[AMDGPU] Fix getEUsPerCU for gfx10 in CU mode

Summary:
"Per CU" is a bit simplistic for gfx10, but I couldn't think of a better
name.

Reviewers: arsenm, rampitec, nhaehnle, dstuttard, tpr

Subscribers: kzhuravl, jvesely, wdng, yaxunl, t-tye, hiraditya, kerbowa, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D76861

llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp

@@ -268,6 +268,13 @@ unsigned getLocalMemorySize(const MCSubtargetInfo *STI) {
 }
 
 unsigned getEUsPerCU(const MCSubtargetInfo *STI) {
+  // "Per CU" really means "per whatever functional block the waves of a
+  // workgroup must share". For gfx10 in CU mode this is the CU, which contains
+  // two SIMDs.
+  if (isGFX10(*STI) && STI->getFeatureBits().test(FeatureCuMode))
+    return 2;
+  // Pre-gfx10 a CU contains four SIMDs. For gfx10 in WGP mode the WGP contains
+  // two CUs, so a total of four SIMDs.
   return 4;
 }