[llvm] AMDGPU: Fix atomic expand tests accidentally underaligning (PR #147299)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Jul 7 06:41:03 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Matt Arsenault (arsenm)
<details>
<summary>Changes</summary>
---
Patch is 448.50 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/147299.diff
2 Files Affected:
- (modified) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-f64-agent.ll (+1942-750)
- (modified) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-f64-system.ll (+1586-715)
``````````diff
diff --git a/llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-f64-agent.ll b/llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-f64-agent.ll
index 1c2ae608711cc..668e7ba9b1f0f 100644
--- a/llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-f64-agent.ll
+++ b/llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-f64-agent.ll
@@ -787,419 +787,1863 @@ define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_no_fine_grained_memo
}
define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode(ptr addrspace(1) %ptr, double %value) {
-; COMMON-LABEL: define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode(
-; COMMON-SAME: ptr addrspace(1) [[PTR:%.*]], double [[VALUE:%.*]]) #[[ATTR0]] {
-; COMMON-NEXT: [[TMP1:%.*]] = alloca double, align 8, addrspace(5)
-; COMMON-NEXT: [[TMP2:%.*]] = alloca double, align 8, addrspace(5)
-; COMMON-NEXT: [[TMP3:%.*]] = load double, ptr addrspace(1) [[PTR]], align 4
-; COMMON-NEXT: br label [[ATOMICRMW_START:%.*]]
-; COMMON: atomicrmw.start:
-; COMMON-NEXT: [[LOADED:%.*]] = phi double [ [[TMP3]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
-; COMMON-NEXT: [[NEW:%.*]] = fadd double [[LOADED]], [[VALUE]]
-; COMMON-NEXT: [[TMP4:%.*]] = addrspacecast ptr addrspace(1) [[PTR]] to ptr
-; COMMON-NEXT: call void @llvm.lifetime.start.p5(i64 8, ptr addrspace(5) [[TMP1]])
-; COMMON-NEXT: store double [[LOADED]], ptr addrspace(5) [[TMP1]], align 8
-; COMMON-NEXT: call void @llvm.lifetime.start.p5(i64 8, ptr addrspace(5) [[TMP2]])
-; COMMON-NEXT: store double [[NEW]], ptr addrspace(5) [[TMP2]], align 8
-; COMMON-NEXT: [[TMP5:%.*]] = call zeroext i1 @__atomic_compare_exchange(i64 8, ptr [[TMP4]], ptr addrspace(5) [[TMP1]], ptr addrspace(5) [[TMP2]], i32 5, i32 5)
-; COMMON-NEXT: call void @llvm.lifetime.end.p5(i64 8, ptr addrspace(5) [[TMP2]])
-; COMMON-NEXT: [[TMP6:%.*]] = load double, ptr addrspace(5) [[TMP1]], align 8
-; COMMON-NEXT: call void @llvm.lifetime.end.p5(i64 8, ptr addrspace(5) [[TMP1]])
-; COMMON-NEXT: [[TMP7:%.*]] = insertvalue { double, i1 } poison, double [[TMP6]], 0
-; COMMON-NEXT: [[TMP8:%.*]] = insertvalue { double, i1 } [[TMP7]], i1 [[TMP5]], 1
-; COMMON-NEXT: [[SUCCESS:%.*]] = extractvalue { double, i1 } [[TMP8]], 1
-; COMMON-NEXT: [[NEWLOADED]] = extractvalue { double, i1 } [[TMP8]], 0
-; COMMON-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
-; COMMON: atomicrmw.end:
-; COMMON-NEXT: ret double [[NEWLOADED]]
+; GFX803-LABEL: define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode(
+; GFX803-SAME: ptr addrspace(1) [[PTR:%.*]], double [[VALUE:%.*]]) #[[ATTR0]] {
+; GFX803-NEXT: [[TMP1:%.*]] = load double, ptr addrspace(1) [[PTR]], align 8
+; GFX803-NEXT: br label [[ATOMICRMW_START:%.*]]
+; GFX803: atomicrmw.start:
+; GFX803-NEXT: [[LOADED:%.*]] = phi double [ [[TMP1]], [[TMP0:%.*]] ], [ [[TMP5:%.*]], [[ATOMICRMW_START]] ]
+; GFX803-NEXT: [[NEW:%.*]] = fadd double [[LOADED]], [[VALUE]]
+; GFX803-NEXT: [[TMP2:%.*]] = bitcast double [[NEW]] to i64
+; GFX803-NEXT: [[TMP3:%.*]] = bitcast double [[LOADED]] to i64
+; GFX803-NEXT: [[TMP4:%.*]] = cmpxchg ptr addrspace(1) [[PTR]], i64 [[TMP3]], i64 [[TMP2]] syncscope("agent") seq_cst seq_cst, align 8
+; GFX803-NEXT: [[SUCCESS:%.*]] = extractvalue { i64, i1 } [[TMP4]], 1
+; GFX803-NEXT: [[NEWLOADED:%.*]] = extractvalue { i64, i1 } [[TMP4]], 0
+; GFX803-NEXT: [[TMP5]] = bitcast i64 [[NEWLOADED]] to double
+; GFX803-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; GFX803: atomicrmw.end:
+; GFX803-NEXT: ret double [[TMP5]]
+;
+; GFX906-LABEL: define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode(
+; GFX906-SAME: ptr addrspace(1) [[PTR:%.*]], double [[VALUE:%.*]]) #[[ATTR0]] {
+; GFX906-NEXT: [[TMP1:%.*]] = load double, ptr addrspace(1) [[PTR]], align 8
+; GFX906-NEXT: br label [[ATOMICRMW_START:%.*]]
+; GFX906: atomicrmw.start:
+; GFX906-NEXT: [[LOADED:%.*]] = phi double [ [[TMP1]], [[TMP0:%.*]] ], [ [[TMP5:%.*]], [[ATOMICRMW_START]] ]
+; GFX906-NEXT: [[NEW:%.*]] = fadd double [[LOADED]], [[VALUE]]
+; GFX906-NEXT: [[TMP2:%.*]] = bitcast double [[NEW]] to i64
+; GFX906-NEXT: [[TMP3:%.*]] = bitcast double [[LOADED]] to i64
+; GFX906-NEXT: [[TMP4:%.*]] = cmpxchg ptr addrspace(1) [[PTR]], i64 [[TMP3]], i64 [[TMP2]] syncscope("agent") seq_cst seq_cst, align 8
+; GFX906-NEXT: [[SUCCESS:%.*]] = extractvalue { i64, i1 } [[TMP4]], 1
+; GFX906-NEXT: [[NEWLOADED:%.*]] = extractvalue { i64, i1 } [[TMP4]], 0
+; GFX906-NEXT: [[TMP5]] = bitcast i64 [[NEWLOADED]] to double
+; GFX906-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; GFX906: atomicrmw.end:
+; GFX906-NEXT: ret double [[TMP5]]
+;
+; GFX908-LABEL: define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode(
+; GFX908-SAME: ptr addrspace(1) [[PTR:%.*]], double [[VALUE:%.*]]) #[[ATTR0]] {
+; GFX908-NEXT: [[TMP1:%.*]] = load double, ptr addrspace(1) [[PTR]], align 8
+; GFX908-NEXT: br label [[ATOMICRMW_START:%.*]]
+; GFX908: atomicrmw.start:
+; GFX908-NEXT: [[LOADED:%.*]] = phi double [ [[TMP1]], [[TMP0:%.*]] ], [ [[TMP5:%.*]], [[ATOMICRMW_START]] ]
+; GFX908-NEXT: [[NEW:%.*]] = fadd double [[LOADED]], [[VALUE]]
+; GFX908-NEXT: [[TMP2:%.*]] = bitcast double [[NEW]] to i64
+; GFX908-NEXT: [[TMP3:%.*]] = bitcast double [[LOADED]] to i64
+; GFX908-NEXT: [[TMP4:%.*]] = cmpxchg ptr addrspace(1) [[PTR]], i64 [[TMP3]], i64 [[TMP2]] syncscope("agent") seq_cst seq_cst, align 8
+; GFX908-NEXT: [[SUCCESS:%.*]] = extractvalue { i64, i1 } [[TMP4]], 1
+; GFX908-NEXT: [[NEWLOADED:%.*]] = extractvalue { i64, i1 } [[TMP4]], 0
+; GFX908-NEXT: [[TMP5]] = bitcast i64 [[NEWLOADED]] to double
+; GFX908-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; GFX908: atomicrmw.end:
+; GFX908-NEXT: ret double [[TMP5]]
+;
+; GFX90A-LABEL: define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode(
+; GFX90A-SAME: ptr addrspace(1) [[PTR:%.*]], double [[VALUE:%.*]]) #[[ATTR0]] {
+; GFX90A-NEXT: [[TMP1:%.*]] = load double, ptr addrspace(1) [[PTR]], align 8
+; GFX90A-NEXT: br label [[ATOMICRMW_START:%.*]]
+; GFX90A: atomicrmw.start:
+; GFX90A-NEXT: [[LOADED:%.*]] = phi double [ [[TMP1]], [[TMP0:%.*]] ], [ [[TMP5:%.*]], [[ATOMICRMW_START]] ]
+; GFX90A-NEXT: [[NEW:%.*]] = fadd double [[LOADED]], [[VALUE]]
+; GFX90A-NEXT: [[TMP2:%.*]] = bitcast double [[NEW]] to i64
+; GFX90A-NEXT: [[TMP3:%.*]] = bitcast double [[LOADED]] to i64
+; GFX90A-NEXT: [[TMP4:%.*]] = cmpxchg ptr addrspace(1) [[PTR]], i64 [[TMP3]], i64 [[TMP2]] syncscope("agent") seq_cst seq_cst, align 8
+; GFX90A-NEXT: [[SUCCESS:%.*]] = extractvalue { i64, i1 } [[TMP4]], 1
+; GFX90A-NEXT: [[NEWLOADED:%.*]] = extractvalue { i64, i1 } [[TMP4]], 0
+; GFX90A-NEXT: [[TMP5]] = bitcast i64 [[NEWLOADED]] to double
+; GFX90A-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; GFX90A: atomicrmw.end:
+; GFX90A-NEXT: ret double [[TMP5]]
+;
+; GFX942-LABEL: define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode(
+; GFX942-SAME: ptr addrspace(1) [[PTR:%.*]], double [[VALUE:%.*]]) #[[ATTR0]] {
+; GFX942-NEXT: [[RES:%.*]] = atomicrmw fadd ptr addrspace(1) [[PTR]], double [[VALUE]] syncscope("agent") seq_cst, align 8, !amdgpu.ignore.denormal.mode [[META0]]
+; GFX942-NEXT: ret double [[RES]]
+;
+; GFX10-LABEL: define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode(
+; GFX10-SAME: ptr addrspace(1) [[PTR:%.*]], double [[VALUE:%.*]]) #[[ATTR0]] {
+; GFX10-NEXT: [[TMP1:%.*]] = load double, ptr addrspace(1) [[PTR]], align 8
+; GFX10-NEXT: br label [[ATOMICRMW_START:%.*]]
+; GFX10: atomicrmw.start:
+; GFX10-NEXT: [[LOADED:%.*]] = phi double [ [[TMP1]], [[TMP0:%.*]] ], [ [[TMP5:%.*]], [[ATOMICRMW_START]] ]
+; GFX10-NEXT: [[NEW:%.*]] = fadd double [[LOADED]], [[VALUE]]
+; GFX10-NEXT: [[TMP2:%.*]] = bitcast double [[NEW]] to i64
+; GFX10-NEXT: [[TMP3:%.*]] = bitcast double [[LOADED]] to i64
+; GFX10-NEXT: [[TMP4:%.*]] = cmpxchg ptr addrspace(1) [[PTR]], i64 [[TMP3]], i64 [[TMP2]] syncscope("agent") seq_cst seq_cst, align 8
+; GFX10-NEXT: [[SUCCESS:%.*]] = extractvalue { i64, i1 } [[TMP4]], 1
+; GFX10-NEXT: [[NEWLOADED:%.*]] = extractvalue { i64, i1 } [[TMP4]], 0
+; GFX10-NEXT: [[TMP5]] = bitcast i64 [[NEWLOADED]] to double
+; GFX10-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; GFX10: atomicrmw.end:
+; GFX10-NEXT: ret double [[TMP5]]
+;
+; GFX11-LABEL: define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode(
+; GFX11-SAME: ptr addrspace(1) [[PTR:%.*]], double [[VALUE:%.*]]) #[[ATTR0]] {
+; GFX11-NEXT: [[TMP1:%.*]] = load double, ptr addrspace(1) [[PTR]], align 8
+; GFX11-NEXT: br label [[ATOMICRMW_START:%.*]]
+; GFX11: atomicrmw.start:
+; GFX11-NEXT: [[LOADED:%.*]] = phi double [ [[TMP1]], [[TMP0:%.*]] ], [ [[TMP5:%.*]], [[ATOMICRMW_START]] ]
+; GFX11-NEXT: [[NEW:%.*]] = fadd double [[LOADED]], [[VALUE]]
+; GFX11-NEXT: [[TMP2:%.*]] = bitcast double [[NEW]] to i64
+; GFX11-NEXT: [[TMP3:%.*]] = bitcast double [[LOADED]] to i64
+; GFX11-NEXT: [[TMP4:%.*]] = cmpxchg ptr addrspace(1) [[PTR]], i64 [[TMP3]], i64 [[TMP2]] syncscope("agent") seq_cst seq_cst, align 8
+; GFX11-NEXT: [[SUCCESS:%.*]] = extractvalue { i64, i1 } [[TMP4]], 1
+; GFX11-NEXT: [[NEWLOADED:%.*]] = extractvalue { i64, i1 } [[TMP4]], 0
+; GFX11-NEXT: [[TMP5]] = bitcast i64 [[NEWLOADED]] to double
+; GFX11-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; GFX11: atomicrmw.end:
+; GFX11-NEXT: ret double [[TMP5]]
+;
+; GFX12-LABEL: define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode(
+; GFX12-SAME: ptr addrspace(1) [[PTR:%.*]], double [[VALUE:%.*]]) #[[ATTR0]] {
+; GFX12-NEXT: [[TMP1:%.*]] = load double, ptr addrspace(1) [[PTR]], align 8
+; GFX12-NEXT: br label [[ATOMICRMW_START:%.*]]
+; GFX12: atomicrmw.start:
+; GFX12-NEXT: [[LOADED:%.*]] = phi double [ [[TMP1]], [[TMP0:%.*]] ], [ [[TMP5:%.*]], [[ATOMICRMW_START]] ]
+; GFX12-NEXT: [[NEW:%.*]] = fadd double [[LOADED]], [[VALUE]]
+; GFX12-NEXT: [[TMP2:%.*]] = bitcast double [[NEW]] to i64
+; GFX12-NEXT: [[TMP3:%.*]] = bitcast double [[LOADED]] to i64
+; GFX12-NEXT: [[TMP4:%.*]] = cmpxchg ptr addrspace(1) [[PTR]], i64 [[TMP3]], i64 [[TMP2]] syncscope("agent") seq_cst seq_cst, align 8
+; GFX12-NEXT: [[SUCCESS:%.*]] = extractvalue { i64, i1 } [[TMP4]], 1
+; GFX12-NEXT: [[NEWLOADED:%.*]] = extractvalue { i64, i1 } [[TMP4]], 0
+; GFX12-NEXT: [[TMP5]] = bitcast i64 [[NEWLOADED]] to double
+; GFX12-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; GFX12: atomicrmw.end:
+; GFX12-NEXT: ret double [[TMP5]]
;
- %res = atomicrmw fadd ptr addrspace(1) %ptr, double %value syncscope("agent") seq_cst, align 4, !amdgpu.ignore.denormal.mode !0
+ %res = atomicrmw fadd ptr addrspace(1) %ptr, double %value syncscope("agent") seq_cst, align 8, !amdgpu.ignore.denormal.mode !0
ret double %res
}
define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode__amdgpu_no_fine_grained_memory(ptr addrspace(1) %ptr, double %value) {
-; COMMON-LABEL: define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode__amdgpu_no_fine_grained_memory(
-; COMMON-SAME: ptr addrspace(1) [[PTR:%.*]], double [[VALUE:%.*]]) #[[ATTR0]] {
-; COMMON-NEXT: [[TMP1:%.*]] = alloca double, align 8, addrspace(5)
-; COMMON-NEXT: [[TMP2:%.*]] = alloca double, align 8, addrspace(5)
-; COMMON-NEXT: [[TMP3:%.*]] = load double, ptr addrspace(1) [[PTR]], align 4
-; COMMON-NEXT: br label [[ATOMICRMW_START:%.*]]
-; COMMON: atomicrmw.start:
-; COMMON-NEXT: [[LOADED:%.*]] = phi double [ [[TMP3]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
-; COMMON-NEXT: [[NEW:%.*]] = fadd double [[LOADED]], [[VALUE]]
-; COMMON-NEXT: [[TMP4:%.*]] = addrspacecast ptr addrspace(1) [[PTR]] to ptr
-; COMMON-NEXT: call void @llvm.lifetime.start.p5(i64 8, ptr addrspace(5) [[TMP1]])
-; COMMON-NEXT: store double [[LOADED]], ptr addrspace(5) [[TMP1]], align 8
-; COMMON-NEXT: call void @llvm.lifetime.start.p5(i64 8, ptr addrspace(5) [[TMP2]])
-; COMMON-NEXT: store double [[NEW]], ptr addrspace(5) [[TMP2]], align 8
-; COMMON-NEXT: [[TMP5:%.*]] = call zeroext i1 @__atomic_compare_exchange(i64 8, ptr [[TMP4]], ptr addrspace(5) [[TMP1]], ptr addrspace(5) [[TMP2]], i32 5, i32 5)
-; COMMON-NEXT: call void @llvm.lifetime.end.p5(i64 8, ptr addrspace(5) [[TMP2]])
-; COMMON-NEXT: [[TMP6:%.*]] = load double, ptr addrspace(5) [[TMP1]], align 8
-; COMMON-NEXT: call void @llvm.lifetime.end.p5(i64 8, ptr addrspace(5) [[TMP1]])
-; COMMON-NEXT: [[TMP7:%.*]] = insertvalue { double, i1 } poison, double [[TMP6]], 0
-; COMMON-NEXT: [[TMP8:%.*]] = insertvalue { double, i1 } [[TMP7]], i1 [[TMP5]], 1
-; COMMON-NEXT: [[SUCCESS:%.*]] = extractvalue { double, i1 } [[TMP8]], 1
-; COMMON-NEXT: [[NEWLOADED]] = extractvalue { double, i1 } [[TMP8]], 0
-; COMMON-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
-; COMMON: atomicrmw.end:
-; COMMON-NEXT: ret double [[NEWLOADED]]
+; GFX803-LABEL: define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode__amdgpu_no_fine_grained_memory(
+; GFX803-SAME: ptr addrspace(1) [[PTR:%.*]], double [[VALUE:%.*]]) #[[ATTR0]] {
+; GFX803-NEXT: [[TMP1:%.*]] = load double, ptr addrspace(1) [[PTR]], align 8
+; GFX803-NEXT: br label [[ATOMICRMW_START:%.*]]
+; GFX803: atomicrmw.start:
+; GFX803-NEXT: [[LOADED:%.*]] = phi double [ [[TMP1]], [[TMP0:%.*]] ], [ [[TMP5:%.*]], [[ATOMICRMW_START]] ]
+; GFX803-NEXT: [[NEW:%.*]] = fadd double [[LOADED]], [[VALUE]]
+; GFX803-NEXT: [[TMP2:%.*]] = bitcast double [[NEW]] to i64
+; GFX803-NEXT: [[TMP3:%.*]] = bitcast double [[LOADED]] to i64
+; GFX803-NEXT: [[TMP4:%.*]] = cmpxchg ptr addrspace(1) [[PTR]], i64 [[TMP3]], i64 [[TMP2]] syncscope("agent") seq_cst seq_cst, align 8, !amdgpu.no.fine.grained.memory [[META0]]
+; GFX803-NEXT: [[SUCCESS:%.*]] = extractvalue { i64, i1 } [[TMP4]], 1
+; GFX803-NEXT: [[NEWLOADED:%.*]] = extractvalue { i64, i1 } [[TMP4]], 0
+; GFX803-NEXT: [[TMP5]] = bitcast i64 [[NEWLOADED]] to double
+; GFX803-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; GFX803: atomicrmw.end:
+; GFX803-NEXT: ret double [[TMP5]]
;
- %res = atomicrmw fadd ptr addrspace(1) %ptr, double %value syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !0, !amdgpu.ignore.denormal.mode !0
- ret double %res
-}
-
-define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode__amdgpu_no_remote_memory(ptr addrspace(1) %ptr, double %value) {
-; COMMON-LABEL: define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode__amdgpu_no_remote_memory(
-; COMMON-SAME: ptr addrspace(1) [[PTR:%.*]], double [[VALUE:%.*]]) #[[ATTR0]] {
-; COMMON-NEXT: [[TMP1:%.*]] = alloca double, align 8, addrspace(5)
-; COMMON-NEXT: [[TMP2:%.*]] = alloca double, align 8, addrspace(5)
-; COMMON-NEXT: [[TMP3:%.*]] = load double, ptr addrspace(1) [[PTR]], align 4
-; COMMON-NEXT: br label [[ATOMICRMW_START:%.*]]
-; COMMON: atomicrmw.start:
-; COMMON-NEXT: [[LOADED:%.*]] = phi double [ [[TMP3]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
-; COMMON-NEXT: [[NEW:%.*]] = fadd double [[LOADED]], [[VALUE]]
-; COMMON-NEXT: [[TMP4:%.*]] = addrspacecast ptr addrspace(1) [[PTR]] to ptr
-; COMMON-NEXT: call void @llvm.lifetime.start.p5(i64 8, ptr addrspace(5) [[TMP1]])
-; COMMON-NEXT: store double [[LOADED]], ptr addrspace(5) [[TMP1]], align 8
-; COMMON-NEXT: call void @llvm.lifetime.start.p5(i64 8, ptr addrspace(5) [[TMP2]])
-; COMMON-NEXT: store double [[NEW]], ptr addrspace(5) [[TMP2]], align 8
-; COMMON-NEXT: [[TMP5:%.*]] = call zeroext i1 @__atomic_compare_exchange(i64 8, ptr [[TMP4]], ptr addrspace(5) [[TMP1]], ptr addrspace(5) [[TMP2]], i32 5, i32 5)
-; COMMON-NEXT: call void @llvm.lifetime.end.p5(i64 8, ptr addrspace(5) [[TMP2]])
-; COMMON-NEXT: [[TMP6:%.*]] = load double, ptr addrspace(5) [[TMP1]], align 8
-; COMMON-NEXT: call void @llvm.lifetime.end.p5(i64 8, ptr addrspace(5) [[TMP1]])
-; COMMON-NEXT: [[TMP7:%.*]] = insertvalue { double, i1 } poison, double [[TMP6]], 0
-; COMMON-NEXT: [[TMP8:%.*]] = insertvalue { double, i1 } [[TMP7]], i1 [[TMP5]], 1
-; COMMON-NEXT: [[SUCCESS:%.*]] = extractvalue { double, i1 } [[TMP8]], 1
-; COMMON-NEXT: [[NEWLOADED]] = extractvalue { double, i1 } [[TMP8]], 0
-; COMMON-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
-; COMMON: atomicrmw.end:
-; COMMON-NEXT: ret double [[NEWLOADED]]
+; GFX906-LABEL: define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode__amdgpu_no_fine_grained_memory(
+; GFX906-SAME: ptr addrspace(1) [[PTR:%.*]], double [[VALUE:%.*]]) #[[ATTR0]] {
+; GFX906-NEXT: [[TMP1:%.*]] = load double, ptr addrspace(1) [[PTR]], align 8
+; GFX906-NEXT: br label [[ATOMICRMW_START:%.*]]
+; GFX906: atomicrmw.start:
+; GFX906-NEXT: [[LOADED:%.*]] = phi double [ [[TMP1]], [[TMP0:%.*]] ], [ [[TMP5:%.*]], [[ATOMICRMW_START]] ]
+; GFX906-NEXT: [[NEW:%.*]] = fadd double [[LOADED]], [[VALUE]]
+; GFX906-NEXT: [[TMP2:%.*]] = bitcast double [[NEW]] to i64
+; GFX906-NEXT: [[TMP3:%.*]] = bitcast double [[LOADED]] to i64
+; GFX906-NEXT: [[TMP4:%.*]] = cmpxchg ptr addrspace(1) [[PTR]], i64 [[TMP3]], i64 [[TMP2]] syncscope("agent") seq_cst seq_cst, align 8, !amdgpu.no.fine.grained.memory [[META0]]
+; GFX906-NEXT: [[SUCCESS:%.*]] = extractvalue { i64, i1 } [[TMP4]], 1
+; GFX906-NEXT: [[NEWLOADED:%.*]] = extractvalue { i64, i1 } [[TMP4]], 0
+; GFX906-NEXT: [[TMP5]] = bitcast i64 [[NEWLOADED]] to double
+; GFX906-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; GFX906: atomicrmw.end:
+; GFX906-NEXT: ret double [[TMP5]]
;
- %res = atomicrmw fadd ptr addrspace(1) %ptr, double %value syncscope("agent") seq_cst, align 4, !amdgpu.no.remote.memory !0, !amdgpu.ignore.denormal.mode !0
- ret double %res
-}
-
-define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode__amdgpu_no_fine_grained_memory__amdgpu_no_remote_memory(ptr addrspace(1) %ptr, double %value) {
-; COMMON-LABEL: define double @test_atomicrmw_fadd_f64_global_agent__amdgpu_ignore_denormal_mode__amdgpu_no_fine_grained_memory__amdgpu_no_remote_memory(
-; COMMON-SAME: ptr addrspace(1) [[PTR:%.*]], double [[VALUE:%.*]]) #[[ATTR0]] {
-; COMMON-NEXT: [[TMP1:%.*]] = alloca double, align 8, addrspace(5)
-; COMMON-NEXT: [[TMP2:%.*]] = alloca double, align 8, addrspace(5)
-; COMMON-NEXT: [[TMP3:%.*]] = load double, ptr addrspace(1) [[PTR]], align 4
-; COMMON-NEXT: br label [[ATOMICRMW_START:%.*]]
-; COMMON: atomicrmw.start:
-; COMMON-NEXT: [[LOADED:%.*]] = phi double [ [[TMP3]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
-; COMMON-NEXT: [[NEW:%.*]] = fadd double [[LOADED]], [[VALUE]]
-; COMMON-NEXT: [[TMP4:%.*]] = addrspacecast ptr addrspace(1) [[PTR]] to ptr
-; COMMON-NEXT: call void @llvm.lifetime.start.p5(i64 8, ptr addrspace(5) [[TMP1]])
-; COMMON-NEXT: store double [[LOADED]], ptr addrspace(5) [[TMP1]], align 8
-; COMMON-NEXT: call void @llvm.lifetime.start.p5(i64 8, ptr addrspace(5) [[TMP2]])
-; COMMON-NEXT: store double [[NEW]], ptr addrspace(5) [[TMP2]], align 8
-; COMMON-NEXT: [[TMP5:%.*]] = call zeroext i1 @__atomic_compare_exchange(i64 8, ptr [[TMP4]], ptr addrspace(5) [[TMP1]], ptr addrspace(5) [[TMP2]], i32 5, i32 5)
-; COMMON-NEXT: call void @llvm.lifetime.end.p5(i64 8, ptr addrspace(5) [[TMP2]])
-; COMMON-NEXT: [[TMP6:%.*]] = load double, ptr addrspace(5) [[TMP1]], align 8
-; COMMON-NEXT: call void @llvm.lifetime.end.p5(i64 8, ptr addrspace(5) [[TMP1]])
-; COMMON-NEXT: [[TMP7:%.*]] = insertvalue { double, i1 } ...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/147299
More information about the llvm-commits
mailing list