On Mon, 23 May 2005, Mike Stump wrote:
On May 23, 2005, at 12:01 PM, Mark Mitchell wrote:
We've researched this in detail.
As have I, I also have the timings for template heavy code with the more
egregious of the bugs fixed in the compiler-server branch, at that time, they
were worth a 10x
On May 23, 2005, at 12:01 PM, Mark Mitchell wrote:
We've researched this in detail.
As have I, I also have the timings for template heavy code with the
more egregious of the bugs fixed in the compiler-server branch, at
that time, they were worth a 10x compile time improvement. If
someone
Mark Mitchell wrote:
> It's certainly well-known here -- but that's not to say it shouldn't
> go in some nice FSF-ish place as well in case somebody else wants to
> work on it.
Probably it's obvious but indeed, we already noticed that this is also
*the* bottleneck for the compile-time performance
Karel Gardas wrote:
On Mon, 23 May 2005, Mark Mitchell wrote:
Mike Stump wrote:
On May 17, 2005, at 3:16 PM, Karel Gardas wrote:
1) the most expensive seems to be comptypes -- at least from data L2
refill point of view (~17%)
2) comptypes is also the most CPU intensive operation since t
On Mon, 23 May 2005, Mark Mitchell wrote:
Mike Stump wrote:
On May 17, 2005, at 3:16 PM, Karel Gardas wrote:
1) the most expensive seems to be comptypes -- at least from data L2
refill point of view (~17%)
2) comptypes is also the most CPU intensive operation since the most
of time is
Mike Stump wrote:
On May 17, 2005, at 3:16 PM, Karel Gardas wrote:
1) the most expensive seems to be comptypes -- at least from data L2
refill point of view (~17%)
2) comptypes is also the most CPU intensive operation since the most
of time is spent there
I think comptypes can be sped
On Tue, 17 May 2005, Mike Stump wrote:
On May 17, 2005, at 3:16 PM, Karel Gardas wrote:
1) the most expensive seems to be comptypes -- at least from data L2
refill point of view (~17%)
2) comptypes is also the most CPU intensive operation since the most
of time is spent there
I think comptypes
On May 17, 2005, at 3:16 PM, Karel Gardas wrote:
1) the most expensive seems to be comptypes -- at least from data L2
refill point of view (~17%)
2) comptypes is also the most CPU intensive operation since the most
of time is spent there
I think comptypes can be sped up by canonicalizing type
[rewritten/remeasured as per suggestion by Andy Kleen]
Hello,
I've tried to measure some cache misses of 4.0.1 and 4.1.0 C++
compilers by using oprofile on amd64 box while compiling MICO sources
and found that:
0) compiler options used were:
-I../include -Wall -D_REENTRANT -D_GNU_SOURCE -DP
On Tue, 17 May 2005, Andi Kleen wrote:
Karel Gardas <[EMAIL PROTECTED]> writes:
I've thought that L1 and L2 DTLB misses are the most important for the
overall performance or performance degradation, if not please correct
me since this is my first attempt to measure and interpret such data.
TLB is j
Karel Gardas <[EMAIL PROTECTED]> writes:
> I've thought that L1 and L2 DTLB misses are the most important for the
> overall performance or performance degradation, if not please correct
> me since this is my first attempt to measure and interpret such data.
TLB is just for caching the translation
11 matches
Mail list logo
