[llvm-bugs] [Bug 39165] New: [llvm-exegesis] Bind PFM Counters to the CPUs instead of the SchedModel
via llvm-bugs
llvm-bugs at lists.llvm.org
Wed Oct 3 09:59:01 PDT 2018
https://bugs.llvm.org/show_bug.cgi?id=39165
Bug ID: 39165
Summary: [llvm-exegesis] Bind PFM Counters to the CPUs instead
of the SchedModel
Product: libraries
Version: trunk
Hardware: PC
OS: Windows NT
Status: NEW
Severity: enhancement
Priority: P
Component: Backend: X86
Assignee: unassignedbugs at nondot.org
Reporter: llvm-dev at redking.me.uk
CC: andrea.dibiagio at gmail.com, clement.courbet at gmail.com,
craig.topper at gmail.com, gchatelet at google.com,
lebedev.ri at gmail.com, llvm-bugs at lists.llvm.org
As discussed on D52779, its probably a good idea to bind the PFM counters to
the CPUs instead of the SchedModel.
Not only will this make it easier to reuse models where perf counters don't
match (e.g. bdver1/2 vs bdver3/4 and x86_64 generic) but it could make new
models easier to create - by allowing the cpu to initially just specify
cycle/uop counters.
--
You are receiving this mail because:
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-bugs/attachments/20181003/c01f0fd5/attachment.html>
More information about the llvm-bugs
mailing list