https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98361
Bug ID: 98361
Summary: L1/L2 cache characteristics not recognized with
-mtune=znver2
Product: gcc
Version: 10.2.1
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: sdack at gmx dot com
Target Milestone: ---
Hello,
I've come across an unexpected behaviour of gcc and wanted to ask for
help. I've noticed that when I specify '-march=znver2' does gcc use the
incorrect values for the L1/L2 cache. Only when '-march=native' was used
and gcc detected the CPU at run-time does it use the correct values. For
example on a Ryzen 7 3800X (a Zen 2 CPU):
$ gcc -march=znver2 --help=params -Q|fgrep cache
--param=l1-cache-line-size= 32
--param=l1-cache-size= 64
--param=l2-cache-size= 512
versus:
$ gcc -march=native --help=params -Q|fgrep cache
--param=l1-cache-line-size= 64
--param=l1-cache-size= 32
--param=l2-cache-size= 512
GCC does detect the CPU as 'znver2':
$ gcc -march=native --help=target -Q|fgrep march
-march= znver2
I've also verified this behaviour with '-mtune=znver2', and again does
GCC only use the correct values when it uses auto-detection.
Why does GCC not use the correct L1/L2 cache values when '-march=znver2'
or '-mtune=znver2' is specified?
Sven
PS: I've now also checked parts of the gcc source code and
gcc/config/i386/x86-tune-costs.h (around line 1557) does hold the correct
values and it appears these only don't get used somehow.
