From: Simon Pilgrim <llvm-dev@redking.me.uk>
Date: Sat, 17 Dec 2022 14:06:26 +0000 (+0000)
Subject: [llvm-exegesis][X86] Use the same AGU counter estimate mapping for znver1 as znver2... 
X-Git-Tag: upstream/17.0.6~23408
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=2ee17d691f4f34769b64fffc6fe704ae13667256;p=platform%2Fupstream%2Fllvm.git

[llvm-exegesis][X86] Use the same AGU counter estimate mapping for znver1 as znver2, and count RMW ops as well

znver2 can use the ld/st dispatch counters to make a reasonable estimate for the AGU usage (although it misses complex LEA ops which I don't think we can fix), although it wasn't accounting for RMW ld-st uops which are counted separately - the same approach can be used for znver1 (ymm double-pumping ld/st agu is correctly measured as 2uops)

This change is mainly academic, but was noticed as the znver1/2 models incorrectly assume scalar RMW ops take 2uops
---

diff --git a/llvm/lib/Target/X86/X86PfmCounters.td b/llvm/lib/Target/X86/X86PfmCounters.td
index ea165ba..d2460e1 100644
--- a/llvm/lib/Target/X86/X86PfmCounters.td
+++ b/llvm/lib/Target/X86/X86PfmCounters.td
@@ -262,6 +262,7 @@ def ZnVer1PfmCounters : ProcPfmCounters {
     PfmIssueCounter<"ZnFPU1", "fpu_pipe_assignment:total1">,
     PfmIssueCounter<"ZnFPU2", "fpu_pipe_assignment:total2">,
     PfmIssueCounter<"ZnFPU3", "fpu_pipe_assignment:total3">,
+    PfmIssueCounter<"ZnAGU", "ls_dispatch:ld_st_dispatch + ls_dispatch:ld_dispatch + ls_dispatch:store_dispatch">,
     PfmIssueCounter<"ZnDivider", "div_op_count">
   ];
 }
@@ -271,7 +272,7 @@ def ZnVer2PfmCounters : ProcPfmCounters {
   let CycleCounter = PfmCounter<"cycles_not_in_halt">;
   let UopsCounter = PfmCounter<"retired_uops">;
   let IssueCounters = [
-    PfmIssueCounter<"Zn2AGU", "ls_dispatch:ld_dispatch + ls_dispatch:store_dispatch">,
+    PfmIssueCounter<"Zn2AGU", "ls_dispatch:ld_st_dispatch + ls_dispatch:ld_dispatch + ls_dispatch:store_dispatch">,
     PfmIssueCounter<"Zn2Divider", "div_op_count">
   ];
 }