yaxunl updated this revision to Diff 92977.
yaxunl added a comment.
Revised by Tony's suggestions.
https://reviews.llvm.org/D31210
Files:
lib/Basic/Targets.cpp
test/CodeGenOpenCL/amdgpu-env-amdgiz.cl
Index: test/CodeGenOpenCL/amdgpu-env-amdgiz.cl
===================================================================
--- /dev/null
+++ test/CodeGenOpenCL/amdgpu-env-amdgiz.cl
@@ -0,0 +1,9 @@
+// RUN: %clang_cc1 %s -O0 -triple amdgcn -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 %s -O0 -triple amdgcn---opencl -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 %s -O0 -triple amdgcn---amdgiz -emit-llvm -o - | FileCheck -check-prefix=NEW %s
+// RUN: %clang_cc1 %s -O0 -triple amdgcn---amdgizcl -emit-llvm -o - | FileCheck -check-prefix=NEW %s
+
+// CHECK: target datalayout = "e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
+// NEW: target datalayout = "e-p:64:64-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
+void foo(void) {}
+
Index: lib/Basic/Targets.cpp
===================================================================
--- lib/Basic/Targets.cpp
+++ lib/Basic/Targets.cpp
@@ -2002,14 +2002,23 @@
return llvm::makeArrayRef(GCCRegNames);
}
-static const unsigned AMDGPUAddrSpaceMap[] = {
- 1, // opencl_global
- 3, // opencl_local
- 2, // opencl_constant
- 4, // opencl_generic
- 1, // cuda_device
- 2, // cuda_constant
- 3 // cuda_shared
+static LangAS::Map AMDGPUPrivateIsZeroMap = {
+ 1, // opencl_global
+ 3, // opencl_local
+ 2, // opencl_constant
+ 4, // opencl_generic
+ 1, // cuda_device
+ 2, // cuda_constant
+ 3 // cuda_shared
+};
+static LangAS::Map AMDGPUGenericIsZeroMap = {
+ 1, // opencl_global
+ 3, // opencl_local
+ 4, // opencl_constant
+ 0, // opencl_generic
+ 1, // cuda_device
+ 4, // cuda_constant
+ 3 // cuda_shared
};
// If you edit the description strings, make sure you update
@@ -2019,15 +2028,39 @@
"e-p:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128"
"-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64";
-static const char *const DataLayoutStringSI =
+static const char *const DataLayoutStringSIPrivateIsZero =
"e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32"
"-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128"
"-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64";
+static const char *const DataLayoutStringSIGenericIsZero =
+ "e-p:64:64-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32"
+ "-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128"
+ "-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64";
+
class AMDGPUTargetInfo final : public TargetInfo {
static const Builtin::Info BuiltinInfo[];
static const char * const GCCRegNames[];
+ struct AddrSpace {
+ unsigned Generic, Global, Local, Constant, Private;
+ AddrSpace(bool IsGenericZero_ = false){
+ if (IsGenericZero_) {
+ Generic = 0;
+ Global = 1;
+ Local = 3;
+ Constant = 4;
+ Private = 5;
+ } else {
+ Generic = 4;
+ Global = 1;
+ Local = 3;
+ Constant = 2;
+ Private = 0;
+ }
+ }
+ };
+
/// \brief The GPU profiles supported by the AMDGPU target.
enum GPUKind {
GK_NONE,
@@ -2054,39 +2087,43 @@
return TT.getArch() == llvm::Triple::amdgcn;
}
+ static bool isGenericZero(const llvm::Triple &TT) {
+ return TT.getEnvironment() == llvm::Triple::AMDGIZ ||
+ TT.getEnvironment() == llvm::Triple::AMDGIZCL;
+ }
public:
AMDGPUTargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts)
: TargetInfo(Triple) ,
GPU(isAMDGCN(Triple) ? GK_GFX6 : GK_R600),
hasFP64(false),
hasFMAF(false),
hasLDEXPF(false),
- hasFullSpeedFP32Denorms(false){
+ hasFullSpeedFP32Denorms(false),
+ AS(isGenericZero(Triple)){
if (getTriple().getArch() == llvm::Triple::amdgcn) {
hasFP64 = true;
hasFMAF = true;
hasLDEXPF = true;
}
-
+ auto IsGenericZero = isGenericZero(Triple);
resetDataLayout(getTriple().getArch() == llvm::Triple::amdgcn ?
- DataLayoutStringSI : DataLayoutStringR600);
+ (IsGenericZero ? DataLayoutStringSIGenericIsZero :
+ DataLayoutStringSIPrivateIsZero)
+ : DataLayoutStringR600);
- AddrSpaceMap = &AMDGPUAddrSpaceMap;
+ AddrSpaceMap = IsGenericZero ? &AMDGPUGenericIsZeroMap :
+ &AMDGPUPrivateIsZeroMap;
UseAddrSpaceMapMangling = true;
}
uint64_t getPointerWidthV(unsigned AddrSpace) const override {
if (GPU <= GK_CAYMAN)
return 32;
- switch(AddrSpace) {
- default:
- return 64;
- case 0:
- case 3:
- case 5:
- return 32;
+ if (AddrSpace == AS.Private || AddrSpace == AS.Local) {
+ return 32;
}
+ return 64;
}
uint64_t getPreferredPointerWidth(unsigned AddrSpace) const override {
@@ -2283,12 +2320,13 @@
/// DWARF.
Optional<unsigned> getDWARFAddressSpace(
unsigned AddressSpace) const override {
- switch (AddressSpace) {
- case 0: // LLVM Private.
- return 1; // DWARF Private.
- case 3: // LLVM Local.
- return 2; // DWARF Local.
- default:
+ const unsigned DWARF_Private = 1;
+ const unsigned DWARF_Local = 2;
+ if (AddressSpace == AS.Private) {
+ return DWARF_Private;
+ } else if (AddressSpace == AS.Local) {
+ return DWARF_Local;
+ } else {
return None;
}
}
@@ -2309,6 +2347,8 @@
uint64_t getNullPointerValue(unsigned AS) const override {
return AS == LangAS::opencl_local ? ~0 : 0;
}
+
+ AddrSpace AS;
};
const Builtin::Info AMDGPUTargetInfo::BuiltinInfo[] = {
_______________________________________________
cfe-commits mailing list
[email protected]
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
