[PATCH] D105186: [AMDGPU] PHI node cost should not be counted for the size and latency.

[Alexander via Phabricator via llvm-commits]

alex-t created this revision.
Herald added subscribers: foad, kerbowa, hiraditya, t-tye, tpr, dstuttard, yaxunl, nhaehnle, jvesely, kzhuravl, arsenm.
alex-t requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

    Details: https://reviews.llvm.org/D96805 changed the GCNTTIImpl::getCFInstrCost to return 1 for the PHI nodes
    for the TTI::TCK_CodeSize and TTI::TCK_SizeAndLatency. This is incorrect because the value moves that are the
    result of the PHI lowering are inserted into the basic block predecessors - not into the block itself.
    As a result of this change LoopRotate and LoopUnroll were broken because of the incorrect Loop header and loop
    body size/cost estimation.
  
    Fixes SWDEV-289429 10-11% Performance drop observed with ROC_OCL_Perf_Linpack_DGEMM_W32
  
  Differential Revision: https://reviews.llvm.org/D105104


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D105186

Files:
  llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
  llvm/test/Analysis/CostModel/AMDGPU/control-flow.ll


Index: llvm/test/Analysis/CostModel/AMDGPU/control-flow.ll
===================================================================
--- llvm/test/Analysis/CostModel/AMDGPU/control-flow.ll
+++ llvm/test/Analysis/CostModel/AMDGPU/control-flow.ll
@@ -8,7 +8,7 @@
 ; SPEED: estimated cost of 10 for instruction: ret void
 ; SIZE: estimated cost of 5 for instruction: br i1
 ; SIZE: estimated cost of 1 for instruction: br label
-; SIZE: estimated cost of 1 for instruction: %phi = phi i32 [
+; SIZE: estimated cost of 0 for instruction: %phi = phi i32 [
 ; SIZE: estimated cost of 1 for instruction: ret void
 define amdgpu_kernel void @test_br_cost(i32 addrspace(1)* %out, i32 addrspace(1)* %vaddr, i32 %b) #0 {
 bb0:
Index: llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
+++ llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
@@ -837,10 +837,6 @@
   }
   case Instruction::Ret:
     return SCost ? 1 : 10;
-  case Instruction::PHI:
-    // TODO: 1. A prediction phi won't be eliminated?
-    //       2. Estimate data copy instructions in this case.
-    return 1;
   }
   return BaseT::getCFInstrCost(Opcode, CostKind, I);
 }


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D105186.355517.patch
Type: text/x-patch
Size: 1253 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210630/530e1451/attachment.bin>