; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a -verify-each -atomic-expand %s | FileCheck -check-prefix=GFX90A %s
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -verify-each -atomic-expand %s | FileCheck -check-prefix=GFX1100 %s
; Contains a variety of tests with different types of atomic expansions to check that MMRAs are
; preserved.
define i16 @test_atomicrmw_xchg_i16_global_agent(ptr addrspace(1) %ptr, i16 %value) {
; GFX90A-LABEL: define i16 @test_atomicrmw_xchg_i16_global_agent(
; GFX90A-SAME: ptr addrspace(1) [[PTR:%.*]], i16 [[VALUE:%.*]]) #[[ATTR0:[0-9]+]] {
; GFX90A-NEXT: [[ALIGNEDADDR:%.*]] = call ptr addrspace(1) @llvm.ptrmask.p1.i64(ptr addrspace(1) [[PTR]], i64 -4)
; GFX90A-NEXT: [[TMP1:%.*]] = ptrtoint ptr addrspace(1) [[PTR]] to i64
; GFX90A-NEXT: [[PTRLSB:%.*]] = and i64 [[TMP1]], 3
; GFX90A-NEXT: [[TMP2:%.*]] = shl i64 [[PTRLSB]], 3
; GFX90A-NEXT: [[SHIFTAMT:%.*]] = trunc i64 [[TMP2]] to i32
; GFX90A-NEXT: [[MASK:%.*]] = shl i32 65535, [[SHIFTAMT]]
; GFX90A-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
; GFX90A-NEXT: [[TMP3:%.*]] = zext i16 [[VALUE]] to i32
; GFX90A-NEXT: [[VALOPERAND_SHIFTED:%.*]] = shl i32 [[TMP3]], [[SHIFTAMT]]
; GFX90A-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(1) [[ALIGNEDADDR]], align 4, !mmra [[META0:![0-9]+]]
; GFX90A-NEXT: br label [[ATOMICRMW_START:%.*]]
; GFX90A: atomicrmw.start:
; GFX90A-NEXT: [[LOADED:%.*]] = phi i32 [ [[TMP4]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
; GFX90A-NEXT: [[TMP5:%.*]] = and i32 [[LOADED]], [[INV_MASK]]
; GFX90A-NEXT: [[TMP6:%.*]] = or i32 [[TMP5]], [[VALOPERAND_SHIFTED]]
; GFX90A-NEXT: [[TMP7:%.*]] = cmpxchg ptr addrspace(1) [[ALIGNEDADDR]], i32 [[LOADED]], i32 [[TMP6]] syncscope("agent") seq_cst seq_cst, align 4, !mmra [[META0]]
; GFX90A-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP7]], 1
; GFX90A-NEXT: [[NEWLOADED]] = extractvalue { i32, i1 } [[TMP7]], 0
; GFX90A-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
; GFX90A: atomicrmw.end:
; GFX90A-NEXT: [[SHIFTED:%.*]] = lshr i32 [[NEWLOADED]], [[SHIFTAMT]]
; GFX90A-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
; GFX90A-NEXT: ret i16 [[EXTRACTED]]
;
; GFX1100-LABEL: define i16 @test_atomicrmw_xchg_i16_global_agent(
; GFX1100-SAME: ptr addrspace(1) [[PTR:%.*]], i16 [[VALUE:%.*]]) #[[ATTR0:[0-9]+]] {
; GFX1100-NEXT: [[ALIGNEDADDR:%.*]] = call ptr addrspace(1) @llvm.ptrmask.p1.i64(ptr addrspace(1) [[PTR]], i64 -4)
; GFX1100-NEXT: [[TMP1:%.*]] = ptrtoint ptr addrspace(1) [[PTR]] to i64
; GFX1100-NEXT: [[PTRLSB:%.*]] = and i64 [[TMP1]], 3
; GFX1100-NEXT: [[TMP2:%.*]] = shl i64 [[PTRLSB]], 3
; GFX1100-NEXT: [[SHIFTAMT:%.*]] = trunc i64 [[TMP2]] to i32
; GFX1100-NEXT: [[MASK:%.*]] = shl i32 65535, [[SHIFTAMT]]
; GFX1100-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
; GFX1100-NEXT: [[TMP3:%.*]] = zext i16 [[VALUE]] to i32
; GFX1100-NEXT: [[VALOPERAND_SHIFTED:%.*]] = shl i32 [[TMP3]], [[SHIFTAMT]]
; GFX1100-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(1) [[ALIGNEDADDR]], align 4, !mmra [[META0:![0-9]+]]
; GFX1100-NEXT: br label [[ATOMICRMW_START:%.*]]
; GFX1100: atomicrmw.start:
; GFX1100-NEXT: [[LOADED:%.*]] = phi i32 [ [[TMP4]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
; GFX1100-NEXT: [[TMP5:%.*]] = and i32 [[LOADED]], [[INV_MASK]]
; GFX1100-NEXT: [[TMP6:%.*]] = or i32 [[TMP5]], [[VALOPERAND_SHIFTED]]
; GFX1100-NEXT: [[TMP7:%.*]] = cmpxchg ptr addrspace(1) [[ALIGNEDADDR]], i32 [[LOADED]], i32 [[TMP6]] syncscope("agent") seq_cst seq_cst, align 4, !mmra [[META0]]
; GFX1100-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP7]], 1
; GFX1100-NEXT: [[NEWLOADED]] = extractvalue { i32, i1 } [[TMP7]], 0
; GFX1100-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
; GFX1100: atomicrmw.end:
; GFX1100-NEXT: [[SHIFTED:%.*]] = lshr i32 [[NEWLOADED]], [[SHIFTAMT]]
; GFX1100-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
; GFX1100-NEXT: ret i16 [[EXTRACTED]]
;
%res = atomicrmw xchg ptr addrspace(1) %ptr, i16 %value syncscope("agent") seq_cst, !mmra !2
ret i16 %res
}
define i16 @test_cmpxchg_i16_global_agent_align4(ptr addrspace(1) %out, i16 %in, i16 %old) {
; GFX90A-LABEL: define i16 @test_cmpxchg_i16_global_agent_align4(
; GFX90A-SAME: ptr addrspace(1) [[OUT:%.*]], i16 [[IN:%.*]], i16 [[OLD:%.*]]) #[[ATTR0]] {
; GFX90A-NEXT: [[GEP:%.*]] = getelementptr i16, ptr addrspace(1) [[OUT]], i64 4
; GFX90A-NEXT: [[TMP1:%.*]] = zext i16 [[IN]] to i32
; GFX90A-NEXT: [[TMP2:%.*]] = zext i16 [[OLD]] to i32
; GFX90A-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(1) [[GEP]], align 4, !mmra [[META0]]
; GFX90A-NEXT: [[TMP4:%.*]] = and i32 [[TMP3]], -65536
; GFX90A-NEXT: br label [[PARTWORD_CMPXCHG_LOOP:%.*]]
; GFX90A: partword.cmpxchg.loop:
; GFX90A-NEXT: [[TMP5:%.*]] = phi i32 [ [[TMP4]], [[TMP0:%.*]] ], [ [[TMP11:%.*]], [[PARTWORD_CMPXCHG_FAILURE:%.*]] ]
; GFX90A-NEXT: [[TMP6:%.*]] = or i32 [[TMP5]], [[TMP1]]
; GFX90A-NEXT: [[TMP7:%.*]] = or i32 [[TMP5]], [[TMP2]]
; GFX90A-NEXT: [[TMP8:%.*]] = cmpxchg ptr addrspace(1) [[GEP]], i32 [[TMP7]], i32 [[TMP6]] seq_cst seq_cst, align 4, !mmra [[META0]]
; GFX90A-NEXT: [[TMP9:%.*]] = extractvalue { i32, i1 } [[TMP8]], 0
; GFX90A-NEXT: [[TMP10:%.*]] = extractvalue { i32, i1 } [[TMP8]], 1
; GFX90A-NEXT: br i1 [[TMP10]], label [[PARTWORD_CMPXCHG_END:%.*]], label [[PARTWORD_CMPXCHG_FAILURE]]
; GFX90A: partword.cmpxchg.failure:
; GFX90A-NEXT: [[TMP11]] = and i32 [[TMP9]], -65536
; GFX90A-NEXT: [[TMP12:%.*]] = icmp ne i32 [[TMP5]], [[TMP11]]
; GFX90A-NEXT: br i1 [[TMP12]], label [[PARTWORD_CMPXCHG_LOOP]], label [[PARTWORD_CMPXCHG_END]]
; GFX90A: partword.cmpxchg.end:
; GFX90A-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[TMP9]] to i16
; GFX90A-NEXT: [[TMP13:%.*]] = insertvalue { i16, i1 } poison, i16 [[EXTRACTED]], 0
; GFX90A-NEXT: [[TMP14:%.*]] = insertvalue { i16, i1 } [[TMP13]], i1 [[TMP10]], 1
; GFX90A-NEXT: [[EXTRACT:%.*]] = extractvalue { i16, i1 } [[TMP14]], 0
; GFX90A-NEXT: ret i16 [[EXTRACT]]
;
; GFX1100-LABEL: define i16 @test_cmpxchg_i16_global_agent_align4(
; GFX1100-SAME: ptr addrspace(1) [[OUT:%.*]], i16 [[IN:%.*]], i16 [[OLD:%.*]]) #[[ATTR0]] {
; GFX1100-NEXT: [[GEP:%.*]] = getelementptr i16, ptr addrspace(1) [[OUT]], i64 4
; GFX1100-NEXT: [[TMP1:%.*]] = zext i16 [[IN]] to i32
; GFX1100-NEXT: [[TMP2:%.*]] = zext i16 [[OLD]] to i32
; GFX1100-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(1) [[GEP]], align 4, !mmra [[META0]]
; GFX1100-NEXT: [[TMP4:%.*]] = and i32 [[TMP3]], -65536
; GFX1100-NEXT: br label [[PARTWORD_CMPXCHG_LOOP:%.*]]
; GFX1100: partword.cmpxchg.loop:
; GFX1100-NEXT: [[TMP5:%.*]] = phi i32 [ [[TMP4]], [[TMP0:%.*]] ], [ [[TMP11:%.*]], [[PARTWORD_CMPXCHG_FAILURE:%.*]] ]
; GFX1100-NEXT: [[TMP6:%.*]] = or i32 [[TMP5]], [[TMP1]]
; GFX1100-NEXT: [[TMP7:%.*]] = or i32 [[TMP5]], [[TMP2]]
; GFX1100-NEXT: [[TMP8:%.*]] = cmpxchg ptr addrspace(1) [[GEP]], i32 [[TMP7]], i32 [[TMP6]] seq_cst seq_cst, align 4, !mmra [[META0]]
; GFX1100-NEXT: [[TMP9:%.*]] = extractvalue { i32, i1 } [[TMP8]], 0
; GFX1100-NEXT: [[TMP10:%.*]] = extractvalue { i32, i1 } [[TMP8]], 1
; GFX1100-NEXT: br i1 [[TMP10]], label [[PARTWORD_CMPXCHG_END:%.*]], label [[PARTWORD_CMPXCHG_FAILURE]]
; GFX1100: partword.cmpxchg.failure:
; GFX1100-NEXT: [[TMP11]] = and i32 [[TMP9]], -65536
; GFX1100-NEXT: [[TMP12:%.*]] = icmp ne i32 [[TMP5]], [[TMP11]]
; GFX1100-NEXT: br i1 [[TMP12]], label [[PARTWORD_CMPXCHG_LOOP]], label [[PARTWORD_CMPXCHG_END]]
; GFX1100: partword.cmpxchg.end:
; GFX1100-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[TMP9]] to i16
; GFX1100-NEXT: [[TMP13:%.*]] = insertvalue { i16, i1 } poison, i16 [[EXTRACTED]], 0
; GFX1100-NEXT: [[TMP14:%.*]] = insertvalue { i16, i1 } [[TMP13]], i1 [[TMP10]], 1
; GFX1100-NEXT: [[EXTRACT:%.*]] = extractvalue { i16, i1 } [[TMP14]], 0
; GFX1100-NEXT: ret i16 [[EXTRACT]]
;
%gep = getelementptr i16, ptr addrspace(1) %out, i64 4
%res = cmpxchg ptr addrspace(1) %gep, i16 %old, i16 %in seq_cst seq_cst, align 4, !mmra !2
%extract = extractvalue {i16, i1} %res, 0
ret i16 %extract
}
define void @syncscope_workgroup_nortn(ptr %addr, float %val) {
; GFX90A-LABEL: define void @syncscope_workgroup_nortn(
; GFX90A-SAME: ptr [[ADDR:%.*]], float [[VAL:%.*]]) #[[ATTR1:[0-9]+]] {
; GFX90A-NEXT: [[IS_SHARED:%.*]] = call i1 @llvm.amdgcn.is.shared(ptr [[ADDR]])
; GFX90A-NEXT: br i1 [[IS_SHARED]], label [[ATOMICRMW_SHARED:%.*]], label [[ATOMICRMW_CHECK_PRIVATE:%.*]]
; GFX90A: atomicrmw.shared:
; GFX90A-NEXT: [[TMP1:%.*]] = addrspacecast ptr [[ADDR]] to ptr addrspace(3)
; GFX90A-NEXT: [[TMP2:%.*]] = atomicrmw fadd ptr addrspace(3) [[TMP1]], float [[VAL]] syncscope("workgroup") seq_cst, align 4, !mmra [[META0]]
; GFX90A-NEXT: br label [[ATOMICRMW_PHI:%.*]]
; GFX90A: atomicrmw.check.private:
; GFX90A-NEXT: [[IS_PRIVATE:%.*]] = call i1 @llvm.amdgcn.is.private(ptr [[ADDR]])
; GFX90A-NEXT: br i1 [[IS_PRIVATE]], label [[ATOMICRMW_PRIVATE:%.*]], label [[ATOMICRMW_GLOBAL:%.*]]
; GFX90A: atomicrmw.private:
; GFX90A-NEXT: [[TMP3:%.*]] = addrspacecast ptr [[ADDR]] to ptr addrspace(5)
; GFX90A-NEXT: [[LOADED_PRIVATE:%.*]] = load float, ptr addrspace(5) [[TMP3]], align 4
; GFX90A-NEXT: [[VAL_NEW:%.*]] = fadd float [[LOADED_PRIVATE]], [[VAL]]
; GFX90A-NEXT: store float [[VAL_NEW]], ptr addrspace(5) [[TMP3]], align 4
; GFX90A-NEXT: br label [[ATOMICRMW_PHI]]
; GFX90A: atomicrmw.global:
; GFX90A-NEXT: [[TMP4:%.*]] = addrspacecast ptr [[ADDR]] to ptr addrspace(1)
; GFX90A-NEXT: [[TMP5:%.*]] = atomicrmw fadd ptr addrspace(1) [[TMP4]], float [[VAL]] syncscope("workgroup") seq_cst, align 4, !mmra [[META0]]
; GFX90A-NEXT: br label [[ATOMICRMW_PHI]]
; GFX90A: atomicrmw.phi:
; GFX90A-NEXT: br label [[ATOMICRMW_END:%.*]]
; GFX90A: atomicrmw.end:
; GFX90A-NEXT: ret void
;
; GFX1100-LABEL: define void @syncscope_workgroup_nortn(
; GFX1100-SAME: ptr [[ADDR:%.*]], float [[VAL:%.*]]) #[[ATTR1:[0-9]+]] {
; GFX1100-NEXT: [[RES:%.*]] = atomicrmw fadd ptr [[ADDR]], float [[VAL]] syncscope("workgroup") seq_cst, align 4, !mmra [[META0]]
; GFX1100-NEXT: ret void
;
%res = atomicrmw fadd ptr %addr, float %val syncscope("workgroup") seq_cst, !mmra !2, !amdgpu.no.fine.grained.memory !3, !amdgpu.ignore.denormal.mode !3
ret void
}
define i32 @atomic_load_global_align1(ptr addrspace(1) %ptr) {
; GFX90A-LABEL: define i32 @atomic_load_global_align1(
; GFX90A-SAME: ptr addrspace(1) [[PTR:%.*]]) #[[ATTR0]] {
; GFX90A-NEXT: [[TMP1:%.*]] = addrspacecast ptr addrspace(1) [[PTR]] to ptr
; GFX90A-NEXT: [[TMP2:%.*]] = alloca i32, align 4, addrspace(5)
; GFX90A-NEXT: call void @llvm.lifetime.start.p5(i64 4, ptr addrspace(5) [[TMP2]])
; GFX90A-NEXT: call void @__atomic_load(i64 4, ptr [[TMP1]], ptr addrspace(5) [[TMP2]], i32 5)
; GFX90A-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(5) [[TMP2]], align 4
; GFX90A-NEXT: call void @llvm.lifetime.end.p5(i64 4, ptr addrspace(5) [[TMP2]])
; GFX90A-NEXT: ret i32 [[TMP3]]
;
; GFX1100-LABEL: define i32 @atomic_load_global_align1(
; GFX1100-SAME: ptr addrspace(1) [[PTR:%.*]]) #[[ATTR0]] {
; GFX1100-NEXT: [[TMP1:%.*]] = addrspacecast ptr addrspace(1) [[PTR]] to ptr
; GFX1100-NEXT: [[TMP2:%.*]] = alloca i32, align 4, addrspace(5)
; GFX1100-NEXT: call void @llvm.lifetime.start.p5(i64 4, ptr addrspace(5) [[TMP2]])
; GFX1100-NEXT: call void @__atomic_load(i64 4, ptr [[TMP1]], ptr addrspace(5) [[TMP2]], i32 5)
; GFX1100-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(5) [[TMP2]], align 4
; GFX1100-NEXT: call void @llvm.lifetime.end.p5(i64 4, ptr addrspace(5) [[TMP2]])
; GFX1100-NEXT: ret i32 [[TMP3]]
;
%val = load atomic i32, ptr addrspace(1) %ptr seq_cst, align 1, !mmra !2
ret i32 %val
}
!0 = !{!"foo", !"bar"}
!1 = !{!"bux", !"baz"}
!2 = !{!0, !1}
!3 = !{}
;.
; GFX90A: [[META0]] = !{[[META1:![0-9]+]], [[META2:![0-9]+]]}
; GFX90A: [[META1]] = !{!"foo", !"bar"}
; GFX90A: [[META2]] = !{!"bux", !"baz"}
;.
; GFX1100: [[META0]] = !{[[META1:![0-9]+]], [[META2:![0-9]+]]}
; GFX1100: [[META1]] = !{!"foo", !"bar"}
; GFX1100: [[META2]] = !{!"bux", !"baz"}
;.