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
178 lines
11 KiB
LLVM
178 lines
11 KiB
LLVM
; 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:%.*]]) #[[ATTR0]] {
|
|
; 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]], !amdgpu.no.fine.grained.memory [[META3:![0-9]+]], !amdgpu.ignore.denormal.mode [[META3]]
|
|
; 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: [[RES:%.*]] = atomicrmw fadd ptr addrspace(1) [[TMP4]], float [[VAL]] syncscope("workgroup") seq_cst, align 4, !mmra [[META0]], !amdgpu.no.fine.grained.memory [[META3]], !amdgpu.ignore.denormal.mode [[META3]]
|
|
; 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:%.*]]) #[[ATTR0]] {
|
|
; GFX1100-NEXT: [[RES:%.*]] = atomicrmw fadd ptr [[ADDR]], float [[VAL]] syncscope("workgroup") seq_cst, align 4, !mmra [[META0]], !amdgpu.no.fine.grained.memory [[META3:![0-9]+]], !amdgpu.ignore.denormal.mode [[META3]]
|
|
; 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
|
|
}
|
|
|
|
!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"}
|
|
; GFX90A: [[META3]] = !{}
|
|
;.
|
|
; GFX1100: [[META0]] = !{[[META1:![0-9]+]], [[META2:![0-9]+]]}
|
|
; GFX1100: [[META1]] = !{!"foo", !"bar"}
|
|
; GFX1100: [[META2]] = !{!"bux", !"baz"}
|
|
; GFX1100: [[META3]] = !{}
|
|
;.
|