[llvm] [AMDGPU][AtomicExpand] Use full flat emulation if feasible (PR #142859)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Jun 4 14:32:36 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Shilei Tian (shiltian)
<details>
<summary>Changes</summary>
If a target supports f64 atomic add instruction, we can also use full flat
emulation.
---
Patch is 109.78 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/142859.diff
7 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/SIISelLowering.cpp (+5-3)
- (modified) llvm/test/CodeGen/AMDGPU/atomicrmw-expand.ll (+105-47)
- (modified) llvm/test/CodeGen/AMDGPU/flat-atomicrmw-fadd.ll (+348-108)
- (modified) llvm/test/CodeGen/AMDGPU/gep-const-address-space.ll (+31-12)
- (modified) llvm/test/CodeGen/AMDGPU/infer-addrspace-flat-atomic.ll (+29-10)
- (modified) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-rmw-fadd.ll (+606-97)
- (modified) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomicrmw-flat-noalias-addrspace.ll (+22-6)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
index 1957e442dbabb..7575510dd7f98 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -17541,9 +17541,11 @@ void SITargetLowering::emitExpandAtomicAddrSpacePredicate(
// where we only insert a check for private and still use the flat instruction
// for global and shared.
- bool FullFlatEmulation = RMW && RMW->getOperation() == AtomicRMWInst::FAdd &&
- Subtarget->hasAtomicFaddInsts() &&
- RMW->getType()->isFloatTy();
+ bool FullFlatEmulation =
+ RMW && RMW->getOperation() == AtomicRMWInst::FAdd &&
+ ((Subtarget->hasAtomicFaddInsts() && RMW->getType()->isFloatTy()) ||
+ (Subtarget->hasFlatBufferGlobalAtomicFaddF64Inst() &&
+ RMW->getType()->isDoubleTy()));
// If the return value isn't used, do not introduce a false use in the phi.
bool ReturnValueIsUsed = !AI->use_empty();
diff --git a/llvm/test/CodeGen/AMDGPU/atomicrmw-expand.ll b/llvm/test/CodeGen/AMDGPU/atomicrmw-expand.ll
index 1669909e96eb1..231f53d7f3710 100644
--- a/llvm/test/CodeGen/AMDGPU/atomicrmw-expand.ll
+++ b/llvm/test/CodeGen/AMDGPU/atomicrmw-expand.ll
@@ -799,6 +799,31 @@ define double @optnone_atomicrmw_fadd_f64_expand(double %val) #1 {
; GFX90A-LABEL: optnone_atomicrmw_fadd_f64_expand:
; GFX90A: ; %bb.0:
; GFX90A-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX90A-NEXT: s_mov_b64 s[4:5], src_shared_base
+; GFX90A-NEXT: s_mov_b32 s6, 32
+; GFX90A-NEXT: s_lshr_b64 s[4:5], s[4:5], s6
+; GFX90A-NEXT: s_getpc_b64 s[6:7]
+; GFX90A-NEXT: s_add_u32 s6, s6, global at rel32@lo+4
+; GFX90A-NEXT: s_addc_u32 s7, s7, global at rel32@hi+12
+; GFX90A-NEXT: s_cmp_eq_u32 s7, s4
+; GFX90A-NEXT: s_cselect_b64 s[4:5], -1, 0
+; GFX90A-NEXT: v_cndmask_b32_e64 v2, 0, 1, s[4:5]
+; GFX90A-NEXT: s_mov_b64 s[4:5], -1
+; GFX90A-NEXT: s_mov_b32 s6, 1
+; GFX90A-NEXT: v_cmp_ne_u32_e64 s[6:7], v2, s6
+; GFX90A-NEXT: s_and_b64 vcc, exec, s[6:7]
+; GFX90A-NEXT: ; implicit-def: $vgpr2_vgpr3
+; GFX90A-NEXT: s_cbranch_vccnz .LBB5_3
+; GFX90A-NEXT: .LBB5_1: ; %Flow4
+; GFX90A-NEXT: v_cndmask_b32_e64 v4, 0, 1, s[4:5]
+; GFX90A-NEXT: s_mov_b32 s4, 1
+; GFX90A-NEXT: v_cmp_ne_u32_e64 s[4:5], v4, s4
+; GFX90A-NEXT: s_and_b64 vcc, exec, s[4:5]
+; GFX90A-NEXT: s_cbranch_vccnz .LBB5_10
+; GFX90A-NEXT: ; %bb.2: ; %atomicrmw.shared
+; GFX90A-NEXT: ds_add_rtn_f64 v[2:3], v0, v[0:1]
+; GFX90A-NEXT: s_branch .LBB5_10
+; GFX90A-NEXT: .LBB5_3: ; %atomicrmw.check.private
; GFX90A-NEXT: s_mov_b64 s[4:5], src_private_base
; GFX90A-NEXT: s_mov_b32 s6, 32
; GFX90A-NEXT: s_lshr_b64 s[4:5], s[4:5], s6
@@ -813,50 +838,54 @@ define double @optnone_atomicrmw_fadd_f64_expand(double %val) #1 {
; GFX90A-NEXT: v_cmp_ne_u32_e64 s[6:7], v2, s6
; GFX90A-NEXT: s_and_b64 vcc, exec, s[6:7]
; GFX90A-NEXT: ; implicit-def: $vgpr2_vgpr3
-; GFX90A-NEXT: s_cbranch_vccnz .LBB5_2
-; GFX90A-NEXT: s_branch .LBB5_3
-; GFX90A-NEXT: .LBB5_1: ; %atomicrmw.private
+; GFX90A-NEXT: s_cbranch_vccnz .LBB5_5
+; GFX90A-NEXT: s_branch .LBB5_6
+; GFX90A-NEXT: .LBB5_4: ; %atomicrmw.private
; GFX90A-NEXT: buffer_load_dword v2, v0, s[0:3], 0 offen
; GFX90A-NEXT: s_waitcnt vmcnt(0)
; GFX90A-NEXT: v_mov_b32_e32 v3, v2
-; GFX90A-NEXT: v_add_f64 v[0:1], v[2:3], v[0:1]
-; GFX90A-NEXT: buffer_store_dword v1, v0, s[0:3], 0 offen
-; GFX90A-NEXT: buffer_store_dword v0, v0, s[0:3], 0 offen
-; GFX90A-NEXT: s_branch .LBB5_6
-; GFX90A-NEXT: .LBB5_2: ; %atomicrmw.global
+; GFX90A-NEXT: v_add_f64 v[4:5], v[2:3], v[0:1]
+; GFX90A-NEXT: buffer_store_dword v5, v0, s[0:3], 0 offen
+; GFX90A-NEXT: buffer_store_dword v4, v0, s[0:3], 0 offen
+; GFX90A-NEXT: s_branch .LBB5_9
+; GFX90A-NEXT: .LBB5_5: ; %atomicrmw.global
+; GFX90A-NEXT: v_mov_b32_e32 v2, 0
; GFX90A-NEXT: s_getpc_b64 s[4:5]
; GFX90A-NEXT: s_add_u32 s4, s4, global at rel32@lo+4
; GFX90A-NEXT: s_addc_u32 s5, s5, global at rel32@hi+12
-; GFX90A-NEXT: v_pk_mov_b32 v[2:3], s[4:5], s[4:5] op_sel:[0,1]
-; GFX90A-NEXT: flat_load_dwordx2 v[2:3], v[2:3]
+; GFX90A-NEXT: global_load_dwordx2 v[2:3], v2, s[4:5]
; GFX90A-NEXT: s_mov_b64 s[4:5], 0
-; GFX90A-NEXT: s_branch .LBB5_4
-; GFX90A-NEXT: .LBB5_3: ; %Flow
+; GFX90A-NEXT: s_branch .LBB5_7
+; GFX90A-NEXT: .LBB5_6: ; %Flow
; GFX90A-NEXT: s_and_b64 vcc, exec, s[4:5]
-; GFX90A-NEXT: s_cbranch_vccnz .LBB5_1
-; GFX90A-NEXT: s_branch .LBB5_6
-; GFX90A-NEXT: .LBB5_4: ; %atomicrmw.start
+; GFX90A-NEXT: s_cbranch_vccnz .LBB5_4
+; GFX90A-NEXT: s_branch .LBB5_9
+; GFX90A-NEXT: .LBB5_7: ; %atomicrmw.start
; GFX90A-NEXT: ; =>This Inner Loop Header: Depth=1
-; GFX90A-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX90A-NEXT: s_waitcnt vmcnt(0)
; GFX90A-NEXT: v_pk_mov_b32 v[4:5], v[2:3], v[2:3] op_sel:[0,1]
; GFX90A-NEXT: v_add_f64 v[2:3], v[4:5], v[0:1]
; GFX90A-NEXT: s_getpc_b64 s[6:7]
; GFX90A-NEXT: s_add_u32 s6, s6, global at rel32@lo+4
; GFX90A-NEXT: s_addc_u32 s7, s7, global at rel32@hi+12
-; GFX90A-NEXT: v_pk_mov_b32 v[6:7], s[6:7], s[6:7] op_sel:[0,1]
-; GFX90A-NEXT: flat_atomic_cmpswap_x2 v[2:3], v[6:7], v[2:5] glc
-; GFX90A-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX90A-NEXT: v_mov_b32_e32 v6, 0
+; GFX90A-NEXT: global_atomic_cmpswap_x2 v[2:3], v6, v[2:5], s[6:7] glc
+; GFX90A-NEXT: s_waitcnt vmcnt(0)
; GFX90A-NEXT: v_cmp_eq_u64_e64 s[6:7], v[2:3], v[4:5]
; GFX90A-NEXT: s_or_b64 s[4:5], s[6:7], s[4:5]
; GFX90A-NEXT: s_andn2_b64 exec, exec, s[4:5]
-; GFX90A-NEXT: s_cbranch_execnz .LBB5_4
-; GFX90A-NEXT: ; %bb.5: ; %atomicrmw.end1
+; GFX90A-NEXT: s_cbranch_execnz .LBB5_7
+; GFX90A-NEXT: ; %bb.8: ; %atomicrmw.end1
; GFX90A-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX90A-NEXT: s_mov_b64 s[4:5], 0
-; GFX90A-NEXT: s_branch .LBB5_3
-; GFX90A-NEXT: .LBB5_6: ; %atomicrmw.phi
-; GFX90A-NEXT: ; %bb.7: ; %atomicrmw.end
+; GFX90A-NEXT: s_branch .LBB5_6
+; GFX90A-NEXT: .LBB5_9: ; %Flow3
+; GFX90A-NEXT: s_mov_b64 s[4:5], 0
+; GFX90A-NEXT: s_branch .LBB5_1
+; GFX90A-NEXT: .LBB5_10: ; %atomicrmw.phi
+; GFX90A-NEXT: ; %bb.11: ; %atomicrmw.end
; GFX90A-NEXT: s_mov_b32 s4, 32
+; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: v_lshrrev_b64 v[4:5], s4, v[2:3]
; GFX90A-NEXT: v_mov_b32_e32 v0, v2
; GFX90A-NEXT: v_mov_b32_e32 v1, v4
@@ -866,6 +895,31 @@ define double @optnone_atomicrmw_fadd_f64_expand(double %val) #1 {
; GFX942-LABEL: optnone_atomicrmw_fadd_f64_expand:
; GFX942: ; %bb.0:
; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX942-NEXT: s_mov_b64 s[0:1], src_shared_base
+; GFX942-NEXT: s_mov_b32 s2, 32
+; GFX942-NEXT: s_lshr_b64 s[0:1], s[0:1], s2
+; GFX942-NEXT: s_getpc_b64 s[2:3]
+; GFX942-NEXT: s_add_u32 s2, s2, global at rel32@lo+4
+; GFX942-NEXT: s_addc_u32 s3, s3, global at rel32@hi+12
+; GFX942-NEXT: s_cmp_eq_u32 s3, s0
+; GFX942-NEXT: s_cselect_b64 s[0:1], -1, 0
+; GFX942-NEXT: v_cndmask_b32_e64 v2, 0, 1, s[0:1]
+; GFX942-NEXT: s_mov_b64 s[0:1], -1
+; GFX942-NEXT: s_mov_b32 s2, 1
+; GFX942-NEXT: v_cmp_ne_u32_e64 s[2:3], v2, s2
+; GFX942-NEXT: s_and_b64 vcc, exec, s[2:3]
+; GFX942-NEXT: ; implicit-def: $vgpr2_vgpr3
+; GFX942-NEXT: s_cbranch_vccnz .LBB5_3
+; GFX942-NEXT: .LBB5_1: ; %Flow4
+; GFX942-NEXT: v_cndmask_b32_e64 v4, 0, 1, s[0:1]
+; GFX942-NEXT: s_mov_b32 s0, 1
+; GFX942-NEXT: v_cmp_ne_u32_e64 s[0:1], v4, s0
+; GFX942-NEXT: s_and_b64 vcc, exec, s[0:1]
+; GFX942-NEXT: s_cbranch_vccnz .LBB5_10
+; GFX942-NEXT: ; %bb.2: ; %atomicrmw.shared
+; GFX942-NEXT: ds_add_rtn_f64 v[2:3], v0, v[0:1]
+; GFX942-NEXT: s_branch .LBB5_10
+; GFX942-NEXT: .LBB5_3: ; %atomicrmw.check.private
; GFX942-NEXT: s_mov_b64 s[0:1], src_private_base
; GFX942-NEXT: s_mov_b32 s2, 32
; GFX942-NEXT: s_lshr_b64 s[0:1], s[0:1], s2
@@ -880,48 +934,52 @@ define double @optnone_atomicrmw_fadd_f64_expand(double %val) #1 {
; GFX942-NEXT: v_cmp_ne_u32_e64 s[2:3], v2, s2
; GFX942-NEXT: s_and_b64 vcc, exec, s[2:3]
; GFX942-NEXT: ; implicit-def: $vgpr2_vgpr3
-; GFX942-NEXT: s_cbranch_vccnz .LBB5_2
-; GFX942-NEXT: s_branch .LBB5_3
-; GFX942-NEXT: .LBB5_1: ; %atomicrmw.private
+; GFX942-NEXT: s_cbranch_vccnz .LBB5_5
+; GFX942-NEXT: s_branch .LBB5_6
+; GFX942-NEXT: .LBB5_4: ; %atomicrmw.private
; GFX942-NEXT: scratch_load_dwordx2 v[2:3], off, s0
; GFX942-NEXT: s_waitcnt vmcnt(0)
-; GFX942-NEXT: v_add_f64 v[0:1], v[2:3], v[0:1]
-; GFX942-NEXT: scratch_store_dwordx2 off, v[0:1], s0
-; GFX942-NEXT: s_branch .LBB5_6
-; GFX942-NEXT: .LBB5_2: ; %atomicrmw.global
+; GFX942-NEXT: v_add_f64 v[4:5], v[2:3], v[0:1]
+; GFX942-NEXT: scratch_store_dwordx2 off, v[4:5], s0
+; GFX942-NEXT: s_branch .LBB5_9
+; GFX942-NEXT: .LBB5_5: ; %atomicrmw.global
+; GFX942-NEXT: v_mov_b32_e32 v2, 0
; GFX942-NEXT: s_getpc_b64 s[0:1]
; GFX942-NEXT: s_add_u32 s0, s0, global at rel32@lo+4
; GFX942-NEXT: s_addc_u32 s1, s1, global at rel32@hi+12
-; GFX942-NEXT: v_mov_b64_e32 v[2:3], s[0:1]
-; GFX942-NEXT: flat_load_dwordx2 v[2:3], v[2:3]
+; GFX942-NEXT: global_load_dwordx2 v[2:3], v2, s[0:1]
; GFX942-NEXT: s_mov_b64 s[0:1], 0
-; GFX942-NEXT: s_branch .LBB5_4
-; GFX942-NEXT: .LBB5_3: ; %Flow
+; GFX942-NEXT: s_branch .LBB5_7
+; GFX942-NEXT: .LBB5_6: ; %Flow
; GFX942-NEXT: s_and_b64 vcc, exec, s[0:1]
-; GFX942-NEXT: s_cbranch_vccnz .LBB5_1
-; GFX942-NEXT: s_branch .LBB5_6
-; GFX942-NEXT: .LBB5_4: ; %atomicrmw.start
+; GFX942-NEXT: s_cbranch_vccnz .LBB5_4
+; GFX942-NEXT: s_branch .LBB5_9
+; GFX942-NEXT: .LBB5_7: ; %atomicrmw.start
; GFX942-NEXT: ; =>This Inner Loop Header: Depth=1
-; GFX942-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX942-NEXT: s_waitcnt vmcnt(0)
; GFX942-NEXT: v_mov_b64_e32 v[4:5], v[2:3]
; GFX942-NEXT: v_add_f64 v[2:3], v[4:5], v[0:1]
; GFX942-NEXT: s_getpc_b64 s[2:3]
; GFX942-NEXT: s_add_u32 s2, s2, global at rel32@lo+4
; GFX942-NEXT: s_addc_u32 s3, s3, global at rel32@hi+12
-; GFX942-NEXT: v_mov_b64_e32 v[6:7], s[2:3]
-; GFX942-NEXT: flat_atomic_cmpswap_x2 v[2:3], v[6:7], v[2:5] sc0 sc1
-; GFX942-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX942-NEXT: v_mov_b32_e32 v6, 0
+; GFX942-NEXT: global_atomic_cmpswap_x2 v[2:3], v6, v[2:5], s[2:3] sc0 sc1
+; GFX942-NEXT: s_waitcnt vmcnt(0)
; GFX942-NEXT: v_cmp_eq_u64_e64 s[2:3], v[2:3], v[4:5]
; GFX942-NEXT: s_or_b64 s[0:1], s[2:3], s[0:1]
; GFX942-NEXT: s_andn2_b64 exec, exec, s[0:1]
-; GFX942-NEXT: s_cbranch_execnz .LBB5_4
-; GFX942-NEXT: ; %bb.5: ; %atomicrmw.end1
+; GFX942-NEXT: s_cbranch_execnz .LBB5_7
+; GFX942-NEXT: ; %bb.8: ; %atomicrmw.end1
; GFX942-NEXT: s_or_b64 exec, exec, s[0:1]
; GFX942-NEXT: s_mov_b64 s[0:1], 0
-; GFX942-NEXT: s_branch .LBB5_3
-; GFX942-NEXT: .LBB5_6: ; %atomicrmw.phi
-; GFX942-NEXT: ; %bb.7: ; %atomicrmw.end
+; GFX942-NEXT: s_branch .LBB5_6
+; GFX942-NEXT: .LBB5_9: ; %Flow3
+; GFX942-NEXT: s_mov_b64 s[0:1], 0
+; GFX942-NEXT: s_branch .LBB5_1
+; GFX942-NEXT: .LBB5_10: ; %atomicrmw.phi
+; GFX942-NEXT: ; %bb.11: ; %atomicrmw.end
; GFX942-NEXT: s_mov_b32 s0, 32
+; GFX942-NEXT: s_waitcnt lgkmcnt(0)
; GFX942-NEXT: v_lshrrev_b64 v[4:5], s0, v[2:3]
; GFX942-NEXT: v_mov_b32_e32 v0, v2
; GFX942-NEXT: v_mov_b32_e32 v1, v4
diff --git a/llvm/test/CodeGen/AMDGPU/flat-atomicrmw-fadd.ll b/llvm/test/CodeGen/AMDGPU/flat-atomicrmw-fadd.ll
index e13c895a1cc85..cfe4d24d427e7 100644
--- a/llvm/test/CodeGen/AMDGPU/flat-atomicrmw-fadd.ll
+++ b/llvm/test/CodeGen/AMDGPU/flat-atomicrmw-fadd.ll
@@ -5758,29 +5758,38 @@ define double @flat_agent_atomic_fadd_ret_f64__amdgpu_no_fine_grained_memory(ptr
; GFX942: ; %bb.0:
; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX942-NEXT: v_mov_b32_e32 v5, v1
-; GFX942-NEXT: s_mov_b64 s[0:1], src_private_base
+; GFX942-NEXT: s_mov_b64 s[0:1], src_shared_base
; GFX942-NEXT: v_mov_b32_e32 v4, v0
; GFX942-NEXT: v_cmp_ne_u32_e32 vcc, s1, v5
; GFX942-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX942-NEXT: s_and_saveexec_b64 s[0:1], vcc
; GFX942-NEXT: s_xor_b64 s[0:1], exec, s[0:1]
; GFX942-NEXT: s_cbranch_execnz .LBB30_3
-; GFX942-NEXT: ; %bb.1: ; %Flow
+; GFX942-NEXT: ; %bb.1: ; %Flow2
; GFX942-NEXT: s_andn2_saveexec_b64 s[0:1], s[0:1]
-; GFX942-NEXT: s_cbranch_execnz .LBB30_4
+; GFX942-NEXT: s_cbranch_execnz .LBB30_8
; GFX942-NEXT: .LBB30_2: ; %atomicrmw.phi
; GFX942-NEXT: s_or_b64 exec, exec, s[0:1]
+; GFX942-NEXT: s_waitcnt vmcnt(0)
; GFX942-NEXT: s_setpc_b64 s[30:31]
-; GFX942-NEXT: .LBB30_3: ; %atomicrmw.global
+; GFX942-NEXT: .LBB30_3: ; %atomicrmw.check.private
+; GFX942-NEXT: s_mov_b64 s[2:3], src_private_base
+; GFX942-NEXT: v_cmp_ne_u32_e32 vcc, s3, v5
+; GFX942-NEXT: ; implicit-def: $vgpr0_vgpr1
+; GFX942-NEXT: s_and_saveexec_b64 s[2:3], vcc
+; GFX942-NEXT: s_xor_b64 s[2:3], exec, s[2:3]
+; GFX942-NEXT: s_cbranch_execz .LBB30_5
+; GFX942-NEXT: ; %bb.4: ; %atomicrmw.global
; GFX942-NEXT: buffer_wbl2 sc1
-; GFX942-NEXT: flat_atomic_add_f64 v[0:1], v[4:5], v[2:3] sc0
-; GFX942-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX942-NEXT: global_atomic_add_f64 v[0:1], v[4:5], v[2:3], off sc0
+; GFX942-NEXT: s_waitcnt vmcnt(0)
; GFX942-NEXT: buffer_inv sc1
; GFX942-NEXT: ; implicit-def: $vgpr4_vgpr5
; GFX942-NEXT: ; implicit-def: $vgpr2_vgpr3
-; GFX942-NEXT: s_andn2_saveexec_b64 s[0:1], s[0:1]
-; GFX942-NEXT: s_cbranch_execz .LBB30_2
-; GFX942-NEXT: .LBB30_4: ; %atomicrmw.private
+; GFX942-NEXT: .LBB30_5: ; %Flow
+; GFX942-NEXT: s_andn2_saveexec_b64 s[2:3], s[2:3]
+; GFX942-NEXT: s_cbranch_execz .LBB30_7
+; GFX942-NEXT: ; %bb.6: ; %atomicrmw.private
; GFX942-NEXT: v_cmp_ne_u64_e32 vcc, 0, v[4:5]
; GFX942-NEXT: s_nop 1
; GFX942-NEXT: v_cndmask_b32_e32 v4, -1, v4, vcc
@@ -5788,6 +5797,18 @@ define double @flat_agent_atomic_fadd_ret_f64__amdgpu_no_fine_grained_memory(ptr
; GFX942-NEXT: s_waitcnt vmcnt(0)
; GFX942-NEXT: v_add_f64 v[2:3], v[0:1], v[2:3]
; GFX942-NEXT: scratch_store_dwordx2 v4, v[2:3], off
+; GFX942-NEXT: .LBB30_7: ; %Flow1
+; GFX942-NEXT: s_or_b64 exec, exec, s[2:3]
+; GFX942-NEXT: ; implicit-def: $vgpr4_vgpr5
+; GFX942-NEXT: ; implicit-def: $vgpr2_vgpr3
+; GFX942-NEXT: s_andn2_saveexec_b64 s[0:1], s[0:1]
+; GFX942-NEXT: s_cbranch_execz .LBB30_2
+; GFX942-NEXT: .LBB30_8: ; %atomicrmw.shared
+; GFX942-NEXT: v_cmp_ne_u64_e32 vcc, 0, v[4:5]
+; GFX942-NEXT: s_nop 1
+; GFX942-NEXT: v_cndmask_b32_e32 v0, -1, v4, vcc
+; GFX942-NEXT: ds_add_rtn_f64 v[0:1], v0, v[2:3]
+; GFX942-NEXT: s_waitcnt lgkmcnt(0)
; GFX942-NEXT: s_or_b64 exec, exec, s[0:1]
; GFX942-NEXT: s_waitcnt vmcnt(0)
; GFX942-NEXT: s_setpc_b64 s[30:31]
@@ -5894,28 +5915,37 @@ define double @flat_agent_atomic_fadd_ret_f64__amdgpu_no_fine_grained_memory(ptr
; GFX90A: ; %bb.0:
; GFX90A-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX90A-NEXT: v_mov_b32_e32 v5, v1
-; GFX90A-NEXT: s_mov_b64 s[4:5], src_private_base
+; GFX90A-NEXT: s_mov_b64 s[4:5], src_shared_base
; GFX90A-NEXT: v_mov_b32_e32 v4, v0
; GFX90A-NEXT: v_cmp_ne_u32_e32 vcc, s5, v5
; GFX90A-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX90A-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX90A-NEXT: s_xor_b64 s[4:5], exec, s[4:5]
; GFX90A-NEXT: s_cbranch_execnz .LBB30_3
-; GFX90A-NEXT: ; %bb.1: ; %Flow
+; GFX90A-NEXT: ; %bb.1: ; %Flow2
; GFX90A-NEXT: s_andn2_saveexec_b64 s[4:5], s[4:5]
-; GFX90A-NEXT: s_cbranch_execnz .LBB30_4
+; GFX90A-NEXT: s_cbranch_execnz .LBB30_8
; GFX90A-NEXT: .LBB30_2: ; %atomicrmw.phi
; GFX90A-NEXT: s_or_b64 exec, exec, s[4:5]
+; GFX90A-NEXT: s_waitcnt vmcnt(0)
; GFX90A-NEXT: s_setpc_b64 s[30:31]
-; GFX90A-NEXT: .LBB30_3: ; %atomicrmw.global
-; GFX90A-NEXT: flat_atomic_add_f64 v[0:1], v[4:5], v[2:3] glc
-; GFX90A-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX90A-NEXT: .LBB30_3: ; %atomicrmw.check.private
+; GFX90A-NEXT: s_mov_b64 s[6:7], src_private_base
+; GFX90A-NEXT: v_cmp_ne_u32_e32 vcc, s7, v5
+; GFX90A-NEXT: ; implicit-def: $vgpr0_vgpr1
+; GFX90A-NEXT: s_and_saveexec_b64 s[6:7], vcc
+; GFX90A-NEXT: s_xor_b64 s[6:7], exec, s[6:7]
+; GFX90A-NEXT: s_cbranch_execz .LBB30_5
+; GFX90A-NEXT: ; %bb.4: ; %atomicrmw.global
+; GFX90A-NEXT: global_atomic_add_f64 v[0:1], v[4:5], v[2:3], off glc
+; GFX90A-NEXT: s_waitcnt vmcnt(0)
; GFX90A-NEXT: buffer_wbinvl1
; GFX90A-NEXT: ; implicit-def: $vgpr4_vgpr5
; GFX90A-NEXT: ; implicit-def: $vgpr2_vgpr3
-; GFX90A-NEXT: s_andn2_saveexec_b64 s[4:5], s[4:5]
-; GFX90A-NEXT: s_cbranch_execz .LBB30_2
-; GFX90A-NEXT: .LBB30_4: ; %atomicrmw.private
+; GFX90A-NEXT: .LBB30_5: ; %Flow
+; GFX90A-NEXT: s_andn2_saveexec_b64 s[6:7], s[6:7]
+; GFX90A-NEXT: s_cbranch_execz .LBB30_7
+; GFX90A-NEXT: ; %bb.6: ; %atomicrmw.private
; GFX90A-NEXT: v_cmp_ne_u64_e32 vcc, 0, v[4:5]
; GFX90A-NEXT: v_cndmask_b32_e32 v4, -1, v4, vcc
; GFX90A-NEXT: buffer_load_dword v0, v4, s[0:3], 0 offen
@@ -5924,6 +5954,17 @@ define double @flat_agent_atomic_fadd_ret_f64__amdgpu_no_fine_grained_memory(ptr
; GFX90A-NEXT: v_add_f64 v[2:3], v[0:1], v[2:3]
; GFX90A-NEXT: buffer_store_dword v2, v4, s[0:3], 0 offen
; GFX90A-NEXT: buffer_store_dword v3, v4, s[0:3], 0 offen offset:4
+; GFX90A-NEXT: .LBB30_7: ; %Flow1
+; GFX90A-NEXT: s_or_b64 exec, exec, s[6:7]
+; GFX90A-NEXT: ; implicit-def: $vgpr4_vgpr5
+; GFX90A-NEXT: ; implicit-def: $vgpr2_vgpr3
+; GFX90A-NEXT: s_andn2_saveexec_b64 s[4:5], s[4:5]
+; GFX90A-NEXT: s_cbranch_execz .LBB30_2
+; GFX90A-NEXT: .LBB30_8: ; %atomicrmw.shared
+; GFX90A-NEXT: v_cmp_ne_u64_e32 vcc, 0, v[4:5]
+; GFX90A-NEXT: v_cndmask_b32_e32 v0, -1, v4, vcc
+; GFX90A-NEXT: ds_add_rtn_f64 v[0:1], v0, v[2:3]
+; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX90A-NEXT: s_waitcnt vmcnt(0)
; GFX90A-NEXT: s_setpc_b64 s[30:31]
@@ -6160,28 +6201,37 @@ define double @flat_agent_atomic_fadd_ret_f64__offset12b_pos__amdgpu_no_fine_gra
; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX942-NEXT: s_mov_b64 s[0:1], 0x7f8
; GFX942-NEXT: v_lshl_add_u64 v[4:5], v[0:1], 0, s[0:1]
-; GFX942-NEXT: s_mov_b64 s[0:1], src_private_base
+; GFX942-NEXT: s_mov_b64 s[0:1], src_shared_base
; GFX942-NEXT: v_cmp_ne_u32_e32 vcc, s1, v5
; GFX942-NEXT: ; implicit-def: $vgpr0_vgpr1
; GFX942-NEXT: s_and_saveexec_b64 s[0:1], vcc
; GFX942-NEXT: s_xor_b64 s[0:1], exec, s[0:1]
; GFX942-NEXT: s_cbranch_execnz .LBB31_3
-; GFX942-NEXT: ; %bb.1: ; %Flow
+; GFX942-NEXT: ; %bb.1: ; %Flow2
; GFX942-NEXT: s_andn2_saveexec_b64 s[0:1], s[0:1]
-; GFX942-NEXT: s_cbranch_execnz .LBB31_4
+; GFX942-NEXT: s_cbranch_execnz .LBB31_8
; GFX942-NEXT: .LBB31_2: ; %atomicrmw.phi
; GFX942-NEXT: s_or_b64 exec, exec, s[0:1]
+; GFX942-NEXT: s_waitcnt vmcnt(0)
; GFX942-NEXT: s_setpc_b64 s[30:31]
-; GFX942-NEXT: .LBB31_3: ; %atomicrmw.global
+; GFX942-NEXT: .LBB31_3: ; %atomicrmw.check.private
+; GFX942-NEXT: s_mov_b64 s[2:3], src_private_base
+; GFX942-NEXT: v_cmp_ne_u32_e32 vcc, s3, v5
+; GFX942-NEXT: ; implicit-def: $vgpr0_vgpr1
+; GFX942-NEXT: s_and_saveexec_b64 s[2:3], vcc
+; GFX942-NEXT: s_xor_b64 s[2:3], exec, s[2:3]
+; GFX942-NEXT: s_cbranch_execz .LBB31_5
+; GFX942-NEXT: ; %bb.4: ; %atomicrmw.global
; GFX942-NEXT: buffer_wbl2 sc1
-; GFX942-NEXT: flat_atomic_add_f64 v[0:1], v[4:5], v[2:3] sc0
-; GFX942-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX942-NEXT: global_atomic_add_f64 v[0:1], v[4:5], v[2:3], off sc0
+; GFX942-NEXT: s_waitcnt vmcnt(0)
; GFX942-NEXT: buffer_inv sc1
; GFX942-NEXT: ; implicit-def: $vgpr4_vgpr5
; GFX942-NEXT: ; implicit-def: $vgpr2_vgpr3
-; GFX942-NEXT: s_andn2_saveexec_b64 s[0:1], s[0:1]
-; GFX942-NEXT: s_cbranch_execz .LBB31_2
-; GFX942-NEXT: .LBB31_4: ; %atomicrmw.private
+; GFX942-NEXT: .LBB31_5: ; %Flow
+; GFX942-NEXT: s_andn2_saveexec_b64 s[2:3], s[2:3]
+; GFX942-NEXT: s_cbranch_execz .LBB31_7
+; GFX942-NEXT: ; %bb.6: ; %atomicrmw.private
; GFX942-NEXT: v_cmp_ne_u64_e32 vcc, 0, v[4:5]
; GFX942-NEXT: s_nop 1
; GFX942-NEXT: v_cndmask_b32...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/142859
More information about the llvm-commits
mailing list