[PATCH] D128631: [AArch64] Initial sched model for Neoverse N2

[dewen via Phabricator via llvm-commits]

dewen added inline comments.


================
Comment at: llvm/test/tools/llvm-mca/AArch64/Neoverse/N2-sve-instructions.s:7173
+# CHECK-NEXT:  27     11    4.50           *      U     st4b	{ z5.b, z6.b, z7.b, z8.b }, p3, [x17, x16]
+# CHECK-NEXT:  27     11    4.50           *      U     st4d	{ z0.d, z1.d, z2.d, z3.d }, p0, [x0, x0, lsl #3]
+# CHECK-NEXT:  18     11    4.50           *      U     st4d	{ z0.d, z1.d, z2.d, z3.d }, p0, [x0]
----------------
c-rhodes wrote:
> dewen wrote:
> > c-rhodes wrote:
> > > dewen wrote:
> > > > dewen wrote:
> > > > > I found that the throughput information for this instruction (`st4d`) does not match the description in the documentation. Is there a problem with the document? 
> > > > > {F25275327}
> > > > > 
> > > > > I found that the throughput information for this instruction (`st4d`) does not match the description in the documentation. Is there a problem with the document? 
> > > > > {F25275327}
> > > > > 
> > > > 
> > > > @Cullen Rhodes
> > > > > I found that the throughput information for this instruction (`st4d`) does not match the description in the documentation. Is there a problem with the document? 
> > > > > {F25275327}
> > > > > 
> > > > 
> > > > @Cullen Rhodes
> > > 
> > > I've seen your comment, I don't have an immediate answer but will check.
> > Hey, has this comment come to a conclusion? @c-rhodes 
> > Hey, has this comment come to a conclusion? @c-rhodes 
> 
> The throughput for the ST4 instructions here is incorrect as you pointed out, it should be 9. I noticed ST2 doesn't look correct either. Thanks for reporting, we'll get it fixed.
Okay, look forward to your fix.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D128631/new/

https://reviews.llvm.org/D128631