Changes between Version 4 and Version 5 of LibCSSE

Timestamp:

Aug 8, 2014, 2:46:39 PM (12 years ago)

Author:

john

Comment:

--

LibCSSE

@@ -1 @@
-The first routine I worked on was memcpy().
+= Implementing SSE-optimized variants of string routines in libc for FreeBSD/amd64 =
 
-Comparison of stock memcpy() of a single page on FreeBSD vs Linux on a Westmere (values are TSC deltas):
+There is a subpage for each routine.  Most routines contain multiple variants (e.g. plain SSE2 vs AVX).  For each routine, the various variants were evaluated using micro-benchmarks on a variety of processors.
 
-{{{
-x fbsd/westmere/builtin
-+ linux/builtin
-    N           Min           Max        Median           Avg        Stddev
-x 1000           336         18444           340       361.628     573.11483
-+ 1000           276          9996           280       288.924     307.34136
-Difference at 95.0% confidence
-        -72.704 +/- 40.3074
-        -20.1046% +/- 11.1461%
-        (Student's t, pooled s = 459.847)
-}}}
+Routines:
 
-||= Idea                          =||= Westmere      =||= Sandy Bridge  =||= Ivy Bridge    =||= Penryn     =||
-|| Replace `dec` with `sub`        || none            || none            || none            ||              ||
-|| Use movsd instead of movsq      || slightly slower || slightly slower || 6% faster       ||              ||
-|| Simple `movdqa` loop            || 138% slower     || 58% slower      || 46% slower      ||              ||
-|| `movdqa` 32 at a time (old)     || 27% slower      || 14% faster      || 17% faster      ||              ||
-|| `movdqa` 32 at a time (new)     || 27% slower      || 15% faster      || 18% faster      ||              ||
-|| `movdqa` 32 at a time (reorder) || 27% slower      || 16% faster      || 19% faster      ||              ||
-|| `movdqa` 64 at a time (old)     || 224% slower     || 131% slower     || 116% slower     ||              ||
-|| `movdqa` 64 at a time (new)     || 4 cycles slower || 21% faster      || 24% faster      ||              ||
-|| Intermix SSE and backwards tests|| slightly slower || slightly slower || slightly slower ||              ||
-|| `movaps` 32 at a time           || 24% slower      || 18% faster      || 23% faster      || 52% faster   ||
-|| `movaps` 64 at a time           || 17% faster      || 23% faster      || 25% faster      || 48% faster   ||
-
-Takeaways from this trial:
-- Use `movaps` instead of `movdqa` as `movdqa` has a size (0x66) prefix
-- Minimize branches for the common path.
-- Unroll copy loop
-
-Now testing the overlap case:
-
-||= Idea                          =||= Westmere      =||= Sandy Bridge  =||= Ivy Bridge    =||= Penryn     =||
-|| `movaps` 64 at a time           || 56% faster      || 56% faster      || 56% faster      || 48% faster   ||
-|| Above using leaq                || 50% faster      || 56% faster      || 60% faster      || 52% faster   ||
-
-Notes:
-- leaq seems to be in the noise, it was about 4 cycles faster on Ivy Bridge and possibly Sandy Bridge, 4-8 slower on Westmere, and 8 faster on Penryn
+* [[LibCSSE/memcpy|memcpy]]
+* [[LibCSSE/memset|memset]]
+* [[LibCSSE/strlen|strlen]]