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
301 lines
17 KiB
LLVM
301 lines
17 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -mcpu=hawaii -passes='require<libcall-lowering-info>,atomic-expand' %s | FileCheck -check-prefixes=GCN,GFX7 %s
|
|
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -passes='require<libcall-lowering-info>,atomic-expand' %s | FileCheck -check-prefixes=GCN,GFX9 %s
|
|
|
|
define float @test_atomicrmw_fmax_f32_flat(ptr %ptr, float %value) {
|
|
; GCN-LABEL: @test_atomicrmw_fmax_f32_flat(
|
|
; GCN-NEXT: [[TMP1:%.*]] = load float, ptr [[PTR:%.*]], align 4
|
|
; GCN-NEXT: br label [[ATOMICRMW_START:%.*]]
|
|
; GCN: atomicrmw.start:
|
|
; GCN-NEXT: [[LOADED:%.*]] = phi float [ [[TMP1]], [[TMP0:%.*]] ], [ [[TMP6:%.*]], [[ATOMICRMW_START]] ]
|
|
; GCN-NEXT: [[TMP2:%.*]] = call float @llvm.maxnum.f32(float [[LOADED]], float [[VALUE:%.*]])
|
|
; GCN-NEXT: [[TMP3:%.*]] = bitcast float [[TMP2]] to i32
|
|
; GCN-NEXT: [[TMP4:%.*]] = bitcast float [[LOADED]] to i32
|
|
; GCN-NEXT: [[TMP5:%.*]] = cmpxchg ptr [[PTR]], i32 [[TMP4]], i32 [[TMP3]] seq_cst seq_cst, align 4
|
|
; GCN-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP5]], 1
|
|
; GCN-NEXT: [[NEWLOADED:%.*]] = extractvalue { i32, i1 } [[TMP5]], 0
|
|
; GCN-NEXT: [[TMP6]] = bitcast i32 [[NEWLOADED]] to float
|
|
; GCN-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
|
|
; GCN: atomicrmw.end:
|
|
; GCN-NEXT: ret float [[TMP6]]
|
|
;
|
|
%res = atomicrmw fmax ptr %ptr, float %value seq_cst
|
|
ret float %res
|
|
}
|
|
|
|
define float @test_atomicrmw_fmax_f32_global(ptr addrspace(1) %ptr, float %value) {
|
|
; GCN-LABEL: @test_atomicrmw_fmax_f32_global(
|
|
; GCN-NEXT: [[TMP1:%.*]] = load float, ptr addrspace(1) [[PTR:%.*]], align 4
|
|
; GCN-NEXT: br label [[ATOMICRMW_START:%.*]]
|
|
; GCN: atomicrmw.start:
|
|
; GCN-NEXT: [[LOADED:%.*]] = phi float [ [[TMP1]], [[TMP0:%.*]] ], [ [[TMP6:%.*]], [[ATOMICRMW_START]] ]
|
|
; GCN-NEXT: [[TMP2:%.*]] = call float @llvm.maxnum.f32(float [[LOADED]], float [[VALUE:%.*]])
|
|
; GCN-NEXT: [[TMP3:%.*]] = bitcast float [[TMP2]] to i32
|
|
; GCN-NEXT: [[TMP4:%.*]] = bitcast float [[LOADED]] to i32
|
|
; GCN-NEXT: [[TMP5:%.*]] = cmpxchg ptr addrspace(1) [[PTR]], i32 [[TMP4]], i32 [[TMP3]] seq_cst seq_cst, align 4
|
|
; GCN-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP5]], 1
|
|
; GCN-NEXT: [[NEWLOADED:%.*]] = extractvalue { i32, i1 } [[TMP5]], 0
|
|
; GCN-NEXT: [[TMP6]] = bitcast i32 [[NEWLOADED]] to float
|
|
; GCN-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
|
|
; GCN: atomicrmw.end:
|
|
; GCN-NEXT: ret float [[TMP6]]
|
|
;
|
|
%res = atomicrmw fmax ptr addrspace(1) %ptr, float %value seq_cst
|
|
ret float %res
|
|
}
|
|
|
|
define float @test_atomicrmw_fmax_f32_local(ptr addrspace(3) %ptr, float %value) {
|
|
; GCN-LABEL: @test_atomicrmw_fmax_f32_local(
|
|
; GCN-NEXT: [[RES:%.*]] = atomicrmw fmax ptr addrspace(3) [[PTR:%.*]], float [[VALUE:%.*]] seq_cst, align 4
|
|
; GCN-NEXT: ret float [[RES]]
|
|
;
|
|
%res = atomicrmw fmax ptr addrspace(3) %ptr, float %value seq_cst
|
|
ret float %res
|
|
}
|
|
|
|
define half @test_atomicrmw_fmax_f16_flat(ptr %ptr, half %value) {
|
|
; GCN-LABEL: @test_atomicrmw_fmax_f16_flat(
|
|
; GCN-NEXT: [[ALIGNEDADDR:%.*]] = call ptr @llvm.ptrmask.p0.i64(ptr [[PTR:%.*]], i64 -4)
|
|
; GCN-NEXT: [[TMP1:%.*]] = ptrtoint ptr [[PTR]] to i64
|
|
; GCN-NEXT: [[PTRLSB:%.*]] = and i64 [[TMP1]], 3
|
|
; GCN-NEXT: [[TMP2:%.*]] = shl i64 [[PTRLSB]], 3
|
|
; GCN-NEXT: [[SHIFTAMT:%.*]] = trunc i64 [[TMP2]] to i32
|
|
; GCN-NEXT: [[MASK:%.*]] = shl i32 65535, [[SHIFTAMT]]
|
|
; GCN-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
|
|
; GCN-NEXT: [[TMP3:%.*]] = load i32, ptr [[ALIGNEDADDR]], align 4
|
|
; GCN-NEXT: br label [[ATOMICRMW_START:%.*]]
|
|
; GCN: atomicrmw.start:
|
|
; GCN-NEXT: [[LOADED:%.*]] = phi i32 [ [[TMP3]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
|
|
; GCN-NEXT: [[SHIFTED:%.*]] = lshr i32 [[LOADED]], [[SHIFTAMT]]
|
|
; GCN-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
|
|
; GCN-NEXT: [[TMP4:%.*]] = bitcast i16 [[EXTRACTED]] to half
|
|
; GCN-NEXT: [[TMP5:%.*]] = call half @llvm.maxnum.f16(half [[TMP4]], half [[VALUE:%.*]])
|
|
; GCN-NEXT: [[TMP6:%.*]] = bitcast half [[TMP5]] to i16
|
|
; GCN-NEXT: [[EXTENDED:%.*]] = zext i16 [[TMP6]] to i32
|
|
; GCN-NEXT: [[SHIFTED1:%.*]] = shl nuw i32 [[EXTENDED]], [[SHIFTAMT]]
|
|
; GCN-NEXT: [[UNMASKED:%.*]] = and i32 [[LOADED]], [[INV_MASK]]
|
|
; GCN-NEXT: [[INSERTED:%.*]] = or i32 [[UNMASKED]], [[SHIFTED1]]
|
|
; GCN-NEXT: [[TMP7:%.*]] = cmpxchg ptr [[ALIGNEDADDR]], i32 [[LOADED]], i32 [[INSERTED]] seq_cst seq_cst, align 4
|
|
; GCN-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP7]], 1
|
|
; GCN-NEXT: [[NEWLOADED]] = extractvalue { i32, i1 } [[TMP7]], 0
|
|
; GCN-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
|
|
; GCN: atomicrmw.end:
|
|
; GCN-NEXT: [[SHIFTED2:%.*]] = lshr i32 [[NEWLOADED]], [[SHIFTAMT]]
|
|
; GCN-NEXT: [[EXTRACTED3:%.*]] = trunc i32 [[SHIFTED2]] to i16
|
|
; GCN-NEXT: [[TMP8:%.*]] = bitcast i16 [[EXTRACTED3]] to half
|
|
; GCN-NEXT: ret half [[TMP8]]
|
|
;
|
|
%res = atomicrmw fmax ptr %ptr, half %value seq_cst
|
|
ret half %res
|
|
}
|
|
|
|
define half @test_atomicrmw_fmax_f16_global(ptr addrspace(1) %ptr, half %value) {
|
|
; GCN-LABEL: @test_atomicrmw_fmax_f16_global(
|
|
; GCN-NEXT: [[ALIGNEDADDR:%.*]] = call ptr addrspace(1) @llvm.ptrmask.p1.i64(ptr addrspace(1) [[PTR:%.*]], i64 -4)
|
|
; GCN-NEXT: [[TMP1:%.*]] = ptrtoint ptr addrspace(1) [[PTR]] to i64
|
|
; GCN-NEXT: [[PTRLSB:%.*]] = and i64 [[TMP1]], 3
|
|
; GCN-NEXT: [[TMP2:%.*]] = shl i64 [[PTRLSB]], 3
|
|
; GCN-NEXT: [[SHIFTAMT:%.*]] = trunc i64 [[TMP2]] to i32
|
|
; GCN-NEXT: [[MASK:%.*]] = shl i32 65535, [[SHIFTAMT]]
|
|
; GCN-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
|
|
; GCN-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(1) [[ALIGNEDADDR]], align 4
|
|
; GCN-NEXT: br label [[ATOMICRMW_START:%.*]]
|
|
; GCN: atomicrmw.start:
|
|
; GCN-NEXT: [[LOADED:%.*]] = phi i32 [ [[TMP3]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
|
|
; GCN-NEXT: [[SHIFTED:%.*]] = lshr i32 [[LOADED]], [[SHIFTAMT]]
|
|
; GCN-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
|
|
; GCN-NEXT: [[TMP4:%.*]] = bitcast i16 [[EXTRACTED]] to half
|
|
; GCN-NEXT: [[TMP5:%.*]] = call half @llvm.maxnum.f16(half [[TMP4]], half [[VALUE:%.*]])
|
|
; GCN-NEXT: [[TMP6:%.*]] = bitcast half [[TMP5]] to i16
|
|
; GCN-NEXT: [[EXTENDED:%.*]] = zext i16 [[TMP6]] to i32
|
|
; GCN-NEXT: [[SHIFTED1:%.*]] = shl nuw i32 [[EXTENDED]], [[SHIFTAMT]]
|
|
; GCN-NEXT: [[UNMASKED:%.*]] = and i32 [[LOADED]], [[INV_MASK]]
|
|
; GCN-NEXT: [[INSERTED:%.*]] = or i32 [[UNMASKED]], [[SHIFTED1]]
|
|
; GCN-NEXT: [[TMP7:%.*]] = cmpxchg ptr addrspace(1) [[ALIGNEDADDR]], i32 [[LOADED]], i32 [[INSERTED]] seq_cst seq_cst, align 4
|
|
; GCN-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP7]], 1
|
|
; GCN-NEXT: [[NEWLOADED]] = extractvalue { i32, i1 } [[TMP7]], 0
|
|
; GCN-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
|
|
; GCN: atomicrmw.end:
|
|
; GCN-NEXT: [[SHIFTED2:%.*]] = lshr i32 [[NEWLOADED]], [[SHIFTAMT]]
|
|
; GCN-NEXT: [[EXTRACTED3:%.*]] = trunc i32 [[SHIFTED2]] to i16
|
|
; GCN-NEXT: [[TMP8:%.*]] = bitcast i16 [[EXTRACTED3]] to half
|
|
; GCN-NEXT: ret half [[TMP8]]
|
|
;
|
|
%res = atomicrmw fmax ptr addrspace(1) %ptr, half %value seq_cst
|
|
ret half %res
|
|
}
|
|
|
|
define half @test_atomicrmw_fmax_f16_global_align4(ptr addrspace(1) %ptr, half %value) {
|
|
; GCN-LABEL: @test_atomicrmw_fmax_f16_global_align4(
|
|
; GCN-NEXT: [[TMP1:%.*]] = load i32, ptr addrspace(1) [[PTR:%.*]], align 4
|
|
; GCN-NEXT: br label [[ATOMICRMW_START:%.*]]
|
|
; GCN: atomicrmw.start:
|
|
; GCN-NEXT: [[LOADED:%.*]] = phi i32 [ [[TMP1]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
|
|
; GCN-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[LOADED]] to i16
|
|
; GCN-NEXT: [[TMP2:%.*]] = bitcast i16 [[EXTRACTED]] to half
|
|
; GCN-NEXT: [[TMP3:%.*]] = call half @llvm.maxnum.f16(half [[TMP2]], half [[VALUE:%.*]])
|
|
; GCN-NEXT: [[TMP4:%.*]] = bitcast half [[TMP3]] to i16
|
|
; GCN-NEXT: [[EXTENDED:%.*]] = zext i16 [[TMP4]] to i32
|
|
; GCN-NEXT: [[UNMASKED:%.*]] = and i32 [[LOADED]], -65536
|
|
; GCN-NEXT: [[INSERTED:%.*]] = or i32 [[UNMASKED]], [[EXTENDED]]
|
|
; GCN-NEXT: [[TMP5:%.*]] = cmpxchg ptr addrspace(1) [[PTR]], i32 [[LOADED]], i32 [[INSERTED]] seq_cst seq_cst, align 4
|
|
; GCN-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP5]], 1
|
|
; GCN-NEXT: [[NEWLOADED]] = extractvalue { i32, i1 } [[TMP5]], 0
|
|
; GCN-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
|
|
; GCN: atomicrmw.end:
|
|
; GCN-NEXT: [[EXTRACTED1:%.*]] = trunc i32 [[NEWLOADED]] to i16
|
|
; GCN-NEXT: [[TMP6:%.*]] = bitcast i16 [[EXTRACTED1]] to half
|
|
; GCN-NEXT: ret half [[TMP6]]
|
|
;
|
|
%res = atomicrmw fmax ptr addrspace(1) %ptr, half %value seq_cst, align 4
|
|
ret half %res
|
|
}
|
|
|
|
define half @test_atomicrmw_fmax_f16_local(ptr addrspace(3) %ptr, half %value) {
|
|
; GCN-LABEL: @test_atomicrmw_fmax_f16_local(
|
|
; GCN-NEXT: [[ALIGNEDADDR:%.*]] = call ptr addrspace(3) @llvm.ptrmask.p3.i32(ptr addrspace(3) [[PTR:%.*]], i32 -4)
|
|
; GCN-NEXT: [[TMP1:%.*]] = ptrtoint ptr addrspace(3) [[PTR]] to i32
|
|
; GCN-NEXT: [[PTRLSB:%.*]] = and i32 [[TMP1]], 3
|
|
; GCN-NEXT: [[TMP2:%.*]] = shl i32 [[PTRLSB]], 3
|
|
; GCN-NEXT: [[MASK:%.*]] = shl i32 65535, [[TMP2]]
|
|
; GCN-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
|
|
; GCN-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(3) [[ALIGNEDADDR]], align 4
|
|
; GCN-NEXT: br label [[ATOMICRMW_START:%.*]]
|
|
; GCN: atomicrmw.start:
|
|
; GCN-NEXT: [[LOADED:%.*]] = phi i32 [ [[TMP3]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
|
|
; GCN-NEXT: [[SHIFTED:%.*]] = lshr i32 [[LOADED]], [[TMP2]]
|
|
; GCN-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
|
|
; GCN-NEXT: [[TMP4:%.*]] = bitcast i16 [[EXTRACTED]] to half
|
|
; GCN-NEXT: [[TMP5:%.*]] = call half @llvm.maxnum.f16(half [[TMP4]], half [[VALUE:%.*]])
|
|
; GCN-NEXT: [[TMP6:%.*]] = bitcast half [[TMP5]] to i16
|
|
; GCN-NEXT: [[EXTENDED:%.*]] = zext i16 [[TMP6]] to i32
|
|
; GCN-NEXT: [[SHIFTED1:%.*]] = shl nuw i32 [[EXTENDED]], [[TMP2]]
|
|
; GCN-NEXT: [[UNMASKED:%.*]] = and i32 [[LOADED]], [[INV_MASK]]
|
|
; GCN-NEXT: [[INSERTED:%.*]] = or i32 [[UNMASKED]], [[SHIFTED1]]
|
|
; GCN-NEXT: [[TMP7:%.*]] = cmpxchg ptr addrspace(3) [[ALIGNEDADDR]], i32 [[LOADED]], i32 [[INSERTED]] seq_cst seq_cst, align 4
|
|
; GCN-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP7]], 1
|
|
; GCN-NEXT: [[NEWLOADED]] = extractvalue { i32, i1 } [[TMP7]], 0
|
|
; GCN-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
|
|
; GCN: atomicrmw.end:
|
|
; GCN-NEXT: [[SHIFTED2:%.*]] = lshr i32 [[NEWLOADED]], [[TMP2]]
|
|
; GCN-NEXT: [[EXTRACTED3:%.*]] = trunc i32 [[SHIFTED2]] to i16
|
|
; GCN-NEXT: [[TMP8:%.*]] = bitcast i16 [[EXTRACTED3]] to half
|
|
; GCN-NEXT: ret half [[TMP8]]
|
|
;
|
|
%res = atomicrmw fmax ptr addrspace(3) %ptr, half %value seq_cst
|
|
ret half %res
|
|
}
|
|
|
|
define double @test_atomicrmw_fmax_f64_flat(ptr %ptr, double %value) {
|
|
; GCN-LABEL: @test_atomicrmw_fmax_f64_flat(
|
|
; GCN-NEXT: [[IS_PRIVATE:%.*]] = call i1 @llvm.amdgcn.is.private(ptr [[PTR:%.*]])
|
|
; GCN-NEXT: br i1 [[IS_PRIVATE]], label [[ATOMICRMW_PRIVATE:%.*]], label [[ATOMICRMW_GLOBAL:%.*]]
|
|
; GCN: atomicrmw.private:
|
|
; GCN-NEXT: [[TMP1:%.*]] = addrspacecast ptr [[PTR]] to ptr addrspace(5)
|
|
; GCN-NEXT: [[LOADED_PRIVATE:%.*]] = load double, ptr addrspace(5) [[TMP1]], align 8
|
|
; GCN-NEXT: [[TMP2:%.*]] = call double @llvm.maxnum.f64(double [[LOADED_PRIVATE]], double [[VALUE:%.*]])
|
|
; GCN-NEXT: store double [[TMP2]], ptr addrspace(5) [[TMP1]], align 8
|
|
; GCN-NEXT: br label [[ATOMICRMW_PHI:%.*]]
|
|
; GCN: atomicrmw.global:
|
|
; GCN-NEXT: [[TMP3:%.*]] = load double, ptr [[PTR]], align 8
|
|
; GCN-NEXT: br label [[ATOMICRMW_START:%.*]]
|
|
; GCN: atomicrmw.start:
|
|
; GCN-NEXT: [[LOADED:%.*]] = phi double [ [[TMP3]], [[ATOMICRMW_GLOBAL]] ], [ [[TMP8:%.*]], [[ATOMICRMW_START]] ]
|
|
; GCN-NEXT: [[TMP4:%.*]] = call double @llvm.maxnum.f64(double [[LOADED]], double [[VALUE]])
|
|
; GCN-NEXT: [[TMP5:%.*]] = bitcast double [[TMP4]] to i64
|
|
; GCN-NEXT: [[TMP6:%.*]] = bitcast double [[LOADED]] to i64
|
|
; GCN-NEXT: [[TMP7:%.*]] = cmpxchg ptr [[PTR]], i64 [[TMP6]], i64 [[TMP5]] seq_cst seq_cst, align 8, !noalias.addrspace [[META0:![0-9]+]]
|
|
; GCN-NEXT: [[SUCCESS:%.*]] = extractvalue { i64, i1 } [[TMP7]], 1
|
|
; GCN-NEXT: [[NEWLOADED:%.*]] = extractvalue { i64, i1 } [[TMP7]], 0
|
|
; GCN-NEXT: [[TMP8]] = bitcast i64 [[NEWLOADED]] to double
|
|
; GCN-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END1:%.*]], label [[ATOMICRMW_START]]
|
|
; GCN: atomicrmw.end1:
|
|
; GCN-NEXT: br label [[ATOMICRMW_PHI]]
|
|
; GCN: atomicrmw.phi:
|
|
; GCN-NEXT: [[RES:%.*]] = phi double [ [[LOADED_PRIVATE]], [[ATOMICRMW_PRIVATE]] ], [ [[TMP8]], [[ATOMICRMW_END1]] ]
|
|
; GCN-NEXT: br label [[ATOMICRMW_END:%.*]]
|
|
; GCN: atomicrmw.end:
|
|
; GCN-NEXT: ret double [[RES]]
|
|
;
|
|
%res = atomicrmw fmax ptr %ptr, double %value seq_cst
|
|
ret double %res
|
|
}
|
|
|
|
define double @test_atomicrmw_fmax_f64_flat__noprivate(ptr %ptr, double %value) {
|
|
; GCN-LABEL: @test_atomicrmw_fmax_f64_flat__noprivate(
|
|
; GCN-NEXT: [[TMP1:%.*]] = load double, ptr [[PTR:%.*]], align 8
|
|
; GCN-NEXT: br label [[ATOMICRMW_START:%.*]]
|
|
; GCN: atomicrmw.start:
|
|
; GCN-NEXT: [[LOADED:%.*]] = phi double [ [[TMP1]], [[TMP0:%.*]] ], [ [[TMP6:%.*]], [[ATOMICRMW_START]] ]
|
|
; GCN-NEXT: [[TMP2:%.*]] = call double @llvm.maxnum.f64(double [[LOADED]], double [[VALUE:%.*]])
|
|
; GCN-NEXT: [[TMP3:%.*]] = bitcast double [[TMP2]] to i64
|
|
; GCN-NEXT: [[TMP4:%.*]] = bitcast double [[LOADED]] to i64
|
|
; GCN-NEXT: [[TMP5:%.*]] = cmpxchg ptr [[PTR]], i64 [[TMP4]], i64 [[TMP3]] seq_cst seq_cst, align 8, !noalias.addrspace [[META0]]
|
|
; GCN-NEXT: [[SUCCESS:%.*]] = extractvalue { i64, i1 } [[TMP5]], 1
|
|
; GCN-NEXT: [[NEWLOADED:%.*]] = extractvalue { i64, i1 } [[TMP5]], 0
|
|
; GCN-NEXT: [[TMP6]] = bitcast i64 [[NEWLOADED]] to double
|
|
; GCN-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
|
|
; GCN: atomicrmw.end:
|
|
; GCN-NEXT: ret double [[TMP6]]
|
|
;
|
|
%res = atomicrmw fmax ptr %ptr, double %value seq_cst, !noalias.addrspace !0
|
|
ret double %res
|
|
}
|
|
|
|
define double @test_atomicrmw_fmax_f64_global(ptr addrspace(1) %ptr, double %value) {
|
|
; GCN-LABEL: @test_atomicrmw_fmax_f64_global(
|
|
; GCN-NEXT: [[TMP1:%.*]] = load double, ptr addrspace(1) [[PTR:%.*]], align 8
|
|
; GCN-NEXT: br label [[ATOMICRMW_START:%.*]]
|
|
; GCN: atomicrmw.start:
|
|
; GCN-NEXT: [[LOADED:%.*]] = phi double [ [[TMP1]], [[TMP0:%.*]] ], [ [[TMP6:%.*]], [[ATOMICRMW_START]] ]
|
|
; GCN-NEXT: [[TMP2:%.*]] = call double @llvm.maxnum.f64(double [[LOADED]], double [[VALUE:%.*]])
|
|
; GCN-NEXT: [[TMP3:%.*]] = bitcast double [[TMP2]] to i64
|
|
; GCN-NEXT: [[TMP4:%.*]] = bitcast double [[LOADED]] to i64
|
|
; GCN-NEXT: [[TMP5:%.*]] = cmpxchg ptr addrspace(1) [[PTR]], i64 [[TMP4]], i64 [[TMP3]] seq_cst seq_cst, align 8
|
|
; GCN-NEXT: [[SUCCESS:%.*]] = extractvalue { i64, i1 } [[TMP5]], 1
|
|
; GCN-NEXT: [[NEWLOADED:%.*]] = extractvalue { i64, i1 } [[TMP5]], 0
|
|
; GCN-NEXT: [[TMP6]] = bitcast i64 [[NEWLOADED]] to double
|
|
; GCN-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
|
|
; GCN: atomicrmw.end:
|
|
; GCN-NEXT: ret double [[TMP6]]
|
|
;
|
|
%res = atomicrmw fmax ptr addrspace(1) %ptr, double %value seq_cst
|
|
ret double %res
|
|
}
|
|
|
|
define double @test_atomicrmw_fmax_f64_local(ptr addrspace(3) %ptr, double %value) {
|
|
; GCN-LABEL: @test_atomicrmw_fmax_f64_local(
|
|
; GCN-NEXT: [[RES:%.*]] = atomicrmw fmax ptr addrspace(3) [[PTR:%.*]], double [[VALUE:%.*]] seq_cst, align 8
|
|
; GCN-NEXT: ret double [[RES]]
|
|
;
|
|
%res = atomicrmw fmax ptr addrspace(3) %ptr, double %value seq_cst
|
|
ret double %res
|
|
}
|
|
|
|
define double @test_atomicrmw_fmax_f64_global_strictfp(ptr addrspace(1) %ptr, double %value) strictfp {
|
|
; GCN-LABEL: @test_atomicrmw_fmax_f64_global_strictfp(
|
|
; GCN-NEXT: [[TMP1:%.*]] = load double, ptr addrspace(1) [[PTR:%.*]], align 8
|
|
; GCN-NEXT: br label [[ATOMICRMW_START:%.*]]
|
|
; GCN: atomicrmw.start:
|
|
; GCN-NEXT: [[LOADED:%.*]] = phi double [ [[TMP1]], [[TMP0:%.*]] ], [ [[TMP6:%.*]], [[ATOMICRMW_START]] ]
|
|
; GCN-NEXT: [[TMP2:%.*]] = call double @llvm.experimental.constrained.maxnum.f64(double [[LOADED]], double [[VALUE:%.*]], metadata !"fpexcept.strict") #[[ATTR4:[0-9]+]]
|
|
; GCN-NEXT: [[TMP3:%.*]] = bitcast double [[TMP2]] to i64
|
|
; GCN-NEXT: [[TMP4:%.*]] = bitcast double [[LOADED]] to i64
|
|
; GCN-NEXT: [[TMP5:%.*]] = cmpxchg ptr addrspace(1) [[PTR]], i64 [[TMP4]], i64 [[TMP3]] seq_cst seq_cst, align 8
|
|
; GCN-NEXT: [[SUCCESS:%.*]] = extractvalue { i64, i1 } [[TMP5]], 1
|
|
; GCN-NEXT: [[NEWLOADED:%.*]] = extractvalue { i64, i1 } [[TMP5]], 0
|
|
; GCN-NEXT: [[TMP6]] = bitcast i64 [[NEWLOADED]] to double
|
|
; GCN-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
|
|
; GCN: atomicrmw.end:
|
|
; GCN-NEXT: ret double [[TMP6]]
|
|
;
|
|
%res = atomicrmw fmax ptr addrspace(1) %ptr, double %value seq_cst
|
|
ret double %res
|
|
}
|
|
|
|
!0 = !{i32 5, i32 6}
|
|
|
|
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
|
|
; GFX7: {{.*}}
|
|
; GFX9: {{.*}}
|