[clang] [NVPTX][AMDGPU][CodeGen] Fix `local_space nullptr` handling for NVPTX and local/private `nullptr` value for AMDGPU. (PR #78759)
via cfe-commits
cfe-commits at lists.llvm.org
Fri Jan 19 10:51:50 PST 2024
https://github.com/mmoadeli created https://github.com/llvm/llvm-project/pull/78759
- Address space cast of nullptr in local_space into a generic_space for the CUDA backend. The reason for this cast was having invalid local memory base address for the associated variable.
- In the context of AMD GPU, assigns a NULL value as ~0 for the address spaces of sycl_local and sycl_private to match the ones for opencl_local and opencl_private.
>From 286ac8f3ea6aec711827ccab9608b010e78b18cf Mon Sep 17 00:00:00 2001
From: m moadeli <mahmoud.moadeli at codeplay.com>
Date: Fri, 19 Jan 2024 18:42:24 +0000
Subject: [PATCH] - Address space cast of a `local_space` specialized `nullptr`
into a generic space for the CUDA backend. - In the context of AMD GPU,
assigns a NULL value of `~0` for the address spaces of `sycl_local` and
`sycl_private`
---
clang/lib/Basic/Targets/AMDGPU.h | 6 +-
clang/lib/CodeGen/Targets/NVPTX.cpp | 18 +++
.../CodeGenSYCL/address-space-conversions.cpp | 4 +
.../amd-address-space-conversions.cpp | 128 ++++++++++++++++++
.../cuda-address-space-conversions.cpp | 122 +++++++++++++++++
5 files changed, 276 insertions(+), 2 deletions(-)
create mode 100644 clang/test/CodeGenSYCL/amd-address-space-conversions.cpp
create mode 100644 clang/test/CodeGenSYCL/cuda-address-space-conversions.cpp
diff --git a/clang/lib/Basic/Targets/AMDGPU.h b/clang/lib/Basic/Targets/AMDGPU.h
index 90a1516ecdd20d..94d6ee7f5f72df 100644
--- a/clang/lib/Basic/Targets/AMDGPU.h
+++ b/clang/lib/Basic/Targets/AMDGPU.h
@@ -418,8 +418,10 @@ class LLVM_LIBRARY_VISIBILITY AMDGPUTargetInfo final : public TargetInfo {
// value ~0.
uint64_t getNullPointerValue(LangAS AS) const override {
// FIXME: Also should handle region.
- return (AS == LangAS::opencl_local || AS == LangAS::opencl_private)
- ? ~0 : 0;
+ return (AS == LangAS::opencl_local || AS == LangAS::opencl_private ||
+ AS == LangAS::sycl_local || AS == LangAS::sycl_private)
+ ? ~0
+ : 0;
}
void setAuxTarget(const TargetInfo *Aux) override;
diff --git a/clang/lib/CodeGen/Targets/NVPTX.cpp b/clang/lib/CodeGen/Targets/NVPTX.cpp
index d0dc7c258a03a6..8718f1ecf3a7e0 100644
--- a/clang/lib/CodeGen/Targets/NVPTX.cpp
+++ b/clang/lib/CodeGen/Targets/NVPTX.cpp
@@ -47,6 +47,10 @@ class NVPTXTargetCodeGenInfo : public TargetCodeGenInfo {
CodeGen::CodeGenModule &M) const override;
bool shouldEmitStaticExternCAliases() const override;
+ llvm::Constant *getNullPointer(const CodeGen::CodeGenModule &CGM,
+ llvm::PointerType *T,
+ QualType QT) const override;
+
llvm::Type *getCUDADeviceBuiltinSurfaceDeviceType() const override {
// On the device side, surface reference is represented as an object handle
// in 64-bit integer.
@@ -285,6 +289,20 @@ void NVPTXTargetCodeGenInfo::addNVVMMetadata(llvm::GlobalValue *GV,
bool NVPTXTargetCodeGenInfo::shouldEmitStaticExternCAliases() const {
return false;
}
+
+llvm::Constant *
+NVPTXTargetCodeGenInfo::getNullPointer(const CodeGen::CodeGenModule &CGM,
+ llvm::PointerType *PT,
+ QualType QT) const {
+ auto &Ctx = CGM.getContext();
+ if (PT->getAddressSpace() != Ctx.getTargetAddressSpace(LangAS::opencl_local))
+ return llvm::ConstantPointerNull::get(PT);
+
+ auto NPT = llvm::PointerType::get(
+ PT->getContext(), Ctx.getTargetAddressSpace(LangAS::opencl_generic));
+ return llvm::ConstantExpr::getAddrSpaceCast(
+ llvm::ConstantPointerNull::get(NPT), PT);
+}
}
void CodeGenModule::handleCUDALaunchBoundsAttr(llvm::Function *F,
diff --git a/clang/test/CodeGenSYCL/address-space-conversions.cpp b/clang/test/CodeGenSYCL/address-space-conversions.cpp
index 3933ad375412da..10a181318a174b 100644
--- a/clang/test/CodeGenSYCL/address-space-conversions.cpp
+++ b/clang/test/CodeGenSYCL/address-space-conversions.cpp
@@ -25,6 +25,10 @@ void usages() {
__attribute__((opencl_local)) int *LOC;
// CHECK-DAG: [[NoAS:%[a-zA-Z0-9]+]] = alloca ptr addrspace(4)
// CHECK-DAG: [[NoAS]].ascast = addrspacecast ptr [[NoAS]] to ptr addrspace(4)
+ LOC = nullptr;
+ // CHECK-DAG: store ptr addrspace(3) null, ptr addrspace(4) [[LOC]].ascast, align 8
+ GLOB = nullptr;
+ // CHECK-DAG: store ptr addrspace(1) null, ptr addrspace(4) [[GLOB]].ascast, align 8
int *NoAS;
// CHECK-DAG: [[PRIV:%[a-zA-Z0-9]+]] = alloca ptr
// CHECK-DAG: [[PRIV]].ascast = addrspacecast ptr [[PRIV]] to ptr addrspace(4)
diff --git a/clang/test/CodeGenSYCL/amd-address-space-conversions.cpp b/clang/test/CodeGenSYCL/amd-address-space-conversions.cpp
new file mode 100644
index 00000000000000..35da61cd8cbbe3
--- /dev/null
+++ b/clang/test/CodeGenSYCL/amd-address-space-conversions.cpp
@@ -0,0 +1,128 @@
+// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -fsycl-is-device -disable-llvm-passes -emit-llvm %s -o - | FileCheck %s
+void bar(int &Data) {}
+// CHECK-DAG: define dso_local void @[[RAW_REF:[a-zA-Z0-9_]+]](ptr noundef nonnull align 4 dereferenceable(4) %
+void bar2(int &Data) {}
+// CHECK-DAG: define dso_local void @[[RAW_REF2:[a-zA-Z0-9_]+]](ptr noundef nonnull align 4 dereferenceable(4) %
+void bar(__attribute__((opencl_local)) int &Data) {}
+// CHECK-DAG: define dso_local void @[[LOCAL_REF:[a-zA-Z0-9_]+]](ptr addrspace(3) noundef align 4 dereferenceable(4) %
+void foo(int *Data) {}
+// CHECK-DAG: define dso_local void @[[RAW_PTR:[a-zA-Z0-9_]+]](ptr noundef %
+void foo2(int *Data) {}
+// CHECK-DAG: define dso_local void @[[RAW_PTR2:[a-zA-Z0-9_]+]](ptr noundef %
+void foo(__attribute__((opencl_local)) int *Data) {}
+// CHECK-DAG: define dso_local void @[[LOC_PTR:[a-zA-Z0-9_]+]](ptr addrspace(3) noundef %
+
+template <typename T>
+void tmpl(T t);
+// See Check Lines below.
+
+void usages() {
+ __attribute__((opencl_global)) int *GLOB;
+ // CHECK-DAG: [[GLOB:%[a-zA-Z0-9]+]] = alloca ptr addrspace(1), align 8, addrspace(5)
+ __attribute__((opencl_local)) int *LOC;
+ // CHECK-DAG: [[LOC:%[a-zA-Z0-9]+]] = alloca ptr addrspace(3), align 4, addrspace(5)
+ LOC = nullptr;
+ // CHECK-DAG: store ptr addrspace(3) addrspacecast (ptr null to ptr addrspace(3)), ptr [[LOC]].ascast, align 4
+ GLOB = nullptr;
+ // CHECK-DAG: store ptr addrspace(1) null, ptr [[GLOB]].ascast, align 8
+ int *NoAS;
+ // CHECK-DAG: [[NoAS:%[a-zA-Z0-9]+]] = alloca ptr, align 8, addrspace(5)
+ __attribute__((opencl_private)) int *PRIV;
+ // CHECK-DAG: [[PRIV:%[a-zA-Z0-9]+]] = alloca ptr addrspace(5), align 4, addrspace(5)
+ __attribute__((opencl_global_device)) int *GLOBDEVICE;
+ // CHECK-DAG: [[GLOB_DEVICE:%[a-zA-Z0-9]+]] = alloca ptr addrspace(1), align 8, addrspace(5)
+ __attribute__((opencl_global_host)) int *GLOBHOST;
+ // CHECK-DAG: [[GLOB_HOST:%[a-zA-Z0-9]+]] = alloca ptr addrspace(1), align 8, addrspace(5)
+ NoAS = (int *)GLOB;
+ // CHECK-DAG: [[GLOB_LOAD:%[a-zA-Z0-9]+]] = load ptr addrspace(1), ptr [[GLOB]].ascast, align 8
+ // CHECK-DAG: [[GLOB_CAST:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(1) [[GLOB_LOAD]] to ptr
+ // CHECK-DAG: store ptr [[GLOB_CAST]], ptr [[NoAS]].ascast, align 8
+ NoAS = (int *)LOC;
+ // CHECK-DAG: [[LOC_LOAD:%[a-zA-Z0-9]+]] = load ptr addrspace(3), ptr [[LOC]].ascast, align 4
+ // CHECK-DAG: [[LOC_CAST:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(3) [[LOC_LOAD]] to ptr
+ // CHECK-DAG: store ptr [[LOC_CAST]], ptr [[NoAS]].ascast, align 8
+ NoAS = (int *)PRIV;
+ // CHECK-DAG: [[NoAS_LOAD:%[a-zA-Z0-9]+]] = load ptr addrspace(5), ptr [[PRIV]].ascast, align 4
+ // CHECK-DAG: [[NoAS_CAST:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(5) [[NoAS_LOAD]] to ptr
+ // CHECK-DAG: store ptr %5, ptr [[NoAS]].ascast, align 8
+ GLOB = (__attribute__((opencl_global)) int *)NoAS;
+ // CHECK-DAG: [[NoAS_LOAD:%[a-zA-Z0-9]+]] = load ptr, ptr [[NoAS]].ascast, align 8
+ // CHECK-DAG: [[NoAS_CAST:%[a-zA-Z0-9]+]] = addrspacecast ptr %6 to ptr addrspace(1)
+ // CHECK-DAG: store ptr addrspace(1) %7, ptr [[GLOB]].ascast, align 8
+ LOC = (__attribute__((opencl_local)) int *)NoAS;
+ // CHECK-DAG: [[NoAS_LOAD:%[a-zA-Z0-9]+]] = load ptr, ptr [[NoAS]].ascast, align 8
+ // CHECK-DAG: [[NoAS_CAST:%[a-zA-Z0-9]+]] = addrspacecast ptr [[NoAS_LOAD]] to ptr addrspace(3)
+ // CHECK-DAG: store ptr addrspace(3) %9, ptr [[LOC]].ascast, align 4
+ PRIV = (__attribute__((opencl_private)) int *)NoAS;
+ // CHECK-DAG: [[NoAS_LOAD:%[a-zA-Z0-9]+]] = load ptr, ptr [[NoAS]].ascast, align 8
+ // CHECK-DAG: [[NoAS_CAST:%[a-zA-Z0-9]+]] = addrspacecast ptr [[NoAS_LOAD]] to ptr addrspace(5)
+ // CHECK-DAG: store ptr addrspace(5) [[NoAS_CAST]], ptr [[PRIV]].ascast, align 4
+ GLOB = (__attribute__((opencl_global)) int *)GLOBDEVICE;
+ // CHECK-DAG: [[NoAS_LOAD:%[a-zA-Z0-9]+]] = load ptr addrspace(1), ptr [[GLOB]]DEVICE.ascast, align 8
+ // CHECK-DAG: store ptr addrspace(1) [[NoAS_LOAD]], ptr [[GLOB]].ascast, align 8
+ GLOB = (__attribute__((opencl_global)) int *)GLOBHOST;
+ // CHECK-DAG: [[NoAS_LOAD:%[a-zA-Z0-9]+]] = load ptr addrspace(1), ptr [[GLOB]]HOST.ascast, align 8
+ // CHECK-DAG: tore ptr addrspace(1) [[NoAS_LOAD]], ptr [[GLOB]].ascast, align 8
+ bar(*GLOB);
+ // CHECK-DAG: [[GLOB_LOAD:%[a-zA-Z0-9]+]] = load ptr addrspace(1), ptr [[GLOB]].ascast, align 8
+ // CHECK-DAG: [[GLOB_CAST:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(1) [[GLOB_LOAD]] to ptr
+ // CHECK-DAG: call void @[[RAW_REF]](ptr noundef nonnull align 4 dereferenceable(4) [[GLOB_CAST]])
+ bar2(*GLOB);
+ // CHECK-DAG: [[GLOB_LOAD:%[a-zA-Z0-9]+]] = load ptr addrspace(1), ptr [[GLOB]].ascast, align 8
+ // CHECK-DAG: [[GLOB_CAST:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(1) [[GLOB_LOAD]] to ptr
+ // CHECK-DAG: call void @[[RAW_REF2]](ptr noundef nonnull align 4 dereferenceable(4) [[GLOB_CAST]])
+ bar(*LOC);
+ // CHECK-DAG: [[LOC_LOAD:%[a-zA-Z0-9]+]] = load ptr addrspace(3), ptr [[LOC]].ascast, align 4
+ // CHECK-DAG: call void @_Z3barRU3AS3i(ptr addrspace(3) noundef align 4 dereferenceable(4) [[LOC_LOAD]])
+ bar2(*LOC);
+ // CHECK-DAG: [[LOC_LOAD2:%[a-zA-Z0-9]+]] = load ptr addrspace(3), ptr [[LOC]].ascast, align 4
+ // CHECK-DAG: [[LOC_CAST2:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(3) [[LOC_LOAD2]] to ptr
+ // CHECK-DAG: call void @_Z4bar2Ri(ptr noundef nonnull align 4 dereferenceable(4) [[LOC_CAST2]])
+ bar(*NoAS);
+ // CHECK-DAG: [[NoAS_LOAD:%[a-zA-Z0-9]+]] = load ptr, ptr [[NoAS]].ascast, align 8
+ // CHECK-DAG: call void @_Z3barRi(ptr noundef nonnull align 4 dereferenceable(4) [[NoAS_LOAD]])
+ bar2(*NoAS);
+ // CHECK-DAG: [[NoAS_LOAD2:%[a-zA-Z0-9]+]] = load ptr, ptr [[NoAS]].ascast, align 8
+ // CHECK-DAG: call void @_Z4bar2Ri(ptr noundef nonnull align 4 dereferenceable(4) [[NoAS_LOAD2]])
+ foo(GLOB);
+ // CHECK-DAG: [[GLOB_LOAD3:%[a-zA-Z0-9]+]] = load ptr addrspace(1), ptr [[GLOB]].ascast, align 8
+ // CHECK-DAG: [[GLOB_CAST3:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(1) [[GLOB_LOAD3]] to ptr
+ // CHECK-DAG: call void @[[RAW_PTR]](ptr noundef [[GLOB_CAST3]])
+ foo2(GLOB);
+ // CHECK-DAG: [[GLOB_LOAD4:%[a-zA-Z0-9]+]] = load ptr addrspace(1), ptr [[GLOB]].ascast, align 8
+ // CHECK-DAG: [[GLOB_CAST4:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(1) [[GLOB_LOAD4]] to ptr
+ // CHECK-DAG: call void @[[RAW_PTR2]](ptr noundef [[GLOB_CAST4]])
+ foo(LOC);
+ // CHECK-DAG: [[LOC_LOAD3:%[a-zA-Z0-9]+]] = load ptr addrspace(3), ptr [[LOC]].ascast, align 4
+ // CHECK-DAG: call void @[[LOC_PTR]](ptr addrspace(3) noundef [[LOC_LOAD3]])
+ foo2(LOC);
+ // CHECK-DAG: [[LOC_LOAD4:%[a-zA-Z0-9]+]] = load ptr addrspace(3), ptr [[LOC]].ascast, align 4
+ // CHECK-DAG: [[LOC_CAST4:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(3) [[LOC_LOAD4]] to ptr
+ // CHECK-DAG: call void @[[RAW_PTR2]](ptr noundef [[LOC_CAST4]])
+ foo(NoAS);
+ // CHECK-DAG: [[NoAS_LOAD3:%[a-zA-Z0-9]+]] = load ptr, ptr [[NoAS]].ascast, align 8
+ // CHECK-DAG: call void @[[RAW_PTR]](ptr noundef [[NoAS_LOAD3]])
+ foo2(NoAS);
+ // CHECK-DAG: [[NoAS_LOAD4:%[a-zA-Z0-9]+]] = load ptr, ptr [[NoAS]].ascast, align 8
+ // CHECK-DAG: call void @[[RAW_PTR2]](ptr noundef [[NoAS_LOAD4]])
+
+ // Ensure that we still get 3 different template instantiations.
+ tmpl(GLOB);
+ // CHECK-DAG: [[GLOB_LOAD4:%[a-zA-Z0-9]+]] = load ptr addrspace(1), ptr [[GLOB]].ascast, align 8
+ // CHECK-DAG: call void @_Z4tmplIPU3AS1iEvT_(ptr addrspace(1) noundef [[GLOB_LOAD4]])
+ tmpl(LOC);
+ // CHECK-DAG: [[LOC_LOAD5:%[a-zA-Z0-9]+]] = load ptr addrspace(3), ptr [[LOC]].ascast, align 4
+ // CHECK-DAG: call void @_Z4tmplIPU3AS3iEvT_(ptr addrspace(3) noundef [[LOC_LOAD5]])
+ tmpl(PRIV);
+ // CHECK-DAG: [[PRIV_LOAD5:%[a-zA-Z0-9]+]] = load ptr addrspace(5), ptr [[PRIV]].ascast, align 4
+ // CHECK-DAG: call void @_Z4tmplIPU3AS5iEvT_(ptr addrspace(5) noundef [[PRIV_LOAD5]])
+ tmpl(NoAS);
+ // CHECK-DAG: [[NoAS_LOAD5:%[a-zA-Z0-9]+]] = load ptr, ptr [[NoAS]].ascast, align 8
+ // CHECK-DAG: call void @_Z4tmplIPiEvT_(ptr noundef [[NoAS_LOAD5]])
+}
+
+// CHECK-DAG: declare void @_Z4tmplIPU3AS1iEvT_(ptr addrspace(1) noundef)
+// CHECK-DAG: declare void @_Z4tmplIPU3AS3iEvT_(ptr addrspace(3) noundef)
+// CHECK-DAG: declare void @_Z4tmplIPU3AS5iEvT_(ptr addrspace(5) noundef)
+// CHECK-DAG: declare void @_Z4tmplIPiEvT_(ptr noundef)
+
diff --git a/clang/test/CodeGenSYCL/cuda-address-space-conversions.cpp b/clang/test/CodeGenSYCL/cuda-address-space-conversions.cpp
new file mode 100644
index 00000000000000..82b80d8fc6b6ff
--- /dev/null
+++ b/clang/test/CodeGenSYCL/cuda-address-space-conversions.cpp
@@ -0,0 +1,122 @@
+// RUN: %clang_cc1 -triple nvptx64-nvidia-cuda -fsycl-is-device -disable-llvm-passes -emit-llvm %s -o - | FileCheck %s
+void bar(int &Data) {}
+// CHECK-DAG: define dso_local void @[[RAW_REF:[a-zA-Z0-9_]+]](ptr noundef nonnull align 4 dereferenceable(4) %
+void bar2(int &Data) {}
+// CHECK-DAG: define dso_local void @[[RAW_REF2:[a-zA-Z0-9_]+]](ptr noundef nonnull align 4 dereferenceable(4) %
+void bar(__attribute__((opencl_local)) int &Data) {}
+// CHECK-DAG: define dso_local void @[[LOCAL_REF:[a-zA-Z0-9_]+]](ptr addrspace(3) noundef align 4 dereferenceable(4) %
+void foo(int *Data) {}
+// CHECK-DAG: define dso_local void @[[RAW_PTR:[a-zA-Z0-9_]+]](ptr noundef %
+void foo2(int *Data) {}
+// CHECK-DAG: define dso_local void @[[RAW_PTR2:[a-zA-Z0-9_]+]](ptr noundef %
+void foo(__attribute__((opencl_local)) int *Data) {}
+// CHECK-DAG: define dso_local void @[[LOC_PTR:[a-zA-Z0-9_]+]](ptr addrspace(3) noundef %
+
+template <typename T>
+void tmpl(T t);
+// See Check Lines below.
+
+void usages() {
+ __attribute__((opencl_global)) int *GLOB;
+ // CHECK-DAG: [[GLOB:%[a-zA-Z0-9]+]] = alloca ptr addrspace(1), align 8
+ __attribute__((opencl_local)) int *LOC;
+ // CHECK-DAG: [[LOC:%[a-zA-Z0-9]+]] = alloca ptr addrspace(3), align 8
+ LOC = nullptr;
+ // CHECK-DAG: store ptr addrspace(3) addrspacecast (ptr null to ptr addrspace(3)), ptr [[LOC]], align 8
+ GLOB = nullptr;
+ // CHECK-DAG: store ptr addrspace(1) null, ptr [[GLOB]], align 8
+ int *NoAS;
+ // CHECK-DAG: [[NoAS:%[a-zA-Z0-9]+]] = alloca ptr, align 8
+ __attribute__((opencl_private)) int *PRIV;
+ // CHECK-DAG: [[PRIV:%[a-zA-Z0-9]+]] = alloca ptr, align 8
+ __attribute__((opencl_global_device)) int *GLOBDEVICE;
+ // CHECK-DAG: [[GLOB_DEVICE:%[a-zA-Z0-9]+]] = alloca ptr addrspace(1), align 8
+ __attribute__((opencl_global_host)) int *GLOBHOST;
+ // CHECK-DAG: [[GLOB_HOST:%[a-zA-Z0-9]+]] = alloca ptr addrspace(1), align 8
+ NoAS = (int *)GLOB;
+ // CHECK-DAG: [[GLOB_LOAD:%[a-zA-Z0-9]+]] = load ptr addrspace(1), ptr [[GLOB]], align 8
+ // CHECK-DAG: [[GLOB_CAST:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(1) [[GLOB_LOAD]] to ptr
+ // CHECK-DAG: store ptr [[GLOB_CAST]], ptr [[NoAS]], align 8
+ NoAS = (int *)LOC;
+ // CHECK-DAG: [[LOC_LOAD:%[a-zA-Z0-9]+]] = load ptr addrspace(3), ptr [[LOC]], align 8
+ // CHECK-DAG: [[LOC_CAST:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(3) [[LOC_LOAD]] to ptr
+ // CHECK-DAG: store ptr [[LOC_CAST]], ptr [[NoAS]], align 8
+ NoAS = (int *)PRIV;
+ // CHECK-DAG: [[LOC_LOAD:%[a-zA-Z0-9]+]] = load ptr, ptr [[PRIV]], align 8
+ // CHECK-DAG: store ptr [[LOC_LOAD]], ptr [[NoAS]], align 8
+ GLOB = (__attribute__((opencl_global)) int *)NoAS;
+ // CHECK-DAG: [[NoAS_LOAD:%[a-zA-Z0-9]+]] = load ptr, ptr [[NoAS]], align 8
+ // CHECK-DAG: [[NoAS_CAST:%[a-zA-Z0-9]+]] = addrspacecast ptr [[NoAS_LOAD]] to ptr addrspace(1)
+ // CHECK-DAG: store ptr addrspace(1) [[NoAS_CAST]], ptr [[GLOB]], align 8
+ LOC = (__attribute__((opencl_local)) int *)NoAS;
+ // CHECK-DAG: [[NoAS_LOAD:%[a-zA-Z0-9]+]] = load ptr, ptr [[NoAS]], align 8
+ // CHECK-DAG: [[NoAS_CAST:%[a-zA-Z0-9]+]] = addrspacecast ptr [[NoAS_LOAD]] to ptr addrspace(3)
+ // CHECK-DAG: store ptr addrspace(3) [[NoAS_CAST]], ptr [[LOC]], align 8
+ PRIV = (__attribute__((opencl_private)) int *)NoAS;
+ // CHECK-DAG: [[NoAS_LOAD:%[a-zA-Z0-9]+]] = load ptr, ptr [[NoAS]], align 8
+ // CHECK-DAG: store ptr [[NoAS_LOAD]], ptr [[PRIV]], align 8
+ GLOB = (__attribute__((opencl_global)) int *)GLOBDEVICE;
+ // CHECK-DAG: [[GLOBDEVICE_LOAD:%[a-zA-Z0-9]+]] = load ptr addrspace(1), ptr [[GLOB_DEVICE]], align 8
+ // CHECK-DAG: store ptr addrspace(1) [[GLOBDEVICE_LOAD]], ptr %GLOB, align 8
+ GLOB = (__attribute__((opencl_global)) int *)GLOBHOST;
+ // CHECK-DAG: [[GLOB_HOST_LOAD:%[a-zA-Z0-9]+]] = load ptr addrspace(1), ptr [[GLOB_HOST]], align 8
+ // CHECK-DAG: store ptr addrspace(1) [[GLOB_HOST_LOAD]], ptr [[GLOB]], align 8
+ bar(*GLOB);
+ // CHECK-DAG: [[GLOB_LOAD:%[a-zA-Z0-9]+]] = load ptr addrspace(1), ptr [[GLOB]], align 8
+ // CHECK-DAG: [[GLOB_CAST:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(1) [[GLOB_LOAD]] to ptr
+ // CHECK-DAG: call void @[[RAW_REF]](ptr noundef nonnull align 4 dereferenceable(4) [[GLOB_CAST]])
+ bar2(*GLOB);
+ // CHECK-DAG: [[GLOB_LOAD:%[a-zA-Z0-9]+]] = load ptr addrspace(1), ptr [[GLOB]], align 8
+ // CHECK-DAG: [[GLOB_CAST:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(1) [[GLOB_LOAD]] to ptr
+ // CHECK-DAG: call void @[[RAW_REF2]](ptr noundef nonnull align 4 dereferenceable(4) [[GLOB_CAST]])
+ bar(*LOC);
+ // CHECK-DAG: [[LOC_LOAD:%[a-zA-Z0-9]+]] = load ptr addrspace(3), ptr [[LOC]], align 8
+ // CHECK-DAG: call void @[[LOCAL_REF]](ptr addrspace(3) noundef align 4 dereferenceable(4) [[LOC_LOAD]])
+ bar2(*LOC);
+ // CHECK-DAG: [[LOC_LOAD2:%[a-zA-Z0-9]+]] = load ptr addrspace(3), ptr [[LOC]], align 8
+ // CHECK-DAG: [[LOC_CAST2:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(3) [[LOC_LOAD2]] to ptr
+ // CHECK-DAG: call void @[[RAW_REF2]](ptr noundef nonnull align 4 dereferenceable(4) [[LOC_CAST2]])
+ bar(*NoAS);
+ // CHECK-DAG: [[NoAS_LOAD:%[a-zA-Z0-9]+]] = load ptr, ptr [[NoAS]], align 8
+ // CHECK-DAG: call void @[[RAW_REF]](ptr noundef nonnull align 4 dereferenceable(4) [[NoAS_LOAD]])
+ bar2(*NoAS);
+ // CHECK-DAG: [[NoAS_LOAD2:%[a-zA-Z0-9]+]] = load ptr, ptr [[NoAS]], align 8
+ // CHECK-DAG: call void @[[RAW_REF2]](ptr noundef nonnull align 4 dereferenceable(4) [[NoAS_LOAD2]])
+ foo(GLOB);
+ // CHECK-DAG: [[GLOB_LOAD3:%[a-zA-Z0-9]+]] = load ptr addrspace(1), ptr [[GLOB]], align 8
+ // CHECK-DAG: [[GLOB_CAST3:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(1) [[GLOB_LOAD3]] to ptr
+ // CHECK-DAG: call void @[[RAW_PTR]](ptr noundef [[GLOB_CAST3]])
+ foo2(GLOB);
+ // CHECK-DAG: [[GLOB_LOAD4:%[a-zA-Z0-9]+]] = load ptr addrspace(1), ptr [[GLOB]], align 8
+ // CHECK-DAG: [[GLOB_CAST4:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(1) [[GLOB_LOAD4]] to ptr
+ // CHECK-DAG: call void @[[RAW_PTR2]](ptr noundef [[GLOB_CAST4]])
+ foo(LOC);
+ // CHECK-DAG: [[LOC_LOAD3:%[a-zA-Z0-9]+]] = load ptr addrspace(3), ptr [[LOC]], align 8
+ // CHECK-DAG: call void @[[LOC_PTR]](ptr addrspace(3) noundef [[LOC_LOAD3]])
+ foo2(LOC);
+ // CHECK-DAG: [[LOC_LOAD4:%[a-zA-Z0-9]+]] = load ptr addrspace(3), ptr [[LOC]], align 8
+ // CHECK-DAG: [[LOC_CAST4:%[a-zA-Z0-9]+]] = addrspacecast ptr addrspace(3) [[LOC_LOAD4]] to ptr
+ // CHECK-DAG: call void @[[RAW_PTR2]](ptr noundef [[LOC_CAST4]])
+ foo(NoAS);
+ // CHECK-DAG: [[NoAS_LOAD3:%[a-zA-Z0-9]+]] = load ptr, ptr [[NoAS]], align 8
+ // CHECK-DAG: call void @[[RAW_PTR]](ptr noundef [[NoAS_LOAD3]])
+ foo2(NoAS);
+ // CHECK-DAG: [[NoAS_LOAD4:%[a-zA-Z0-9]+]] = load ptr, ptr [[NoAS]], align 8
+ // CHECK-DAG: call void @[[RAW_PTR2]](ptr noundef [[NoAS_LOAD4]])
+ tmpl(GLOB);
+ // CHECK-DAG: [[GLOB_LOAD4:%[a-zA-Z0-9]+]] = load ptr addrspace(1), ptr [[GLOB]], align 8
+ // CHECK-DAG: call void @_Z4tmplIPU3AS1iEvT_(ptr addrspace(1) noundef [[GLOB_LOAD4]])
+ tmpl(LOC);
+ // CHECK-DAG: [[LOC_LOAD5:%[a-zA-Z0-9]+]] = load ptr addrspace(3), ptr [[LOC]], align 8
+ // CHECK-DAG: call void @_Z4tmplIPU3AS3iEvT_(ptr addrspace(3) noundef [[LOC_LOAD5]])
+ tmpl(PRIV);
+ // CHECK-DAG: [[PRIV_LOAD5:%[a-zA-Z0-9]+]] = load ptr, ptr [[PRIV]], align 8
+ // CHECK-DAG: call void @_Z4tmplIPiEvT_(ptr noundef [[PRIV_LOAD5]])
+ tmpl(NoAS);
+// CHECK-DAG: %33 = load ptr, ptr %NoAS, align 8
+// CHECK-DAG: call void @_Z4tmplIPiEvT_(ptr noundef %33)
+}
+
+// CHECK-DAG: declare void @_Z4tmplIPU3AS1iEvT_(ptr addrspace(1) noundef)
+// CHECK-DAG: declare void @_Z4tmplIPU3AS3iEvT_(ptr addrspace(3) noundef)
+// CHECK-DAG: declare void @_Z4tmplIPiEvT_(ptr noundef)
More information about the cfe-commits
mailing list