diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
--- a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
@@ -61,6 +61,7 @@
   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 @@
     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);
   }
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
@@ -173,6 +173,7 @@
     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));