@@ -3616,6 +3617,12 @@ unsigned FunctionDecl::getBuiltinID(bool
ConsiderWrapperFunctions) const {
if (!ConsiderWrapperFunctions && getStorageClass() == SC_Static)
return 0;
+ // AMDGCN implementation supports printf as a builtin
+ // for OpenCL
+ if
@@ -3616,6 +3617,12 @@ unsigned FunctionDecl::getBuiltinID(bool
ConsiderWrapperFunctions) const {
if (!ConsiderWrapperFunctions && getStorageClass() == SC_Static)
return 0;
+ // AMDGCN implementation supports printf as a builtin
+ // for OpenCL
+ if
@@ -3616,6 +3617,12 @@ unsigned FunctionDecl::getBuiltinID(bool
ConsiderWrapperFunctions) const {
if (!ConsiderWrapperFunctions && getStorageClass() == SC_Static)
return 0;
+ // AMDGCN implementation supports printf as a builtin
+ // for OpenCL
+ if
https://github.com/vikramRH edited
https://github.com/llvm/llvm-project/pull/72556
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/vikramRH edited
https://github.com/llvm/llvm-project/pull/72556
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -3616,6 +3617,12 @@ unsigned FunctionDecl::getBuiltinID(bool
ConsiderWrapperFunctions) const {
if (!ConsiderWrapperFunctions && getStorageClass() == SC_Static)
return 0;
+ // AMDGCN implementation supports printf as a builtin
+ // for OpenCL
+ if
@@ -3616,6 +3617,12 @@ unsigned FunctionDecl::getBuiltinID(bool
ConsiderWrapperFunctions) const {
if (!ConsiderWrapperFunctions && getStorageClass() == SC_Static)
return 0;
+ // AMDGCN implementation supports printf as a builtin
+ // for OpenCL
+ if
@@ -3616,6 +3617,12 @@ unsigned FunctionDecl::getBuiltinID(bool
ConsiderWrapperFunctions) const {
if (!ConsiderWrapperFunctions && getStorageClass() == SC_Static)
return 0;
+ // AMDGCN implementation supports printf as a builtin
+ // for OpenCL
+ if
@@ -2550,6 +2550,11 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl
GD, unsigned BuiltinID,
().getLongDoubleFormat() == ::APFloat::IEEEquad())
BuiltinID = mutateLongDoubleBuiltin(BuiltinID);
+ // Mutate the printf builtin ID so that we use the same
@@ -3616,6 +3617,12 @@ unsigned FunctionDecl::getBuiltinID(bool
ConsiderWrapperFunctions) const {
if (!ConsiderWrapperFunctions && getStorageClass() == SC_Static)
return 0;
+ // AMDGCN implementation supports printf as a builtin
+ // for OpenCL
+ if
@@ -3616,6 +3617,12 @@ unsigned FunctionDecl::getBuiltinID(bool
ConsiderWrapperFunctions) const {
if (!ConsiderWrapperFunctions && getStorageClass() == SC_Static)
return 0;
+ // AMDGCN implementation supports printf as a builtin
+ // for OpenCL
+ if
@@ -202,12 +207,20 @@ RValue
CodeGenFunction::EmitAMDGPUDevicePrintfCallExpr(const CallExpr *E) {
Args.push_back(Arg);
}
- llvm::IRBuilder<> IRB(Builder.GetInsertBlock(), Builder.GetInsertPoint());
- IRB.SetCurrentDebugLocation(Builder.getCurrentDebugLocation());
+
@@ -3616,6 +3617,12 @@ unsigned FunctionDecl::getBuiltinID(bool
ConsiderWrapperFunctions) const {
if (!ConsiderWrapperFunctions && getStorageClass() == SC_Static)
return 0;
+ // AMDGCN implementation supports printf as a builtin
+ // for OpenCL
+ if
@@ -202,12 +207,20 @@ RValue
CodeGenFunction::EmitAMDGPUDevicePrintfCallExpr(const CallExpr *E) {
Args.push_back(Arg);
}
- llvm::IRBuilder<> IRB(Builder.GetInsertBlock(), Builder.GetInsertPoint());
- IRB.SetCurrentDebugLocation(Builder.getCurrentDebugLocation());
+
@@ -2550,6 +2550,11 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl
GD, unsigned BuiltinID,
().getLongDoubleFormat() == ::APFloat::IEEEquad())
BuiltinID = mutateLongDoubleBuiltin(BuiltinID);
+ // Mutate the printf builtin ID so that we use the same
@@ -3616,6 +3617,12 @@ unsigned FunctionDecl::getBuiltinID(bool
ConsiderWrapperFunctions) const {
if (!ConsiderWrapperFunctions && getStorageClass() == SC_Static)
return 0;
+ // AMDGCN implementation supports printf as a builtin
+ // for OpenCL
+ if
@@ -170,20 +173,46 @@ static Value *appendString(IRBuilder<> , Value
*Desc, Value *Arg,
return callAppendStringN(Builder, Desc, Arg, Length, IsLast);
}
+static Value *appendVectorArg(IRBuilder<> , Value *Desc, Value *Arg,
arsenm wrote:
These are all still
@@ -202,12 +207,20 @@ RValue
CodeGenFunction::EmitAMDGPUDevicePrintfCallExpr(const CallExpr *E) {
Args.push_back(Arg);
}
- llvm::IRBuilder<> IRB(Builder.GetInsertBlock(), Builder.GetInsertPoint());
- IRB.SetCurrentDebugLocation(Builder.getCurrentDebugLocation());
+
@@ -202,12 +207,20 @@ RValue
CodeGenFunction::EmitAMDGPUDevicePrintfCallExpr(const CallExpr *E) {
Args.push_back(Arg);
}
- llvm::IRBuilder<> IRB(Builder.GetInsertBlock(), Builder.GetInsertPoint());
- IRB.SetCurrentDebugLocation(Builder.getCurrentDebugLocation());
+
https://github.com/arsenm requested changes to this pull request.
https://github.com/llvm/llvm-project/pull/72556
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -406,5 +410,9 @@ TARGET_BUILTIN(__builtin_amdgcn_cvt_pk_fp8_f32, "iffiIb",
"nc", "fp8-insts")
TARGET_BUILTIN(__builtin_amdgcn_cvt_sr_bf8_f32, "ifiiIi", "nc", "fp8-insts")
TARGET_BUILTIN(__builtin_amdgcn_cvt_sr_fp8_f32, "ifiiIi", "nc", "fp8-insts")
+// OpenCL
@@ -3616,6 +3617,12 @@ unsigned FunctionDecl::getBuiltinID(bool
ConsiderWrapperFunctions) const {
if (!ConsiderWrapperFunctions && getStorageClass() == SC_Static)
return 0;
+ // AMDGCN implementation supports printf as a builtin
+ // for OpenCL
+ if
@@ -2550,6 +2550,11 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl
GD, unsigned BuiltinID,
().getLongDoubleFormat() == ::APFloat::IEEEquad())
BuiltinID = mutateLongDoubleBuiltin(BuiltinID);
+ // Mutate the printf builtin ID so that we use the same
https://github.com/arsenm edited https://github.com/llvm/llvm-project/pull/72556
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/ssahasra approved this pull request.
https://github.com/llvm/llvm-project/pull/72556
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -178,17 +181,29 @@ RValue
CodeGenFunction::EmitNVPTXDevicePrintfCallExpr(const CallExpr *E) {
E, this, GetVprintfDeclaration(CGM.getModule()), false);
}
+// Deterimines if an argument is a string
+static bool isString(const clang::Type *argXTy) {
@@ -199,15 +214,31 @@ RValue
CodeGenFunction::EmitAMDGPUDevicePrintfCallExpr(const CallExpr *E) {
}
llvm::Value *Arg = A.getRValue(*this).getScalarVal();
+if (isString(A.getType().getTypePtr()) && CGM.getLangOpts().OpenCL)
ssahasra wrote:
The
@@ -198,15 +213,31 @@ RValue
CodeGenFunction::EmitAMDGPUDevicePrintfCallExpr(const CallExpr *E) {
}
llvm::Value *Arg = A.getRValue(*this).getScalarVal();
+if (isString(A.getType().getTypePtr()) && CGM.getLangOpts().OpenCL)
+ Arg =
@@ -178,17 +181,29 @@ RValue
CodeGenFunction::EmitNVPTXDevicePrintfCallExpr(const CallExpr *E) {
E, this, GetVprintfDeclaration(CGM.getModule()), false);
}
+// Deterimines if an argument is a string
+static bool isString(const clang::Type *argXTy) {
vikramRH wrote:
The new set of changes adds following changes,
1. The iteration over vector elements now happens using vector size from the
format specifier as reference, this is inline with runtime implementation and
helps handling undefined behavior when we have a mismatch.
2. The error flag
@@ -198,15 +213,31 @@ RValue
CodeGenFunction::EmitAMDGPUDevicePrintfCallExpr(const CallExpr *E) {
}
llvm::Value *Arg = A.getRValue(*this).getScalarVal();
+if (isString(A.getType().getTypePtr()) && CGM.getLangOpts().OpenCL)
+ Arg =
@@ -168,20 +174,48 @@ static Value *appendString(IRBuilder<> , Value
*Desc, Value *Arg,
return callAppendStringN(Builder, Desc, Arg, Length, IsLast);
}
+static Value *appendVectorArg(IRBuilder<> , Value *Desc, Value *Arg,
+ bool IsLast, bool
@@ -170,20 +173,49 @@ static Value *appendString(IRBuilder<> , Value
*Desc, Value *Arg,
return callAppendStringN(Builder, Desc, Arg, Length, IsLast);
}
+static Value *appendVectorArg(IRBuilder<> , Value *Desc, Value *Arg,
+ bool IsLast, bool
@@ -4742,6 +4742,16 @@ void Clang::ConstructJob(Compilation , const JobAction
,
Args.ClaimAllArgs(options::OPT_gen_cdb_fragment_path);
}
+ if (TC.getTriple().isAMDGPU() && types::isOpenCL(Input.getType())) {
+if (Args.getLastArg(options::OPT_mprintf_kind_EQ)) {
+
https://github.com/ssahasra requested changes to this pull request.
https://github.com/llvm/llvm-project/pull/72556
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -170,20 +173,49 @@ static Value *appendString(IRBuilder<> , Value
*Desc, Value *Arg,
return callAppendStringN(Builder, Desc, Arg, Length, IsLast);
}
+static Value *appendVectorArg(IRBuilder<> , Value *Desc, Value *Arg,
+ bool IsLast, bool
vikramRH wrote:
> Is there a separate PR open for "Add vector processing support to AMDGPU
> printf"? I think it's easiest to move this part forward first
@arsenm , you are right. I just want to make sure we are good on runtime
changes too now since there seems to be a blocker. The changes
https://github.com/arsenm commented:
Is there a separate PR open for "Add vector processing support to AMDGPU
printf"? I think it's easiest to move this part forward first
https://github.com/llvm/llvm-project/pull/72556
___
cfe-commits mailing list
@@ -1,12 +1,68 @@
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
-// RUN: %clang_cc1 -cl-std=CL1.2 -triple amdgcn-amd-amdhsa
-disable-llvm-passes -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -cl-std=CL1.2 -triple amdgcn-amd-amdhsa
arsenm wrote:
> ping
The split up parts are still part of this one PR. Currently you're supposed to
create a separate PR for each separate change. The set behavior is to squash
all of these together on submit
https://github.com/llvm/llvm-project/pull/72556
vikramRH wrote:
ping
https://github.com/llvm/llvm-project/pull/72556
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/vikramRH edited
https://github.com/llvm/llvm-project/pull/72556
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
42 matches
Mail list logo
