Also check wether we're targeting Pascal or prior

llvm · Sep 24, 2024 · 6bc6174 · 6bc6174
1 parent 681c40f
commit 6bc6174
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 7 deletions.
diff --git a/llvm/lib/Target/NVPTX/NVPTXSubtarget.h b/llvm/lib/Target/NVPTX/NVPTXSubtarget.h
@@ -95,6 +95,9 @@ class NVPTXSubtarget : public NVPTXGenSubtargetInfo {
   bool hasDotInstructions() const {
     return SmVersion >= 61 && PTXVersion >= 50;
   }
+  bool hasPTXASUnreachableBug() const {
+    return SmVersion < 70 && PTXVersion <= 74;
+  }
   bool hasCvtaParam() const { return SmVersion >= 70 && PTXVersion >= 77; }
   unsigned int getFullSmVersion() const { return FullSmVersion; }
   unsigned int getSmVersion() const { return getFullSmVersion() / 10; }

diff --git a/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp b/llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp
@@ -368,11 +368,9 @@ void NVPTXPassConfig::addIRPasses() {
     addPass(createSROAPass());
   }
 
-  if (ST.getPTXVersion() <= 74) {
-    // This pass is a WAR for a bug that's present in `ptxas` binaries that are
-    // shipped in or prior to CUDA Toolkit 11.4. The highest version that's
-    // supported by `ptxas` in CUDA 11.4 is 7.4. Limit this pass to only run
-    // when targeting PTX 7.4 or lower.
+  if (ST.hasPTXASUnreachableBug()) {
+    // Run LowerUnreachable to WAR a ptxas bug. See the commit description of
+    // 1ee4d880e8760256c606fe55b7af85a4f70d006d for more details.
     const auto &Options = getNVPTXTargetMachine().Options;
     addPass(createNVPTXLowerUnreachablePass(Options.TrapUnreachable,
                                             Options.NoTrapAfterNoreturn));

diff --git a/llvm/test/CodeGen/NVPTX/unreachable.ll b/llvm/test/CodeGen/NVPTX/unreachable.ll
@@ -3,7 +3,9 @@
 ; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 -verify-machineinstrs \
 ; RUN:     | FileCheck %s  --check-prefixes=CHECK,CHECK-NOTRAP
 ; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 -verify-machineinstrs -mattr=+ptx75 \
-; RUN:     | FileCheck %s  --check-prefixes=CHECK-PTX75
+; RUN:     | FileCheck %s  --check-prefixes=CHECK-BUG-FIXED
+; RUN: llc < %s -march=nvptx64 -mcpu=sm_70 -verify-machineinstrs \
+; RUN:     | FileCheck %s  --check-prefixes=CHECK-BUG-FIXED
 ; RUN: llc < %s -march=nvptx -mcpu=sm_20 -verify-machineinstrs -trap-unreachable \
 ; RUN:     | FileCheck %s --check-prefixes=CHECK,CHECK-TRAP
 ; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 -verify-machineinstrs -trap-unreachable \
@@ -23,7 +25,7 @@ define void @kernel_func() {
 ; CHECK-TRAP: trap;
 ; CHECK-NOTRAP-NOT: trap;
 ; CHECK: exit;
-; CHECK-PTX75-NOT: exit;
+; CHECK-BUG-FIXED-NOT: exit;
   unreachable
 }