Skip to content

[PGO][Offload] Disable PGO on NVPTX #133522

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 1 commit into from
Mar 28, 2025
Merged

[PGO][Offload] Disable PGO on NVPTX #133522

merged 1 commit into from
Mar 28, 2025

Conversation

EthanLuisMcDonough
Copy link
Member

No description provided.

@llvmbot llvmbot added clang Clang issues not falling into any other category clang:driver 'clang' and 'clang++' user-facing binaries. Not 'clang-cl' PGO Profile Guided Optimizations offload labels Mar 28, 2025
@llvmbot
Copy link
Member

llvmbot commented Mar 28, 2025 •
edited
Loading

@llvm/pr-subscribers-offload

@llvm/pr-subscribers-pgo

Author: Ethan Luis McDonough (EthanLuisMcDonough)

Changes

Full diff: https://github.com/llvm/llvm-project/pull/133522.diff

5 Files Affected:

  • (modified) clang/lib/Driver/ToolChains/Clang.cpp (+3-1)
  • (added) clang/test/Driver/cuda-no-pgo-or-coverage.cu (+33)
  • (modified) llvm/test/tools/llvm-profdata/malformed-ptr-to-counter-array.test (+1-1)
  • (modified) offload/test/offloading/gpupgo/pgo1.c (+1-1)
  • (modified) offload/test/offloading/gpupgo/pgo2.c (+1-1)
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index 26fa234dd4e9b..5f45cf0865b9e 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -6397,7 +6397,9 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
   Args.AddLastArg(CmdArgs, options::OPT_fconvergent_functions,
                   options::OPT_fno_convergent_functions);
 
-  addPGOAndCoverageFlags(TC, C, JA, Output, Args, SanitizeArgs, CmdArgs);
+  // NVPTX doesn't support PGO or coverage
+  if (!Triple.isNVPTX())
+    addPGOAndCoverageFlags(TC, C, JA, Output, Args, SanitizeArgs, CmdArgs);
 
   Args.AddLastArg(CmdArgs, options::OPT_fclang_abi_compat_EQ);
 
diff --git a/clang/test/Driver/cuda-no-pgo-or-coverage.cu b/clang/test/Driver/cuda-no-pgo-or-coverage.cu
new file mode 100644
index 0000000000000..b84587e1e182b
--- /dev/null
+++ b/clang/test/Driver/cuda-no-pgo-or-coverage.cu
@@ -0,0 +1,33 @@
+// Check that profiling/coverage arguments doen't get passed down to device-side
+// compilation.
+//
+//
+// XRUN: not %clang -### --target=x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 \
+// XRUN:   -fprofile-generate %s 2>&1 | \
+// XRUN:   FileCheck --check-prefixes=CHECK,PROF %s
+//
+// RUN: not %clang -### --target=x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 \
+// RUN:   -fprofile-instr-generate %s 2>&1 | \
+// RUN:   FileCheck --check-prefixes=CHECK,PROF %s
+//
+// RUN: not %clang -### --target=x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 \
+// RUN:   -coverage %s 2>&1 | \
+// RUN:   FileCheck --check-prefixes=CHECK,GCOV %s
+//
+// RUN: not %clang -### --target=x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 \
+// RUN:   -ftest-coverage %s 2>&1 | \
+// RUN:   FileCheck --check-prefixes=CHECK,GCOV %s
+//
+// RUN: not %clang -### --target=x86_64-linux-gnu -c --cuda-gpu-arch=sm_20   \
+// RUN:   -fprofile-instr-generate -fcoverage-mapping %s 2>&1 | \
+// RUN:   FileCheck --check-prefixes=CHECK,PROF %s
+//
+//
+// CHECK-NOT: error: unsupported option '-fprofile
+// CHECK-NOT: error: invalid argument
+// CHECK-DAG: "-fcuda-is-device"
+// CHECK-NOT: "-f{{[^"/]*coverage.*}}"
+// CHECK-NOT: "-fprofile{{[^"]*}}"
+// CHECK: "-triple" "x86_64-unknown-linux-gnu"
+// PROF:      "-fprofile{{.*}}"
+// GCOV:      "-coverage-notes-file=
diff --git a/llvm/test/tools/llvm-profdata/malformed-ptr-to-counter-array.test b/llvm/test/tools/llvm-profdata/malformed-ptr-to-counter-array.test
index 49c5ae9b0931d..83cf76f68fb63 100644
--- a/llvm/test/tools/llvm-profdata/malformed-ptr-to-counter-array.test
+++ b/llvm/test/tools/llvm-profdata/malformed-ptr-to-counter-array.test
@@ -1,7 +1,7 @@
 // Header
 //
 // INSTR_PROF_RAW_HEADER(uint64_t, Magic, __llvm_profile_get_magic())
-// INSTR_PROF_RAW_HEADER(uint64_t, Version, Version)
+// INSTR_PROF_RAW_HEADER(uint64_t, Version, __llvm_profile_get_version())
 // INSTR_PROF_RAW_HEADER(uint64_t, BinaryIdsSize, __llvm_write_binary_ids(NULL))
 // INSTR_PROF_RAW_HEADER(uint64_t, DataSize, DataSize)
 // INSTR_PROF_RAW_HEADER(uint64_t, CountersSize, CountersSize)
diff --git a/offload/test/offloading/gpupgo/pgo1.c b/offload/test/offloading/gpupgo/pgo1.c
index c8011cbae83c0..af6d8e806cd37 100644
--- a/offload/test/offloading/gpupgo/pgo1.c
+++ b/offload/test/offloading/gpupgo/pgo1.c
@@ -14,7 +14,7 @@
 // RUN:     %target_triple.%basename_t.clang.profraw | \
 // RUN:     %fcheck-generic --check-prefix="CLANG-PGO"
 
-// REQUIRES: gpu
+// REQUIRES: amdgpu
 // REQUIRES: pgo
 
 int test1(int a) { return a / 2; }
diff --git a/offload/test/offloading/gpupgo/pgo2.c b/offload/test/offloading/gpupgo/pgo2.c
index b75b0beaffdec..b67a63bc8fc3d 100644
--- a/offload/test/offloading/gpupgo/pgo2.c
+++ b/offload/test/offloading/gpupgo/pgo2.c
@@ -48,7 +48,7 @@
 // RUN:     %target_triple.%basename_t.hfdi.profraw \
 // RUN:     | %fcheck-generic --check-prefix="LLVM-DEVICE"
 
-// REQUIRES: gpu
+// REQUIRES: amdgpu
 // REQUIRES: pgo
 
 int main() {

@llvmbot
Copy link
Member

llvmbot commented Mar 28, 2025

@llvm/pr-subscribers-clang-driver

Author: Ethan Luis McDonough (EthanLuisMcDonough)

Changes

Full diff: https://github.com/llvm/llvm-project/pull/133522.diff

5 Files Affected:

  • (modified) clang/lib/Driver/ToolChains/Clang.cpp (+3-1)
  • (added) clang/test/Driver/cuda-no-pgo-or-coverage.cu (+33)
  • (modified) llvm/test/tools/llvm-profdata/malformed-ptr-to-counter-array.test (+1-1)
  • (modified) offload/test/offloading/gpupgo/pgo1.c (+1-1)
  • (modified) offload/test/offloading/gpupgo/pgo2.c (+1-1)
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index 26fa234dd4e9b..5f45cf0865b9e 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -6397,7 +6397,9 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
   Args.AddLastArg(CmdArgs, options::OPT_fconvergent_functions,
                   options::OPT_fno_convergent_functions);
 
-  addPGOAndCoverageFlags(TC, C, JA, Output, Args, SanitizeArgs, CmdArgs);
+  // NVPTX doesn't support PGO or coverage
+  if (!Triple.isNVPTX())
+    addPGOAndCoverageFlags(TC, C, JA, Output, Args, SanitizeArgs, CmdArgs);
 
   Args.AddLastArg(CmdArgs, options::OPT_fclang_abi_compat_EQ);
 
diff --git a/clang/test/Driver/cuda-no-pgo-or-coverage.cu b/clang/test/Driver/cuda-no-pgo-or-coverage.cu
new file mode 100644
index 0000000000000..b84587e1e182b
--- /dev/null
+++ b/clang/test/Driver/cuda-no-pgo-or-coverage.cu
@@ -0,0 +1,33 @@
+// Check that profiling/coverage arguments doen't get passed down to device-side
+// compilation.
+//
+//
+// XRUN: not %clang -### --target=x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 \
+// XRUN:   -fprofile-generate %s 2>&1 | \
+// XRUN:   FileCheck --check-prefixes=CHECK,PROF %s
+//
+// RUN: not %clang -### --target=x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 \
+// RUN:   -fprofile-instr-generate %s 2>&1 | \
+// RUN:   FileCheck --check-prefixes=CHECK,PROF %s
+//
+// RUN: not %clang -### --target=x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 \
+// RUN:   -coverage %s 2>&1 | \
+// RUN:   FileCheck --check-prefixes=CHECK,GCOV %s
+//
+// RUN: not %clang -### --target=x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 \
+// RUN:   -ftest-coverage %s 2>&1 | \
+// RUN:   FileCheck --check-prefixes=CHECK,GCOV %s
+//
+// RUN: not %clang -### --target=x86_64-linux-gnu -c --cuda-gpu-arch=sm_20   \
+// RUN:   -fprofile-instr-generate -fcoverage-mapping %s 2>&1 | \
+// RUN:   FileCheck --check-prefixes=CHECK,PROF %s
+//
+//
+// CHECK-NOT: error: unsupported option '-fprofile
+// CHECK-NOT: error: invalid argument
+// CHECK-DAG: "-fcuda-is-device"
+// CHECK-NOT: "-f{{[^"/]*coverage.*}}"
+// CHECK-NOT: "-fprofile{{[^"]*}}"
+// CHECK: "-triple" "x86_64-unknown-linux-gnu"
+// PROF:      "-fprofile{{.*}}"
+// GCOV:      "-coverage-notes-file=
diff --git a/llvm/test/tools/llvm-profdata/malformed-ptr-to-counter-array.test b/llvm/test/tools/llvm-profdata/malformed-ptr-to-counter-array.test
index 49c5ae9b0931d..83cf76f68fb63 100644
--- a/llvm/test/tools/llvm-profdata/malformed-ptr-to-counter-array.test
+++ b/llvm/test/tools/llvm-profdata/malformed-ptr-to-counter-array.test
@@ -1,7 +1,7 @@
 // Header
 //
 // INSTR_PROF_RAW_HEADER(uint64_t, Magic, __llvm_profile_get_magic())
-// INSTR_PROF_RAW_HEADER(uint64_t, Version, Version)
+// INSTR_PROF_RAW_HEADER(uint64_t, Version, __llvm_profile_get_version())
 // INSTR_PROF_RAW_HEADER(uint64_t, BinaryIdsSize, __llvm_write_binary_ids(NULL))
 // INSTR_PROF_RAW_HEADER(uint64_t, DataSize, DataSize)
 // INSTR_PROF_RAW_HEADER(uint64_t, CountersSize, CountersSize)
diff --git a/offload/test/offloading/gpupgo/pgo1.c b/offload/test/offloading/gpupgo/pgo1.c
index c8011cbae83c0..af6d8e806cd37 100644
--- a/offload/test/offloading/gpupgo/pgo1.c
+++ b/offload/test/offloading/gpupgo/pgo1.c
@@ -14,7 +14,7 @@
 // RUN:     %target_triple.%basename_t.clang.profraw | \
 // RUN:     %fcheck-generic --check-prefix="CLANG-PGO"
 
-// REQUIRES: gpu
+// REQUIRES: amdgpu
 // REQUIRES: pgo
 
 int test1(int a) { return a / 2; }
diff --git a/offload/test/offloading/gpupgo/pgo2.c b/offload/test/offloading/gpupgo/pgo2.c
index b75b0beaffdec..b67a63bc8fc3d 100644
--- a/offload/test/offloading/gpupgo/pgo2.c
+++ b/offload/test/offloading/gpupgo/pgo2.c
@@ -48,7 +48,7 @@
 // RUN:     %target_triple.%basename_t.hfdi.profraw \
 // RUN:     | %fcheck-generic --check-prefix="LLVM-DEVICE"
 
-// REQUIRES: gpu
+// REQUIRES: amdgpu
 // REQUIRES: pgo
 
 int main() {

@llvmbot
Copy link
Member

llvmbot commented Mar 28, 2025

@llvm/pr-subscribers-clang

Author: Ethan Luis McDonough (EthanLuisMcDonough)

Changes

Full diff: https://github.com/llvm/llvm-project/pull/133522.diff

5 Files Affected:

  • (modified) clang/lib/Driver/ToolChains/Clang.cpp (+3-1)
  • (added) clang/test/Driver/cuda-no-pgo-or-coverage.cu (+33)
  • (modified) llvm/test/tools/llvm-profdata/malformed-ptr-to-counter-array.test (+1-1)
  • (modified) offload/test/offloading/gpupgo/pgo1.c (+1-1)
  • (modified) offload/test/offloading/gpupgo/pgo2.c (+1-1)
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index 26fa234dd4e9b..5f45cf0865b9e 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -6397,7 +6397,9 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
   Args.AddLastArg(CmdArgs, options::OPT_fconvergent_functions,
                   options::OPT_fno_convergent_functions);
 
-  addPGOAndCoverageFlags(TC, C, JA, Output, Args, SanitizeArgs, CmdArgs);
+  // NVPTX doesn't support PGO or coverage
+  if (!Triple.isNVPTX())
+    addPGOAndCoverageFlags(TC, C, JA, Output, Args, SanitizeArgs, CmdArgs);
 
   Args.AddLastArg(CmdArgs, options::OPT_fclang_abi_compat_EQ);
 
diff --git a/clang/test/Driver/cuda-no-pgo-or-coverage.cu b/clang/test/Driver/cuda-no-pgo-or-coverage.cu
new file mode 100644
index 0000000000000..b84587e1e182b
--- /dev/null
+++ b/clang/test/Driver/cuda-no-pgo-or-coverage.cu
@@ -0,0 +1,33 @@
+// Check that profiling/coverage arguments doen't get passed down to device-side
+// compilation.
+//
+//
+// XRUN: not %clang -### --target=x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 \
+// XRUN:   -fprofile-generate %s 2>&1 | \
+// XRUN:   FileCheck --check-prefixes=CHECK,PROF %s
+//
+// RUN: not %clang -### --target=x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 \
+// RUN:   -fprofile-instr-generate %s 2>&1 | \
+// RUN:   FileCheck --check-prefixes=CHECK,PROF %s
+//
+// RUN: not %clang -### --target=x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 \
+// RUN:   -coverage %s 2>&1 | \
+// RUN:   FileCheck --check-prefixes=CHECK,GCOV %s
+//
+// RUN: not %clang -### --target=x86_64-linux-gnu -c --cuda-gpu-arch=sm_20 \
+// RUN:   -ftest-coverage %s 2>&1 | \
+// RUN:   FileCheck --check-prefixes=CHECK,GCOV %s
+//
+// RUN: not %clang -### --target=x86_64-linux-gnu -c --cuda-gpu-arch=sm_20   \
+// RUN:   -fprofile-instr-generate -fcoverage-mapping %s 2>&1 | \
+// RUN:   FileCheck --check-prefixes=CHECK,PROF %s
+//
+//
+// CHECK-NOT: error: unsupported option '-fprofile
+// CHECK-NOT: error: invalid argument
+// CHECK-DAG: "-fcuda-is-device"
+// CHECK-NOT: "-f{{[^"/]*coverage.*}}"
+// CHECK-NOT: "-fprofile{{[^"]*}}"
+// CHECK: "-triple" "x86_64-unknown-linux-gnu"
+// PROF:      "-fprofile{{.*}}"
+// GCOV:      "-coverage-notes-file=
diff --git a/llvm/test/tools/llvm-profdata/malformed-ptr-to-counter-array.test b/llvm/test/tools/llvm-profdata/malformed-ptr-to-counter-array.test
index 49c5ae9b0931d..83cf76f68fb63 100644
--- a/llvm/test/tools/llvm-profdata/malformed-ptr-to-counter-array.test
+++ b/llvm/test/tools/llvm-profdata/malformed-ptr-to-counter-array.test
@@ -1,7 +1,7 @@
 // Header
 //
 // INSTR_PROF_RAW_HEADER(uint64_t, Magic, __llvm_profile_get_magic())
-// INSTR_PROF_RAW_HEADER(uint64_t, Version, Version)
+// INSTR_PROF_RAW_HEADER(uint64_t, Version, __llvm_profile_get_version())
 // INSTR_PROF_RAW_HEADER(uint64_t, BinaryIdsSize, __llvm_write_binary_ids(NULL))
 // INSTR_PROF_RAW_HEADER(uint64_t, DataSize, DataSize)
 // INSTR_PROF_RAW_HEADER(uint64_t, CountersSize, CountersSize)
diff --git a/offload/test/offloading/gpupgo/pgo1.c b/offload/test/offloading/gpupgo/pgo1.c
index c8011cbae83c0..af6d8e806cd37 100644
--- a/offload/test/offloading/gpupgo/pgo1.c
+++ b/offload/test/offloading/gpupgo/pgo1.c
@@ -14,7 +14,7 @@
 // RUN:     %target_triple.%basename_t.clang.profraw | \
 // RUN:     %fcheck-generic --check-prefix="CLANG-PGO"
 
-// REQUIRES: gpu
+// REQUIRES: amdgpu
 // REQUIRES: pgo
 
 int test1(int a) { return a / 2; }
diff --git a/offload/test/offloading/gpupgo/pgo2.c b/offload/test/offloading/gpupgo/pgo2.c
index b75b0beaffdec..b67a63bc8fc3d 100644
--- a/offload/test/offloading/gpupgo/pgo2.c
+++ b/offload/test/offloading/gpupgo/pgo2.c
@@ -48,7 +48,7 @@
 // RUN:     %target_triple.%basename_t.hfdi.profraw \
 // RUN:     | %fcheck-generic --check-prefix="LLVM-DEVICE"
 
-// REQUIRES: gpu
+// REQUIRES: amdgpu
 // REQUIRES: pgo
 
 int main() {

@EthanLuisMcDonough EthanLuisMcDonough mentioned this pull request Mar 28, 2025
Merged
Artem-B
Artem-B approved these changes Mar 28, 2025
View reviewed changes
Copy link
Member

@Artem-B Artem-B left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM with a comment nit.

clang/lib/Driver/ToolChains/Clang.cpp
@@ -6397,7 +6397,9 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
Args.AddLastArg(CmdArgs, options::OPT_fconvergent_functions,
options::OPT_fno_convergent_functions);

addPGOAndCoverageFlags(TC, C, JA, Output, Args, SanitizeArgs, CmdArgs);
// NVPTX doesn't support PGO or coverage
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'd add the pointer to the failure details mentioning circular data references and, maybe, point for the PR comment with the details.

@EthanLuisMcDonough EthanLuisMcDonough merged commit 0c81105 into llvm:main Mar 28, 2025
11 of 15 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@Artem-B Artem-B Artem-B approved these changes

@jhuber6 jhuber6 jhuber6 approved these changes

Assignees
No one assigned
Labels
clang:driver 'clang' and 'clang++' user-facing binaries. Not 'clang-cl' clang Clang issues not falling into any other category offload PGO Profile Guided Optimizations
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
4 participants
@EthanLuisMcDonough @llvmbot @Artem-B @jhuber6