DAG: Ignore call site attributes when emitting target intrinsic

A target intrinsic may be defined as possibly reading memory,
but the call site may have additional knowledge that it doesn't read
memory. The intrinsic lowering will expect the pessimistic
assumption of the intrinsic definition, so the chain should
still be used.

llvm-svn: 287593

diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
index 4bb3cd2..4594f92 100644 (file)
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -4061,8 +4061,12 @@ void SelectionDAGBuilder::visitAtomicStore(const StoreInst &I) {
 /// node.
 void SelectionDAGBuilder::visitTargetIntrinsic(const CallInst &I,
                                                unsigned Intrinsic) {
-  bool HasChain = !I.doesNotAccessMemory();
-  bool OnlyLoad = HasChain && I.onlyReadsMemory();
+  // Ignore the callsite's attributes. A specific call site may be marked with
+  // readnone, but the lowering code will expect the chain based on the
+  // definition.
+  const Function *F = I.getCalledFunction();
+  bool HasChain = !F->doesNotAccessMemory();
+  bool OnlyLoad = HasChain && F->onlyReadsMemory();
 
   // Build the operand list.
   SmallVector<SDValue, 8> Ops;

diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.getreg.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.getreg.ll
index 251eec6..4304398 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.getreg.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.getreg.ll
@@ -1,11 +1,21 @@
-; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck %s
-; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck %s
-; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -verify-machineinstrs < %s | FileCheck %s
+; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 
-; FUNC-LABEL: {{^}}s_getreg_test:
-; CHECK: s_getreg_b32 s{{[0-9]+}}, hwreg(HW_REG_LDS_ALLOC, 8, 23)
+; GCN-LABEL: {{^}}s_getreg_test:
+; GCN: s_getreg_b32 s{{[0-9]+}}, hwreg(HW_REG_LDS_ALLOC, 8, 23)
 define void @s_getreg_test(i32 addrspace(1)* %out) { ; simm16=45574 for lds size.
-  %lds_size_64dwords = call i32 @llvm.amdgcn.s.getreg(i32 45574) #0
+  %lds_size_64dwords = call i32 @llvm.amdgcn.s.getreg(i32 45574)
+  %lds_size_bytes = shl i32 %lds_size_64dwords, 8
+  store i32 %lds_size_bytes, i32 addrspace(1)* %out
+  ret void
+}
+
+; Call site has additional readnone knowledge.
+; GCN-LABEL: {{^}}readnone_s_getreg_test:
+; GCN: s_getreg_b32 s{{[0-9]+}}, hwreg(HW_REG_LDS_ALLOC, 8, 23)
+define void @readnone_s_getreg_test(i32 addrspace(1)* %out) { ; simm16=45574 for lds size.
+  %lds_size_64dwords = call i32 @llvm.amdgcn.s.getreg(i32 45574) #1
   %lds_size_bytes = shl i32 %lds_size_64dwords, 8
   store i32 %lds_size_bytes, i32 addrspace(1)* %out
   ret void
@@ -13,4 +23,5 @@ define void @s_getreg_test(i32 addrspace(1)* %out) { ; simm16=45574 for lds size
 
 declare i32 @llvm.amdgcn.s.getreg(i32) #0
 
-attributes #0 = { nounwind readonly}
+attributes #0 = { nounwind readonly }
+attributes #1 = { nounwind readnone }