[PATCH] D105651: [AMDGPU] Tune perfhint analysis to account access width

[Yaxun Liu via Phabricator via llvm-commits]

yaxunl added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUPerfHintAnalysis.cpp:220-221
+            32);
+        FI.MemInstCount += Size;
+        FI.InstCount += Size;
         continue;
----------------
rampitec wrote:
> foad wrote:
> > The "InstCount" names seem like a lie since we are no longer counting the number of instructions, but I don't have a better idea.
> Yes, I also didn't come up with a better name. In fact it always was a lie since IR instruction is not a HW instruction. All of that was inspired by the desire to move pass later in the pipeline and then I realized to preserve its behavior I need to adjust it for LD/ST combining. But the metric name has drifred even more from reality as it used to be.
How about Count => Cost ?

Also, we need to do the same change to IAMInstCoount and LSMInstCount to keep the way to calculate the cost consistent.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D105651/new/

https://reviews.llvm.org/D105651