Messages in this thread | | | Date | Wed, 1 Jul 2009 15:12:17 +0200 | From | Ingo Molnar <> | Subject | Re: [PATCH -tip] perf_counter: Add Generalized Hardware FPU support for AMD |
| |
* Paul Mackerras <paulus@samba.org> wrote:
> Ingo Molnar writes: > > > 19583739 vec-adds ( 2.01x scaled) > > 20856051 vec-muls ( 2.01x scaled) > > 20856051 vec-divs ( 2.01x scaled) > > 25100224054 vec-idle-cycles ( 1.99x scaled) > > 12540131 vec-busy-cycles ( 1.99x scaled) > > 42286702 vec-ops ( 2.01x scaled) > > > > Paulus: would this categorization fit PowerPC too? > > Conceptually that looks nice, but unfortunately we don't have > events that correspond to that categorization on any PowerPC with > vector hardware (VMX/Altivec). POWER6 seems to have the most > vector events, and they are mostly divided up along the lines of > simple / complex / permute / load / store operations, and whether > they are integer or floating-point operations.
Here's what we have on x86:
20177177044 vec-adds (scaled from 66.63%) 34101687027 vec-muls (scaled from 66.64%) 3984060862 vec-divs (scaled from 66.71%) 26349684710 vec-idle-cycles (scaled from 66.65%) 9052001905 vec-stall-cycles (scaled from 66.66%) 76440734242 vec-ops (scaled from 66.71%)
Could at least the idle/busy/stall/total generic stats be filled in on powerpc, with a reasonable enough approximation? Those utilization metrics are the most important ones when one tries to figure out how well utilized the vector units are.
Ingo
| |