s | FileCheck -check-prefixes=GFX942-TGSPLIT %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1100 < %s | FileCheck --check-prefixes=GFX11-WGP %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1100 -mattr=+cumode < %s | FileCheck --check-prefixes=GFX11-CU %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 < %s | FileCheck --check-prefixes=GFX12-WGP %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 -mattr=+cumode < %s | FileCheck --check-prefixes=GFX12-CU %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1250 < %s | FileCheck --check-prefixes=GFX1250 %s
|
|
|
|
define amdgpu_kernel void @workgroup_acquire_fence() {
|
|
; GFX6-LABEL: workgroup_acquire_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: workgroup_acquire_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: workgroup_acquire_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: workgroup_acquire_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: workgroup_acquire_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: workgroup_acquire_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: workgroup_acquire_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: workgroup_acquire_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: workgroup_acquire_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: workgroup_acquire_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: workgroup_acquire_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: workgroup_acquire_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_SE
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: workgroup_acquire_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: workgroup_acquire_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("workgroup") acquire, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @workgroup_release_fence() {
|
|
; GFX6-LABEL: workgroup_release_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: workgroup_release_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: workgroup_release_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: workgroup_release_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: workgroup_release_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: workgroup_release_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: workgroup_release_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: workgroup_release_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: workgroup_release_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: workgroup_release_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: workgroup_release_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: workgroup_release_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: workgroup_release_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: workgroup_release_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("workgroup") release, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @workgroup_acq_rel_fence() {
|
|
; GFX6-LABEL: workgroup_acq_rel_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: workgroup_acq_rel_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: workgroup_acq_rel_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: workgroup_acq_rel_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: workgroup_acq_rel_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: workgroup_acq_rel_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: workgroup_acq_rel_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: workgroup_acq_rel_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: workgroup_acq_rel_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: workgroup_acq_rel_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: workgroup_acq_rel_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: workgroup_acq_rel_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_SE
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: workgroup_acq_rel_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: workgroup_acq_rel_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("workgroup") acq_rel, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @workgroup_seq_cst_fence() {
|
|
; GFX6-LABEL: workgroup_seq_cst_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: workgroup_seq_cst_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: workgroup_seq_cst_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: workgroup_seq_cst_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: workgroup_seq_cst_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: workgroup_seq_cst_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: workgroup_seq_cst_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: workgroup_seq_cst_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: workgroup_seq_cst_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: workgroup_seq_cst_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: workgroup_seq_cst_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: workgroup_seq_cst_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_SE
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: workgroup_seq_cst_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: workgroup_seq_cst_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("workgroup") seq_cst, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @workgroup_one_as_acquire_fence() {
|
|
; GFX6-LABEL: workgroup_one_as_acquire_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: workgroup_one_as_acquire_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: workgroup_one_as_acquire_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: workgroup_one_as_acquire_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: workgroup_one_as_acquire_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: workgroup_one_as_acquire_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: workgroup_one_as_acquire_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: workgroup_one_as_acquire_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: workgroup_one_as_acquire_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: workgroup_one_as_acquire_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: workgroup_one_as_acquire_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: workgroup_one_as_acquire_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_SE
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: workgroup_one_as_acquire_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: workgroup_one_as_acquire_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("workgroup-one-as") acquire, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @workgroup_one_as_release_fence() {
|
|
; GFX6-LABEL: workgroup_one_as_release_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: workgroup_one_as_release_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: workgroup_one_as_release_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: workgroup_one_as_release_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: workgroup_one_as_release_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: workgroup_one_as_release_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: workgroup_one_as_release_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: workgroup_one_as_release_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: workgroup_one_as_release_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: workgroup_one_as_release_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: workgroup_one_as_release_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: workgroup_one_as_release_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: workgroup_one_as_release_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: workgroup_one_as_release_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("workgroup-one-as") release, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @workgroup_one_as_acq_rel_fence() {
|
|
; GFX6-LABEL: workgroup_one_as_acq_rel_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: workgroup_one_as_acq_rel_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: workgroup_one_as_acq_rel_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: workgroup_one_as_acq_rel_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: workgroup_one_as_acq_rel_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: workgroup_one_as_acq_rel_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: workgroup_one_as_acq_rel_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: workgroup_one_as_acq_rel_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: workgroup_one_as_acq_rel_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: workgroup_one_as_acq_rel_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: workgroup_one_as_acq_rel_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: workgroup_one_as_acq_rel_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_SE
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: workgroup_one_as_acq_rel_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: workgroup_one_as_acq_rel_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("workgroup-one-as") acq_rel, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @workgroup_one_as_seq_cst_fence() {
|
|
; GFX6-LABEL: workgroup_one_as_seq_cst_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: workgroup_one_as_seq_cst_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: workgroup_one_as_seq_cst_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: workgroup_one_as_seq_cst_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: workgroup_one_as_seq_cst_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: workgroup_one_as_seq_cst_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: workgroup_one_as_seq_cst_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: workgroup_one_as_seq_cst_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: workgroup_one_as_seq_cst_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: workgroup_one_as_seq_cst_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: workgroup_one_as_seq_cst_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: workgroup_one_as_seq_cst_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_SE
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: workgroup_one_as_seq_cst_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: workgroup_one_as_seq_cst_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("workgroup-one-as") seq_cst, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @agent_acquire_fence() {
|
|
; GFX6-LABEL: agent_acquire_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_wbinvl1
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: agent_acquire_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: buffer_wbinvl1_vol
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: agent_acquire_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl1_inv
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: agent_acquire_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: buffer_gl1_inv
|
|
; GFX10-CU-NEXT: buffer_gl0_inv
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: agent_acquire_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: agent_acquire_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: agent_acquire_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: agent_acquire_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_inv sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: agent_acquire_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc1
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: agent_acquire_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl1_inv
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: agent_acquire_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: buffer_gl1_inv
|
|
; GFX11-CU-NEXT: buffer_gl0_inv
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: agent_acquire_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: agent_acquire_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: agent_acquire_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("agent") acquire, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @agent_release_fence() {
|
|
; GFX6-LABEL: agent_release_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: agent_release_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: agent_release_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: agent_release_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: agent_release_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: agent_release_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: agent_release_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: agent_release_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_wbl2 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: agent_release_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: buffer_wbl2 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: agent_release_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: agent_release_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: agent_release_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: agent_release_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: agent_release_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_wb scope:SCOPE_DEV
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("agent") release, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @agent_acq_rel_fence() {
|
|
; GFX6-LABEL: agent_acq_rel_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_wbinvl1
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: agent_acq_rel_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: buffer_wbinvl1_vol
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: agent_acq_rel_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl1_inv
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: agent_acq_rel_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: buffer_gl1_inv
|
|
; GFX10-CU-NEXT: buffer_gl0_inv
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: agent_acq_rel_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: agent_acq_rel_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: agent_acq_rel_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: agent_acq_rel_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_wbl2 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_inv sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: agent_acq_rel_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: buffer_wbl2 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc1
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: agent_acq_rel_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl1_inv
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: agent_acq_rel_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: buffer_gl1_inv
|
|
; GFX11-CU-NEXT: buffer_gl0_inv
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: agent_acq_rel_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: agent_acq_rel_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: agent_acq_rel_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_wb scope:SCOPE_DEV
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("agent") acq_rel, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @agent_seq_cst_fence() {
|
|
; GFX6-LABEL: agent_seq_cst_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_wbinvl1
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: agent_seq_cst_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: buffer_wbinvl1_vol
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: agent_seq_cst_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl1_inv
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: agent_seq_cst_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: buffer_gl1_inv
|
|
; GFX10-CU-NEXT: buffer_gl0_inv
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: agent_seq_cst_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: agent_seq_cst_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: agent_seq_cst_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: agent_seq_cst_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_wbl2 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_inv sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: agent_seq_cst_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: buffer_wbl2 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc1
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: agent_seq_cst_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl1_inv
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: agent_seq_cst_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: buffer_gl1_inv
|
|
; GFX11-CU-NEXT: buffer_gl0_inv
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: agent_seq_cst_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: agent_seq_cst_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: agent_seq_cst_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_wb scope:SCOPE_DEV
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("agent") seq_cst, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @agent_one_as_acquire_fence() {
|
|
; GFX6-LABEL: agent_one_as_acquire_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_wbinvl1
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: agent_one_as_acquire_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: buffer_wbinvl1_vol
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: agent_one_as_acquire_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl1_inv
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: agent_one_as_acquire_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: buffer_gl1_inv
|
|
; GFX10-CU-NEXT: buffer_gl0_inv
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: agent_one_as_acquire_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: agent_one_as_acquire_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: agent_one_as_acquire_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: agent_one_as_acquire_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_inv sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: agent_one_as_acquire_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc1
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: agent_one_as_acquire_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl1_inv
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: agent_one_as_acquire_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: buffer_gl1_inv
|
|
; GFX11-CU-NEXT: buffer_gl0_inv
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: agent_one_as_acquire_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: agent_one_as_acquire_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: agent_one_as_acquire_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("agent-one-as") acquire, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @agent_one_as_release_fence() {
|
|
; GFX6-LABEL: agent_one_as_release_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: agent_one_as_release_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: agent_one_as_release_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: agent_one_as_release_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: agent_one_as_release_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: agent_one_as_release_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: agent_one_as_release_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: agent_one_as_release_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_wbl2 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: agent_one_as_release_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: buffer_wbl2 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: agent_one_as_release_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: agent_one_as_release_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: agent_one_as_release_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: agent_one_as_release_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: agent_one_as_release_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_wb scope:SCOPE_DEV
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("agent-one-as") release, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @agent_one_as_acq_rel_fence() {
|
|
; GFX6-LABEL: agent_one_as_acq_rel_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_wbinvl1
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: agent_one_as_acq_rel_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: buffer_wbinvl1_vol
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: agent_one_as_acq_rel_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl1_inv
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: agent_one_as_acq_rel_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: buffer_gl1_inv
|
|
; GFX10-CU-NEXT: buffer_gl0_inv
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: agent_one_as_acq_rel_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: agent_one_as_acq_rel_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: agent_one_as_acq_rel_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: agent_one_as_acq_rel_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_wbl2 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_inv sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: agent_one_as_acq_rel_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: buffer_wbl2 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc1
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: agent_one_as_acq_rel_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl1_inv
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: agent_one_as_acq_rel_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: buffer_gl1_inv
|
|
; GFX11-CU-NEXT: buffer_gl0_inv
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: agent_one_as_acq_rel_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: agent_one_as_acq_rel_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: agent_one_as_acq_rel_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_wb scope:SCOPE_DEV
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("agent-one-as") acq_rel, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @agent_one_as_seq_cst_fence() {
|
|
; GFX6-LABEL: agent_one_as_seq_cst_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_wbinvl1
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: agent_one_as_seq_cst_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: buffer_wbinvl1_vol
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: agent_one_as_seq_cst_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl1_inv
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: agent_one_as_seq_cst_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: buffer_gl1_inv
|
|
; GFX10-CU-NEXT: buffer_gl0_inv
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: agent_one_as_seq_cst_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: agent_one_as_seq_cst_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: agent_one_as_seq_cst_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: agent_one_as_seq_cst_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_wbl2 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_inv sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: agent_one_as_seq_cst_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: buffer_wbl2 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc1
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: agent_one_as_seq_cst_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl1_inv
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: agent_one_as_seq_cst_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: buffer_gl1_inv
|
|
; GFX11-CU-NEXT: buffer_gl0_inv
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: agent_one_as_seq_cst_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: agent_one_as_seq_cst_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: agent_one_as_seq_cst_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_wb scope:SCOPE_DEV
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_inv scope:SCOPE_DEV
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("agent-one-as") seq_cst, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @system_acquire_fence() {
|
|
; GFX6-LABEL: system_acquire_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_wbinvl1
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: system_acquire_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: buffer_wbinvl1_vol
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: system_acquire_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl1_inv
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: system_acquire_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: buffer_gl1_inv
|
|
; GFX10-CU-NEXT: buffer_gl0_inv
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: system_acquire_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: system_acquire_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_invl2
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: system_acquire_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_invl2
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: system_acquire_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_inv sc0 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: system_acquire_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc0 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: system_acquire_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl1_inv
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: system_acquire_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: buffer_gl1_inv
|
|
; GFX11-CU-NEXT: buffer_gl0_inv
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: system_acquire_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: system_acquire_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: system_acquire_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence acquire, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @system_release_fence() {
|
|
; GFX6-LABEL: system_release_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: system_release_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: system_release_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: system_release_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: system_release_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: system_release_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbl2
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: system_release_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbl2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: system_release_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_wbl2 sc0 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: system_release_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: buffer_wbl2 sc0 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: system_release_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: system_release_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: system_release_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: system_release_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: system_release_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence release, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @system_acq_rel_fence() {
|
|
; GFX6-LABEL: system_acq_rel_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_wbinvl1
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: system_acq_rel_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: buffer_wbinvl1_vol
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: system_acq_rel_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl1_inv
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: system_acq_rel_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: buffer_gl1_inv
|
|
; GFX10-CU-NEXT: buffer_gl0_inv
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: system_acq_rel_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: system_acq_rel_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbl2
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_invl2
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: system_acq_rel_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbl2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_invl2
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: system_acq_rel_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_wbl2 sc0 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_inv sc0 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: system_acq_rel_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: buffer_wbl2 sc0 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc0 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: system_acq_rel_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl1_inv
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: system_acq_rel_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: buffer_gl1_inv
|
|
; GFX11-CU-NEXT: buffer_gl0_inv
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: system_acq_rel_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: system_acq_rel_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: system_acq_rel_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence acq_rel, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @system_seq_cst_fence() {
|
|
; GFX6-LABEL: system_seq_cst_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_wbinvl1
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: system_seq_cst_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: buffer_wbinvl1_vol
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: system_seq_cst_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl1_inv
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: system_seq_cst_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: buffer_gl1_inv
|
|
; GFX10-CU-NEXT: buffer_gl0_inv
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: system_seq_cst_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: system_seq_cst_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbl2
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_invl2
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: system_seq_cst_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbl2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_invl2
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: system_seq_cst_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_wbl2 sc0 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_inv sc0 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: system_seq_cst_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: buffer_wbl2 sc0 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc0 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: system_seq_cst_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl1_inv
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: system_seq_cst_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: buffer_gl1_inv
|
|
; GFX11-CU-NEXT: buffer_gl0_inv
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: system_seq_cst_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: system_seq_cst_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: system_seq_cst_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence seq_cst, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @system_one_as_acquire_fence() {
|
|
; GFX6-LABEL: system_one_as_acquire_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_wbinvl1
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: system_one_as_acquire_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: buffer_wbinvl1_vol
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: system_one_as_acquire_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl1_inv
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: system_one_as_acquire_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: buffer_gl1_inv
|
|
; GFX10-CU-NEXT: buffer_gl0_inv
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: system_one_as_acquire_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: system_one_as_acquire_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_invl2
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: system_one_as_acquire_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_invl2
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: system_one_as_acquire_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_inv sc0 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: system_one_as_acquire_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc0 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: system_one_as_acquire_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl1_inv
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: system_one_as_acquire_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: buffer_gl1_inv
|
|
; GFX11-CU-NEXT: buffer_gl0_inv
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: system_one_as_acquire_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: system_one_as_acquire_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: system_one_as_acquire_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("one-as") acquire, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @system_one_as_release_fence() {
|
|
; GFX6-LABEL: system_one_as_release_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: system_one_as_release_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: system_one_as_release_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: system_one_as_release_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: system_one_as_release_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: system_one_as_release_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbl2
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: system_one_as_release_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbl2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: system_one_as_release_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_wbl2 sc0 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: system_one_as_release_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: buffer_wbl2 sc0 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: system_one_as_release_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: system_one_as_release_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: system_one_as_release_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: system_one_as_release_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: system_one_as_release_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("one-as") release, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @system_one_as_acq_rel_fence() {
|
|
; GFX6-LABEL: system_one_as_acq_rel_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_wbinvl1
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: system_one_as_acq_rel_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: buffer_wbinvl1_vol
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: system_one_as_acq_rel_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl1_inv
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: system_one_as_acq_rel_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: buffer_gl1_inv
|
|
; GFX10-CU-NEXT: buffer_gl0_inv
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: system_one_as_acq_rel_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: system_one_as_acq_rel_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbl2
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_invl2
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: system_one_as_acq_rel_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbl2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_invl2
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: system_one_as_acq_rel_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_wbl2 sc0 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_inv sc0 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: system_one_as_acq_rel_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: buffer_wbl2 sc0 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc0 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: system_one_as_acq_rel_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl1_inv
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: system_one_as_acq_rel_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: buffer_gl1_inv
|
|
; GFX11-CU-NEXT: buffer_gl0_inv
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: system_one_as_acq_rel_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: system_one_as_acq_rel_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: system_one_as_acq_rel_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("one-as") acq_rel, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @system_one_as_seq_cst_fence() {
|
|
; GFX6-LABEL: system_one_as_seq_cst_fence:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_wbinvl1
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: system_one_as_seq_cst_fence:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: buffer_wbinvl1_vol
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: system_one_as_seq_cst_fence:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl1_inv
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: system_one_as_seq_cst_fence:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-CU-NEXT: buffer_gl1_inv
|
|
; GFX10-CU-NEXT: buffer_gl0_inv
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: system_one_as_seq_cst_fence:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: system_one_as_seq_cst_fence:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbl2
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_invl2
|
|
; GFX90A-NOTTGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: system_one_as_seq_cst_fence:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbl2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_invl2
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-NOTTGSPLIT-LABEL: system_one_as_seq_cst_fence:
|
|
; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_wbl2 sc0 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-NOTTGSPLIT-NEXT: buffer_inv sc0 sc1
|
|
; GFX942-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX942-TGSPLIT-LABEL: system_one_as_seq_cst_fence:
|
|
; GFX942-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX942-TGSPLIT-NEXT: buffer_wbl2 sc0 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX942-TGSPLIT-NEXT: buffer_inv sc0 sc1
|
|
; GFX942-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX11-WGP-LABEL: system_one_as_seq_cst_fence:
|
|
; GFX11-WGP: ; %bb.0: ; %entry
|
|
; GFX11-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-WGP-NEXT: buffer_gl1_inv
|
|
; GFX11-WGP-NEXT: buffer_gl0_inv
|
|
; GFX11-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX11-CU-LABEL: system_one_as_seq_cst_fence:
|
|
; GFX11-CU: ; %bb.0: ; %entry
|
|
; GFX11-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX11-CU-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX11-CU-NEXT: buffer_gl1_inv
|
|
; GFX11-CU-NEXT: buffer_gl0_inv
|
|
; GFX11-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX12-WGP-LABEL: system_one_as_seq_cst_fence:
|
|
; GFX12-WGP: ; %bb.0: ; %entry
|
|
; GFX12-WGP-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-WGP-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX12-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX12-CU-LABEL: system_one_as_seq_cst_fence:
|
|
; GFX12-CU: ; %bb.0: ; %entry
|
|
; GFX12-CU-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
|
|
; GFX12-CU-NEXT: s_wait_storecnt 0x0
|
|
; GFX12-CU-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX12-CU-NEXT: s_endpgm
|
|
;
|
|
; GFX1250-LABEL: system_one_as_seq_cst_fence:
|
|
; GFX1250: ; %bb.0: ; %entry
|
|
; GFX1250-NEXT: global_prefetch_b8 v0, s[0:1] scope:SCOPE_SE
|
|
; GFX1250-NEXT: v_nop
|
|
; GFX1250-NEXT: s_setreg_imm32_b32 hwreg(HW_REG_WAVE_MODE, 25, 1), 1 ; msbs: dst=0 src0=0 src1=0 src2=0
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_wb scope:SCOPE_SYS
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_wait_storecnt 0x0
|
|
; GFX1250-NEXT: global_inv scope:SCOPE_SYS
|
|
; GFX1250-NEXT: s_wait_loadcnt 0x0
|
|
; GFX1250-NEXT: s_endpgm
|
|
entry:
|
|
fence syncscope("one-as") seq_cst, !mmra !{!"amdgpu-synchronize-as", !"global"}
|
|
ret void
|
|
}
|