[PATCH] D98362: [AMDGPU] Fix -amdgpu-inline-arg-alloca-cost

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rGb7b99b0799fa: [AMDGPU] Fix -amdgpu-inline-arg-alloca-cost (authored by rampitec).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D98362/new/

https://reviews.llvm.org/D98362

Files:
  llvm/lib/Analysis/InlineCost.cpp
  llvm/test/Transforms/Inline/AMDGPU/amdgpu-inline-alloca-argument-cost.ll


Index: llvm/test/Transforms/Inline/AMDGPU/amdgpu-inline-alloca-argument-cost.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/Inline/AMDGPU/amdgpu-inline-alloca-argument-cost.ll
@@ -0,0 +1,22 @@
+; RUN: opt -mtriple=amdgcn--amdhsa -S -passes=inline -inline-threshold=0 -debug-only=inline-cost < %s 2>&1 | FileCheck %s
+
+; REQUIRES: asserts
+
+target datalayout = "A5"
+
+; Verify we are properly adding cost of the -amdgpu-inline-arg-alloca-cost to the threshold.
+
+; CHECK: NumAllocaArgs: 1
+; CHECK: Threshold: 66000
+
+define void @use_private_ptr_arg(float addrspace(5)* nocapture %p) {
+  ret void
+}
+
+define amdgpu_kernel void @test_inliner_pvt_ptr(float addrspace(1)* nocapture %a, i32 %n) {
+entry:
+  %pvt_arr = alloca [64 x float], align 4, addrspace(5)
+  %to.ptr = getelementptr inbounds [64 x float], [64 x float] addrspace(5)* %pvt_arr, i32 0, i32 0
+  call void @use_private_ptr_arg(float addrspace(5)* %to.ptr)
+  ret void
+}
Index: llvm/lib/Analysis/InlineCost.cpp
===================================================================
--- llvm/lib/Analysis/InlineCost.cpp
+++ llvm/lib/Analysis/InlineCost.cpp
@@ -1577,10 +1577,11 @@
     }
   }
 
+  Threshold += TTI.adjustInliningThreshold(&Call);
+
   // Finally, take the target-specific inlining threshold multiplier into
   // account.
   Threshold *= TTI.getInliningThresholdMultiplier();
-  Threshold += TTI.adjustInliningThreshold(&Call);
 
   SingleBBBonus = Threshold * SingleBBBonusPercent / 100;
   VectorBonus = Threshold * VectorBonusPercent / 100;


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D98362.330292.patch
Type: text/x-patch
Size: 1593 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210312/7ec0226d/attachment.bin>