[PATCH] D39973: Fix CaptureTracking for llvm.invariant.group.barrier

[Yaxun Liu via Phabricator via llvm-commits]

yaxunl created this revision.
Herald added subscribers: Prazek, tpr, JDevlieghere, nhaehnle, wdng.

AMDGPUPromoteAlloca pass relies on CaptureTracking to decide whether
a private pointer is captured. CaptureTracking treats a pointer passed to
intrinsic llvm.invariant.group.barrier as captured, which is incorrect and
causes certain alloca not promoted by AMDGPUPromoteAlloca.

This patch fixes that.


https://reviews.llvm.org/D39973

Files:
  lib/Analysis/CaptureTracking.cpp
  test/CodeGen/AMDGPU/promote-alloca-invariant-markers.ll


Index: test/CodeGen/AMDGPU/promote-alloca-invariant-markers.ll
===================================================================
--- test/CodeGen/AMDGPU/promote-alloca-invariant-markers.ll
+++ test/CodeGen/AMDGPU/promote-alloca-invariant-markers.ll
@@ -1,22 +1,24 @@
-; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mattr=+promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mtriple=amdgcn---amdgiz -mattr=+promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+target datalayout = "A5"
 
-declare {}* @llvm.invariant.start.p0i8(i64, i8* nocapture) #0
-declare void @llvm.invariant.end.p0i8({}*, i64, i8* nocapture) #0
+declare {}* @llvm.invariant.start.p5i8(i64, i8 addrspace(5)* nocapture) #0
+declare void @llvm.invariant.end.p5i8({}*, i64, i8 addrspace(5)* nocapture) #0
 declare i8* @llvm.invariant.group.barrier(i8*) #1
 
 ; GCN-LABEL: {{^}}use_invariant_promotable_lds:
 ; GCN: buffer_load_dword
 ; GCN: ds_write_b32
 define amdgpu_kernel void @use_invariant_promotable_lds(i32 addrspace(1)* %arg) #2 {
 bb:
-  %tmp = alloca i32, align 4
-  %tmp1 = bitcast i32* %tmp to i8*
+  %tmp = alloca i32, align 4, addrspace(5)
+  %tmp1 = bitcast i32 addrspace(5)* %tmp to i8 addrspace(5)*
   %tmp2 = getelementptr inbounds i32, i32 addrspace(1)* %arg, i64 1
   %tmp3 = load i32, i32 addrspace(1)* %tmp2
-  store i32 %tmp3, i32* %tmp
-  %tmp4 = call {}* @llvm.invariant.start.p0i8(i64 4, i8* %tmp1) #0
-  call void @llvm.invariant.end.p0i8({}* %tmp4, i64 4, i8* %tmp1) #0
-  %tmp5 = call i8* @llvm.invariant.group.barrier(i8* %tmp1) #1
+  store i32 %tmp3, i32 addrspace(5)* %tmp
+  %tmp4 = call {}* @llvm.invariant.start.p5i8(i64 4, i8 addrspace(5)* %tmp1) #0
+  call void @llvm.invariant.end.p5i8({}* %tmp4, i64 4, i8 addrspace(5)* %tmp1) #0
+  %tmp5 = addrspacecast i8 addrspace(5)* %tmp1 to i8*
+  %tmp6 = call i8* @llvm.invariant.group.barrier(i8* %tmp5) #1
   ret void
 }
 
Index: lib/Analysis/CaptureTracking.cpp
===================================================================
--- lib/Analysis/CaptureTracking.cpp
+++ lib/Analysis/CaptureTracking.cpp
@@ -243,6 +243,12 @@
       if (CS.onlyReadsMemory() && CS.doesNotThrow() && I->getType()->isVoidTy())
         break;
 
+      // Intrinsic function invariant_group_barrier does not capture pointer.
+      if (isa<IntrinsicInst>(I) && cast<IntrinsicInst>(I)->getIntrinsicID() ==
+                                       Intrinsic::invariant_group_barrier) {
+        break;
+      }
+
       // Volatile operations effectively capture the memory location that they
       // load and store to.
       if (auto *MI = dyn_cast<MemIntrinsic>(I))


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D39973.122705.patch
Type: text/x-patch
Size: 2730 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20171113/8620a5d1/attachment.bin>