[llvm] 84610a8 - AMDGPU: Add AMDGPUSubtarget::getEUsPerCU()

[Nicolai Hähnle via llvm-commits]

Author: Nicolai Hähnle
Date: 2023-01-23T21:43:05+01:00
New Revision: 84610a82a1aa9bac828569560818b919951039e1

URL: https://github.com/llvm/llvm-project/commit/84610a82a1aa9bac828569560818b919951039e1
DIFF: https://github.com/llvm/llvm-project/commit/84610a82a1aa9bac828569560818b919951039e1.diff

LOG: AMDGPU: Add AMDGPUSubtarget::getEUsPerCU()

We will use this for more accurate occupancy computations. Note that
IsaInfo takes WGP mode vs. CU mode into account on gfx10+.

Differential Revision: https://reviews.llvm.org/D139467

Added: 
    

Modified: 
    llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
    llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
index 7af0a7c9e045..4ddc8cf9dfe6 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
@@ -173,6 +173,7 @@ GCNSubtarget::GCNSubtarget(const Triple &TT, StringRef GPU, StringRef FS,
     FrameLowering(TargetFrameLowering::StackGrowsUp, getStackAlignment(), 0) {
   // clang-format on
   MaxWavesPerEU = AMDGPU::IsaInfo::getMaxWavesPerEU(this);
+  EUsPerCU = AMDGPU::IsaInfo::getEUsPerCU(this);
   CallLoweringInfo.reset(new AMDGPUCallLowering(*getTargetLowering()));
   InlineAsmLoweringInfo.reset(new InlineAsmLowering(getTargetLowering()));
   Legalizer.reset(new AMDGPULegalizerInfo(*this, TM));

diff  --git a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
index 7400c81effd0..99177ac07e2d 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
@@ -61,6 +61,7 @@ class AMDGPUSubtarget {
   bool HasFminFmaxLegacy = true;
   bool EnablePromoteAlloca = false;
   bool HasTrigReducedRange = false;
+  unsigned EUsPerCU = 4;
   unsigned MaxWavesPerEU = 10;
   unsigned LocalMemorySize = 0;
   char WavefrontSizeLog2 = 0;
@@ -209,6 +210,11 @@ class AMDGPUSubtarget {
     return LocalMemorySize;
   }
 
+  /// Number of SIMDs/EUs (execution units) per "CU" ("compute unit"), where the
+  /// "CU" is the unit onto which workgroups are mapped. This takes WGP mode vs.
+  /// CU mode into account.
+  unsigned getEUsPerCU() const { return EUsPerCU; }
+
   Align getAlignmentForImplicitArgPtr() const {
     return isAmdHsaOS() ? Align(8) : Align(4);
   }