Skip to content

[AMDGPU] Document & Finalize GFX12 Memory Model #98599

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Sep 9, 2024
Merged

[AMDGPU] Document & Finalize GFX12 Memory Model #98599

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
6509556
[AMDGPU] Document GFX12 Memory Model
Pierre-vh Jul 12, 2024
3734fe2
L1 is now a buffer + other small fix
Pierre-vh Jul 19, 2024
ae1aa5b
Try to make the synscope table clearer
Pierre-vh Aug 2, 2024
6ccf48a
Fix waitcnts
Pierre-vh Aug 19, 2024
0ade58a
additional fixes
Pierre-vh Aug 19, 2024
d880449
Add code changes
Pierre-vh Aug 19, 2024
e89e94b
Added note about WB emission
Pierre-vh Sep 4, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2,241 changes: 2,241 additions & 0 deletions llvm/docs/AMDGPUUsage.rst
View file
Open in desktop

Large diffs are not rendered by default.

185 changes: 98 additions & 87 deletions llvm/lib/Target/AMDGPU/SIMemoryLegalizer.cpp
View file
Open in desktop

Large diffs are not rendered by default.

20 changes: 0 additions & 20 deletions llvm/test/CodeGen/AMDGPU/memory-legalizer-fence-mmra-global.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,8 +70,6 @@ define amdgpu_kernel void @workgroup_acquire_fence() {
;
; GFX12-WGP-LABEL: workgroup_acquire_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
Expand Down Expand Up @@ -356,8 +354,6 @@ define amdgpu_kernel void @workgroup_one_as_acquire_fence() {
;
; GFX12-WGP-LABEL: workgroup_one_as_acquire_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
Expand Down Expand Up @@ -661,17 +657,13 @@ define amdgpu_kernel void @agent_acquire_fence() {
;
; GFX12-WGP-LABEL: agent_acquire_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_acquire_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
Expand Down Expand Up @@ -1041,17 +1033,13 @@ define amdgpu_kernel void @agent_one_as_acquire_fence() {
;
; GFX12-WGP-LABEL: agent_one_as_acquire_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_acquire_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
Expand Down Expand Up @@ -1423,17 +1411,13 @@ define amdgpu_kernel void @system_acquire_fence() {
;
; GFX12-WGP-LABEL: system_acquire_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_SYS
; GFX12-WGP-NEXT: s_endpgm
;
; GFX12-CU-LABEL: system_acquire_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_SYS
Expand Down Expand Up @@ -1815,17 +1799,13 @@ define amdgpu_kernel void @system_one_as_acquire_fence() {
;
; GFX12-WGP-LABEL: system_one_as_acquire_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_SYS
; GFX12-WGP-NEXT: s_endpgm
;
; GFX12-CU-LABEL: system_one_as_acquire_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_SYS
Expand Down
20 changes: 0 additions & 20 deletions llvm/test/CodeGen/AMDGPU/memory-legalizer-fence.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -989,8 +989,6 @@ define amdgpu_kernel void @workgroup_acquire_fence() {
;
; GFX12-WGP-LABEL: workgroup_acquire_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_storecnt 0x0
; GFX12-WGP-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-WGP-NEXT: global_inv scope:SCOPE_SE
Expand Down Expand Up @@ -1300,8 +1298,6 @@ define amdgpu_kernel void @workgroup_one_as_acquire_fence() {
;
; GFX12-WGP-LABEL: workgroup_one_as_acquire_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
Expand Down Expand Up @@ -1605,17 +1601,13 @@ define amdgpu_kernel void @agent_acquire_fence() {
;
; GFX12-WGP-LABEL: agent_acquire_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_storecnt 0x0
; GFX12-WGP-NEXT: s_wait_loadcnt_dscnt 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_bvhcnt 0x0
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
; GFX12-CU-NEXT: s_wait_storecnt 0x0
; GFX12-CU-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
Expand Down Expand Up @@ -1985,17 +1977,13 @@ define amdgpu_kernel void @agent_one_as_acquire_fence() {
;
; GFX12-WGP-LABEL: agent_one_as_acquire_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_acquire_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
Expand Down Expand Up @@ -2367,17 +2355,13 @@ define amdgpu_kernel void @system_acquire_fence() {
;
; GFX12-WGP-LABEL: system_acquire_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_storecnt 0x0
; GFX12-WGP-NEXT: s_wait_loadcnt_dscnt 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_bvhcnt 0x0
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
; GFX12-CU-NEXT: s_wait_storecnt 0x0
; GFX12-CU-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-CU-NEXT: global_inv scope:SCOPE_SYS
Expand Down Expand Up @@ -2759,17 +2743,13 @@ define amdgpu_kernel void @system_one_as_acquire_fence() {
;
; GFX12-WGP-LABEL: system_one_as_acquire_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_SYS
; GFX12-WGP-NEXT: s_endpgm
;
; GFX12-CU-LABEL: system_one_as_acquire_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_SYS
Expand Down
40 changes: 0 additions & 40 deletions llvm/test/CodeGen/AMDGPU/memory-legalizer-flat-agent.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -553,8 +553,6 @@ define amdgpu_kernel void @flat_agent_acquire_load(
; GFX12-WGP-NEXT: v_mov_b32_e32 v0, s2
; GFX12-WGP-NEXT: v_mov_b32_e32 v1, s3
; GFX12-WGP-NEXT: flat_load_b32 v2, v[0:1] scope:SCOPE_DEV
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
; GFX12-WGP-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-WGP-NEXT: global_inv scope:SCOPE_DEV
; GFX12-WGP-NEXT: v_mov_b32_e32 v0, s0
Expand All @@ -571,8 +569,6 @@ define amdgpu_kernel void @flat_agent_acquire_load(
; GFX12-CU-NEXT: v_mov_b32_e32 v0, s2
; GFX12-CU-NEXT: v_mov_b32_e32 v1, s3
; GFX12-CU-NEXT: flat_load_b32 v2, v[0:1] scope:SCOPE_DEV
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
; GFX12-CU-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
; GFX12-CU-NEXT: v_mov_b32_e32 v0, s0
Expand Down Expand Up @@ -2526,8 +2522,6 @@ define amdgpu_kernel void @flat_agent_acquire_ret_atomicrmw(
; GFX12-WGP-NEXT: v_mov_b32_e32 v1, s1
; GFX12-WGP-NEXT: v_mov_b32_e32 v2, s2
; GFX12-WGP-NEXT: flat_atomic_swap_b32 v2, v[0:1], v2 th:TH_ATOMIC_RETURN scope:SCOPE_DEV
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
; GFX12-WGP-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-WGP-NEXT: global_inv scope:SCOPE_DEV
; GFX12-WGP-NEXT: v_mov_b32_e32 v0, s0
Expand All @@ -2544,8 +2538,6 @@ define amdgpu_kernel void @flat_agent_acquire_ret_atomicrmw(
; GFX12-CU-NEXT: v_mov_b32_e32 v1, s1
; GFX12-CU-NEXT: v_mov_b32_e32 v2, s2
; GFX12-CU-NEXT: flat_atomic_swap_b32 v2, v[0:1], v2 th:TH_ATOMIC_RETURN scope:SCOPE_DEV
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
; GFX12-CU-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
; GFX12-CU-NEXT: v_mov_b32_e32 v0, s0
Expand Down Expand Up @@ -7698,8 +7690,6 @@ define amdgpu_kernel void @flat_agent_acquire_monotonic_ret_cmpxchg(
; GFX12-WGP-NEXT: v_mov_b32_e32 v0, s0
; GFX12-WGP-NEXT: v_mov_b32_e32 v1, s1
; GFX12-WGP-NEXT: flat_atomic_cmpswap_b32 v2, v[0:1], v[2:3] offset:16 th:TH_ATOMIC_RETURN scope:SCOPE_DEV
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
; GFX12-WGP-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-WGP-NEXT: global_inv scope:SCOPE_DEV
; GFX12-WGP-NEXT: v_mov_b32_e32 v0, s0
Expand All @@ -7721,8 +7711,6 @@ define amdgpu_kernel void @flat_agent_acquire_monotonic_ret_cmpxchg(
; GFX12-CU-NEXT: v_mov_b32_e32 v0, s0
; GFX12-CU-NEXT: v_mov_b32_e32 v1, s1
; GFX12-CU-NEXT: flat_atomic_cmpswap_b32 v2, v[0:1], v[2:3] offset:16 th:TH_ATOMIC_RETURN scope:SCOPE_DEV
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
; GFX12-CU-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
; GFX12-CU-NEXT: v_mov_b32_e32 v0, s0
Expand Down Expand Up @@ -9217,8 +9205,6 @@ define amdgpu_kernel void @flat_agent_acquire_acquire_ret_cmpxchg(
; GFX12-WGP-NEXT: v_mov_b32_e32 v0, s0
; GFX12-WGP-NEXT: v_mov_b32_e32 v1, s1
; GFX12-WGP-NEXT: flat_atomic_cmpswap_b32 v2, v[0:1], v[2:3] offset:16 th:TH_ATOMIC_RETURN scope:SCOPE_DEV
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
; GFX12-WGP-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-WGP-NEXT: global_inv scope:SCOPE_DEV
; GFX12-WGP-NEXT: v_mov_b32_e32 v0, s0
Expand All @@ -9240,8 +9226,6 @@ define amdgpu_kernel void @flat_agent_acquire_acquire_ret_cmpxchg(
; GFX12-CU-NEXT: v_mov_b32_e32 v0, s0
; GFX12-CU-NEXT: v_mov_b32_e32 v1, s1
; GFX12-CU-NEXT: flat_atomic_cmpswap_b32 v2, v[0:1], v[2:3] offset:16 th:TH_ATOMIC_RETURN scope:SCOPE_DEV
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
; GFX12-CU-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
; GFX12-CU-NEXT: v_mov_b32_e32 v0, s0
Expand Down Expand Up @@ -10802,8 +10786,6 @@ define amdgpu_kernel void @flat_agent_acquire_seq_cst_ret_cmpxchg(
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
; GFX12-WGP-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-WGP-NEXT: flat_atomic_cmpswap_b32 v2, v[0:1], v[2:3] offset:16 th:TH_ATOMIC_RETURN scope:SCOPE_DEV
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
; GFX12-WGP-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-WGP-NEXT: global_inv scope:SCOPE_DEV
; GFX12-WGP-NEXT: v_mov_b32_e32 v0, s0
Expand All @@ -10830,8 +10812,6 @@ define amdgpu_kernel void @flat_agent_acquire_seq_cst_ret_cmpxchg(
; GFX12-CU-NEXT: s_wait_storecnt 0x0
; GFX12-CU-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-CU-NEXT: flat_atomic_cmpswap_b32 v2, v[0:1], v[2:3] offset:16 th:TH_ATOMIC_RETURN scope:SCOPE_DEV
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
; GFX12-CU-NEXT: s_wait_loadcnt_dscnt 0x0
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
; GFX12-CU-NEXT: v_mov_b32_e32 v0, s0
Expand Down Expand Up @@ -12350,8 +12330,6 @@ define amdgpu_kernel void @flat_agent_one_as_acquire_load(
; GFX12-WGP-NEXT: v_mov_b32_e32 v0, s2
; GFX12-WGP-NEXT: v_mov_b32_e32 v1, s3
; GFX12-WGP-NEXT: flat_load_b32 v2, v[0:1] scope:SCOPE_DEV
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
; GFX12-WGP-NEXT: global_inv scope:SCOPE_DEV
; GFX12-WGP-NEXT: v_mov_b32_e32 v0, s0
Expand All @@ -12369,8 +12347,6 @@ define amdgpu_kernel void @flat_agent_one_as_acquire_load(
; GFX12-CU-NEXT: v_mov_b32_e32 v0, s2
; GFX12-CU-NEXT: v_mov_b32_e32 v1, s3
; GFX12-CU-NEXT: flat_load_b32 v2, v[0:1] scope:SCOPE_DEV
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
; GFX12-CU-NEXT: v_mov_b32_e32 v0, s0
Expand Down Expand Up @@ -14331,8 +14307,6 @@ define amdgpu_kernel void @flat_agent_one_as_acquire_ret_atomicrmw(
; GFX12-WGP-NEXT: v_mov_b32_e32 v1, s1
; GFX12-WGP-NEXT: v_mov_b32_e32 v2, s2
; GFX12-WGP-NEXT: flat_atomic_swap_b32 v2, v[0:1], v2 th:TH_ATOMIC_RETURN scope:SCOPE_DEV
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
; GFX12-WGP-NEXT: global_inv scope:SCOPE_DEV
; GFX12-WGP-NEXT: v_mov_b32_e32 v0, s0
Expand All @@ -14350,8 +14324,6 @@ define amdgpu_kernel void @flat_agent_one_as_acquire_ret_atomicrmw(
; GFX12-CU-NEXT: v_mov_b32_e32 v1, s1
; GFX12-CU-NEXT: v_mov_b32_e32 v2, s2
; GFX12-CU-NEXT: flat_atomic_swap_b32 v2, v[0:1], v2 th:TH_ATOMIC_RETURN scope:SCOPE_DEV
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
; GFX12-CU-NEXT: v_mov_b32_e32 v0, s0
Expand Down Expand Up @@ -19481,8 +19453,6 @@ define amdgpu_kernel void @flat_agent_one_as_acquire_monotonic_ret_cmpxchg(
; GFX12-WGP-NEXT: v_mov_b32_e32 v0, s0
; GFX12-WGP-NEXT: v_mov_b32_e32 v1, s1
; GFX12-WGP-NEXT: flat_atomic_cmpswap_b32 v2, v[0:1], v[2:3] offset:16 th:TH_ATOMIC_RETURN scope:SCOPE_DEV
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
; GFX12-WGP-NEXT: global_inv scope:SCOPE_DEV
; GFX12-WGP-NEXT: v_mov_b32_e32 v0, s0
Expand All @@ -19505,8 +19475,6 @@ define amdgpu_kernel void @flat_agent_one_as_acquire_monotonic_ret_cmpxchg(
; GFX12-CU-NEXT: v_mov_b32_e32 v0, s0
; GFX12-CU-NEXT: v_mov_b32_e32 v1, s1
; GFX12-CU-NEXT: flat_atomic_cmpswap_b32 v2, v[0:1], v[2:3] offset:16 th:TH_ATOMIC_RETURN scope:SCOPE_DEV
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
; GFX12-CU-NEXT: v_mov_b32_e32 v0, s0
Expand Down Expand Up @@ -21040,8 +21008,6 @@ define amdgpu_kernel void @flat_agent_one_as_acquire_acquire_ret_cmpxchg(
; GFX12-WGP-NEXT: v_mov_b32_e32 v0, s0
; GFX12-WGP-NEXT: v_mov_b32_e32 v1, s1
; GFX12-WGP-NEXT: flat_atomic_cmpswap_b32 v2, v[0:1], v[2:3] offset:16 th:TH_ATOMIC_RETURN scope:SCOPE_DEV
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
; GFX12-WGP-NEXT: global_inv scope:SCOPE_DEV
; GFX12-WGP-NEXT: v_mov_b32_e32 v0, s0
Expand All @@ -21064,8 +21030,6 @@ define amdgpu_kernel void @flat_agent_one_as_acquire_acquire_ret_cmpxchg(
; GFX12-CU-NEXT: v_mov_b32_e32 v0, s0
; GFX12-CU-NEXT: v_mov_b32_e32 v1, s1
; GFX12-CU-NEXT: flat_atomic_cmpswap_b32 v2, v[0:1], v[2:3] offset:16 th:TH_ATOMIC_RETURN scope:SCOPE_DEV
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
; GFX12-CU-NEXT: v_mov_b32_e32 v0, s0
Expand Down Expand Up @@ -22675,8 +22639,6 @@ define amdgpu_kernel void @flat_agent_one_as_acquire_seq_cst_ret_cmpxchg(
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
; GFX12-WGP-NEXT: s_wait_storecnt 0x0
; GFX12-WGP-NEXT: flat_atomic_cmpswap_b32 v2, v[0:1], v[2:3] offset:16 th:TH_ATOMIC_RETURN scope:SCOPE_DEV
; GFX12-WGP-NEXT: s_wait_bvhcnt 0x0
; GFX12-WGP-NEXT: s_wait_samplecnt 0x0
; GFX12-WGP-NEXT: s_wait_loadcnt 0x0
; GFX12-WGP-NEXT: global_inv scope:SCOPE_DEV
; GFX12-WGP-NEXT: v_mov_b32_e32 v0, s0
Expand Down Expand Up @@ -22704,8 +22666,6 @@ define amdgpu_kernel void @flat_agent_one_as_acquire_seq_cst_ret_cmpxchg(
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
; GFX12-CU-NEXT: s_wait_storecnt 0x0
; GFX12-CU-NEXT: flat_atomic_cmpswap_b32 v2, v[0:1], v[2:3] offset:16 th:TH_ATOMIC_RETURN scope:SCOPE_DEV
; GFX12-CU-NEXT: s_wait_bvhcnt 0x0
; GFX12-CU-NEXT: s_wait_samplecnt 0x0
; GFX12-CU-NEXT: s_wait_loadcnt 0x0
; GFX12-CU-NEXT: global_inv scope:SCOPE_DEV
; GFX12-CU-NEXT: v_mov_b32_e32 v0, s0
Expand Down
Loading
Loading