[PATCH] D48190: [MCA][x86][NFC] Add tests for -register-file-stats, -scheduler-stats
Roman Lebedev via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Fri Jun 15 03:53:49 PDT 2018
lebedev.ri added inline comments.
================
Comment at: test/tools/llvm-mca/X86/register-file-statistics.s:45
+# SKLSER-NEXT: Total number of mappings created: 2
+# SKLSER-NEXT: Max number of mappings used: 2
+
----------------
andreadb wrote:
> lebedev.ri wrote:
> > RKSimon wrote:
> > > A lot of these prefixes look redundant?
> > Oh, indeed.
> >
> > BTW, in this file, everything before `Register File statistics:` isn't expected to be here.
> > Can
> > ```
> > Iterations: 100
> > Instructions: 100
> > Total Cycles: 51
> > Dispatch Width: 2
> > IPC: 1.96
> > Block RThroughput: 0.5
> > ```
> > be named a "-basic-stats", and an option to control that output be added?
> > @andreadb does that sound reasonable?
> Not really.
> I think the summary view should never be optional in llvm-mca.
> It is only a few lines, and it gives a nice overview of the run.
>
I agree that it is quite essential for normal usage,
but in the edge-case use-case like this, it does not seem to be of much use..
================
Comment at: test/tools/llvm-mca/X86/scheduler-queue-usage.s:110-114
+# BTVER2: Scheduler's queue usage:
+# BTVER2-NEXT: No scheduler resources used.
+
+# SLM: Scheduler's queue usage:
+# SLM-NEXT: No scheduler resources used.
----------------
Hm, it seems i have picked a bad example.
Repository:
rL LLVM
https://reviews.llvm.org/D48190
More information about the llvm-commits
mailing list