[NVPTX] Only run LowerUnreachable when necessary (#109868)

Before CUDA 12.3 `ptxas` did not recognize that the trap instruction
terminates a basic block. Instead, it would assume that control flow
continued to the next instruction. The next instruction could be in the
block that's lexically below it. This would lead to phantom CFG edges
being created within ptxas.

[NVPTX: Lower unreachable to exit to allow ptxas to accurately
reconstruct the
CFG.](1ee4d88)
added the LowerUnreachable pass to NVPTX to work around this. Several
other WAR patches followed.

This bug in `ptxas` was fixed in CUDA 12.3 and is thus impossible to
encounter when targeting PTX ISA v8.3+

This commit reverts the WARs for the `ptxas` bug when targeting PTX ISA
v8.3+

CC @maleadt

Author: justinfargnoli

llvm/lib/Target/NVPTX/NVPTXInstrInfo.td

@@ -139,6 +139,8 @@ def hasVote : Predicate<"Subtarget->hasVote()">;
 def hasDouble : Predicate<"Subtarget->hasDouble()">;
 def hasLDG : Predicate<"Subtarget->hasLDG()">;
 def hasLDU : Predicate<"Subtarget->hasLDU()">;
+def hasPTXASUnreachableBug : Predicate<"Subtarget->hasPTXASUnreachableBug()">;
+def noPTXASUnreachableBug : Predicate<"!Subtarget->hasPTXASUnreachableBug()">;
 
 def doF32FTZ : Predicate<"useF32FTZ()">;
 def doNoF32FTZ : Predicate<"!useF32FTZ()">;
@@ -3736,9 +3738,10 @@ def Callseq_End :
             [(callseq_end timm:$amt1, timm:$amt2)]>;
 
 // trap instruction
+def trapinst : NVPTXInst<(outs), (ins), "trap;", [(trap)]>, Requires<[noPTXASUnreachableBug]>;
 // Emit an `exit` as well to convey to ptxas that `trap` exits the CFG.
 // This won't be necessary in a future version of ptxas.
-def trapinst : NVPTXInst<(outs), (ins), "trap; exit;", [(trap)]>;
+def trapexitinst : NVPTXInst<(outs), (ins), "trap; exit;", [(trap)]>, Requires<[hasPTXASUnreachableBug]>;
 // brkpt instruction
 def debugtrapinst : NVPTXInst<(outs), (ins), "brkpt;", [(debugtrap)]>;
 

llvm/lib/Target/NVPTX/NVPTXSubtarget.h

@@ -95,6 +95,14 @@ class NVPTXSubtarget : public NVPTXGenSubtargetInfo {
   bool hasDotInstructions() const {
     return SmVersion >= 61 && PTXVersion >= 50;
   }
+  // Prior to CUDA 12.3 ptxas did not recognize that the trap instruction
+  // terminates a basic block. Instead, it would assume that control flow
+  // continued to the next instruction. The next instruction could be in the
+  // block that's lexically below it. This would lead to a phantom CFG edges
+  // being created within ptxas. This issue was fixed in CUDA 12.3. Thus, when
+  // PTX ISA versions 8.3+ we can confidently say that the bug will not be
+  // present.
+  bool hasPTXASUnreachableBug() const { return PTXVersion < 83; }
   bool hasCvtaParam() const { return SmVersion >= 70 && PTXVersion >= 77; }
   unsigned int getFullSmVersion() const { return FullSmVersion; }
   unsigned int getSmVersion() const { return getFullSmVersion() / 10; }

llvm/lib/Target/NVPTX/NVPTXTargetMachine.cpp

@@ -367,9 +367,13 @@ void NVPTXPassConfig::addIRPasses() {
     addPass(createSROAPass());
   }
 
-  const auto &Options = getNVPTXTargetMachine().Options;
-  addPass(createNVPTXLowerUnreachablePass(Options.TrapUnreachable,
-                                          Options.NoTrapAfterNoreturn));
+  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));
+  }
 }
 
 bool NVPTXPassConfig::addInstSelector() {

llvm/test/CodeGen/NVPTX/unreachable.ll

@@ -1,48 +1,107 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
 ; RUN: llc < %s -march=nvptx -mcpu=sm_20 -verify-machineinstrs -trap-unreachable=false \
-; RUN:     | FileCheck %s  --check-prefix=CHECK --check-prefix=CHECK-NOTRAP
+; RUN:     | FileCheck %s --check-prefixes=CHECK,NO-TRAP-UNREACHABLE
 ; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 -verify-machineinstrs -trap-unreachable=false \
-; RUN:     | FileCheck %s  --check-prefix=CHECK --check-prefix=CHECK-NOTRAP
+; RUN:     | FileCheck %s --check-prefixes=CHECK,NO-TRAP-UNREACHABLE
 ; RUN: llc < %s -march=nvptx -mcpu=sm_20 -verify-machineinstrs -trap-unreachable -no-trap-after-noreturn \
-; RUN:     | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-NOTRAP
+; RUN:     | FileCheck %s --check-prefixes=CHECK,NO-TRAP-AFTER-NORETURN
 ; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 -verify-machineinstrs -trap-unreachable -no-trap-after-noreturn \
-; RUN:     | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-NOTRAP
+; RUN:     | FileCheck %s --check-prefixes=CHECK,NO-TRAP-AFTER-NORETURN
 ; RUN: llc < %s -march=nvptx -mcpu=sm_20 -verify-machineinstrs -trap-unreachable -no-trap-after-noreturn=false \
-; RUN:     | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-TRAP
+; RUN:     | FileCheck %s --check-prefixes=CHECK,TRAP
 ; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 -verify-machineinstrs -trap-unreachable -no-trap-after-noreturn=false \
-; RUN:     | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-TRAP
+; RUN:     | FileCheck %s --check-prefixes=CHECK,TRAP
+; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 -verify-machineinstrs -trap-unreachable -mattr=+ptx83 \
+; RUN:     | FileCheck %s --check-prefixes=BUG-FIXED
 ; RUN: %if ptxas && !ptxas-12.0 %{ llc < %s -march=nvptx -mcpu=sm_20 -verify-machineinstrs | %ptxas-verify %}
 ; RUN: %if ptxas %{ llc < %s -march=nvptx64 -mcpu=sm_20 -verify-machineinstrs | %ptxas-verify %}
 
-; CHECK: .extern .func throw
+target triple = "nvptx-unknown-cuda"
+
 declare void @throw() #0
 declare void @llvm.trap() #0
 
-; CHECK-LABEL: .entry kernel_func
 define void @kernel_func() {
-; CHECK: call.uni
-; CHECK: throw,
+; NO-TRAP-UNREACHABLE-LABEL: kernel_func(
+; NO-TRAP-UNREACHABLE:       {
+; NO-TRAP-UNREACHABLE-EMPTY:
+; NO-TRAP-UNREACHABLE-EMPTY:
+; NO-TRAP-UNREACHABLE-NEXT:  // %bb.0:
+; NO-TRAP-UNREACHABLE-NEXT:    { // callseq 0, 0
+; NO-TRAP-UNREACHABLE-NEXT:    call.uni
+; NO-TRAP-UNREACHABLE-NEXT:    throw,
+; NO-TRAP-UNREACHABLE-NEXT:    (
+; NO-TRAP-UNREACHABLE-NEXT:    );
+; NO-TRAP-UNREACHABLE-NEXT:    } // callseq 0
+; NO-TRAP-UNREACHABLE-NEXT:    // begin inline asm
+; NO-TRAP-UNREACHABLE-NEXT:    exit;
+; NO-TRAP-UNREACHABLE-NEXT:    // end inline asm
+;
+; NO-TRAP-AFTER-NORETURN-LABEL: kernel_func(
+; NO-TRAP-AFTER-NORETURN:       {
+; NO-TRAP-AFTER-NORETURN-EMPTY:
+; NO-TRAP-AFTER-NORETURN-EMPTY:
+; NO-TRAP-AFTER-NORETURN-NEXT:  // %bb.0:
+; NO-TRAP-AFTER-NORETURN-NEXT:    { // callseq 0, 0
+; NO-TRAP-AFTER-NORETURN-NEXT:    call.uni
+; NO-TRAP-AFTER-NORETURN-NEXT:    throw,
+; NO-TRAP-AFTER-NORETURN-NEXT:    (
+; NO-TRAP-AFTER-NORETURN-NEXT:    );
+; NO-TRAP-AFTER-NORETURN-NEXT:    } // callseq 0
+; NO-TRAP-AFTER-NORETURN-NEXT:    // begin inline asm
+; NO-TRAP-AFTER-NORETURN-NEXT:    exit;
+; NO-TRAP-AFTER-NORETURN-NEXT:    // end inline asm
+; NO-TRAP-AFTER-NORETURN-NEXT:    trap; exit;
+;
+; TRAP-LABEL: kernel_func(
+; TRAP:       {
+; TRAP-EMPTY:
+; TRAP-EMPTY:
+; TRAP-NEXT:  // %bb.0:
+; TRAP-NEXT:    { // callseq 0, 0
+; TRAP-NEXT:    call.uni
+; TRAP-NEXT:    throw,
+; TRAP-NEXT:    (
+; TRAP-NEXT:    );
+; TRAP-NEXT:    } // callseq 0
+; TRAP-NEXT:    trap; exit;
+;
+; BUG-FIXED-LABEL: kernel_func(
+; BUG-FIXED:       {
+; BUG-FIXED-EMPTY:
+; BUG-FIXED-EMPTY:
+; BUG-FIXED-NEXT:  // %bb.0:
+; BUG-FIXED-NEXT:    { // callseq 0, 0
+; BUG-FIXED-NEXT:    call.uni
+; BUG-FIXED-NEXT:    throw,
+; BUG-FIXED-NEXT:    (
+; BUG-FIXED-NEXT:    );
+; BUG-FIXED-NEXT:    } // callseq 0
+; BUG-FIXED-NEXT:    trap;
   call void @throw()
-; CHECK-TRAP-NOT: exit;
-; CHECK-TRAP: trap;
-; CHECK-NOTRAP-NOT: trap;
-; CHECK: exit;
   unreachable
 }
 
-; CHECK-LABEL: kernel_func_2
 define void @kernel_func_2() {
-; CHECK: trap; exit;
+; CHECK-LABEL: kernel_func_2(
+; CHECK:       {
+; CHECK-EMPTY:
+; CHECK-EMPTY:
+; CHECK-NEXT:  // %bb.0:
+; CHECK-NEXT:    trap; exit;
+;
+; BUG-FIXED-LABEL: kernel_func_2(
+; BUG-FIXED:       {
+; BUG-FIXED-EMPTY:
+; BUG-FIXED-EMPTY:
+; BUG-FIXED-NEXT:  // %bb.0:
+; BUG-FIXED-NEXT:    trap;
   call void @llvm.trap()
-
-;; Make sure we avoid emitting two trap instructions.
-; CHECK-NOT: trap;
-; CHECK-NOT: exit;
+; Make sure we avoid emitting two trap instructions.
   unreachable
 }
 
 attributes #0 = { noreturn }
 
-
 !nvvm.annotations = !{!1}
-
 !1 = !{ptr @kernel_func, !"kernel", i32 1}