AMD Bulldozer Dual-Interlagos Benchmarks On Linux

[bbordwell]

I think this is really too early silicon:
http://openbenchmarking.org/result/1...KNUC-110322323

Single-threaded new architecture @ 1.8Ghz vs single-threaded old one @ 1.9Ghz and old one wins!? I wouldn't read too much into these results.

I am going to have to agree with you, no way they would release a new arch that is slower than the last.

[LinuxID10T]

I am going to have to agree with you, no way they would release a new arch that is slower than the last.

Also, the new bulldozer cores are supposed to run way faster than the current stars cores.

[thalin]

Heh:

http://openbenchmarking.org/result/1...KNUC-110322585
http://openbenchmarking.org/result/1...KNUC-110322102

I win

But yeah, what's impressive is that you'll be able to get 4 of these on the same system, for a very reasonable price!

As they said in the article, "my" R910 is the best on C-Ray so far, so I win. I have you beat by nearly 2 seconds.

[mtippett]

As they said in the article, "my" R910 is the best on C-Ray so far, so I win. I have you beat by nearly 2 seconds.

Ah.. So you are the owner of that system .

I intend to do a openbenchmarking.org blog posting of that one.. Can you email me matthew @ phoronix.com to discuss?

[bbordwell]

I just found this out and have not seen it come up yet in discussion, C-ray measures floating point performance which is bulldozers weak point as it only has one FP unit per module. Integer performance then should be about double which would put it on par with sandy bridge.

[Jimbo]

Its pretty interesting what AMD has done. Just forget about the number of cores!, they created the bulldozer module which contains 2 integer cores and 1 FP core. A CPU will contain various bulldozer modules.

This redesign is aimed to increase performance on generic programs, which uses lot of integer operations (games included). Programs which makes use of a lot of FP operations (math, video encoders...) would probably not get performance boost.

Indeed, it should be interesting to see more tests of this AMD CPU redesign.

[mirv]

Its pretty interesting what AMD has done. Just forget about the number of cores!, they created the bulldozer module which contains 2 integer cores and 1 FP core. A CPU will contain various bulldozer modules.

This redesign is aimed to increase performance on generic programs, which uses lot of integer operations (games included). Programs which makes use of a lot of FP operations (math, video encoders...) would probably not get performance boost.

Indeed, it should be interesting to see more tests of this AMD CPU redesign.

Agreed here. Also, from what I've read (including the usual marketing stuff), the aim of the Fusion line, and likely Bulldozer, is not single threaded performance, or even single program performance. It's multi-program, multi-threaded performance, with lower power usage that they're aiming for.

[d1saster]

One still can improve the c-ray performance if one uses opencc as a compiler (http://www.openbenchmarking.org/resu...D1SA-CRAYCOM20). The standard makefile deliverd by PTS isnt aware of the CC env-variable, so i patched the install.sh in ~/.phoronix-test-suite/test-profiles/pts/c-ray-1.0.0/ .

#!/bin/sh

tar -zxvf c-ray-1.1.tar.gz

patch -p0 << 'EOF'
--- ./c-ray-1.1/Makefile.orig	2008-04-09 23:57:57.000000000 +0200
+++ ./c-ray-1.1/Makefile	2011-03-23 00:49:20.413694037 +0100
@@ -1,8 +1,8 @@
 obj = c-ray-mt.o
 bin = c-ray-mt
 
-CC = gcc
-CFLAGS = -O3 -ffast-math
+CC ?= gcc
+CFLAGS ?= -O3 -ffast-math
 
 $(bin): $(obj)
 	$(CC) -o [email protected] $(obj) -lm -lpthread
EOF

cd c-ray-1.1/
make -j $NUM_CPU_JOBS
echo $? > ~/install-exit-status
cd ..

echo "#!/bin/sh
cd c-ray-1.1/
RT_THREADS=\$((\$NUM_CPU_CORES * 16))
./c-ray-mt -t \$RT_THREADS -s 1600x1200 -r 8 -i sphfract -o output.ppm > \$LOG_FILE 2>&1
echo \$? > ~/test-exit-status" > c-ray
chmod +x c-ray

[Ferdinand]

So does anybody have an idea where bulldozer will be in relation with sandybridge? Performance per core(half module) per watt per clock?

[popper]

Ah.. So you are the owner of that system .

I intend to do a openbenchmarking.org blog posting of that one.. Can you email me matthew @ phoronix.com to discuss?

matthew why dont you and/or Michael write a openbenchmarking wrapper and use the generic checkasm --bench as supplied with a x264 git pull that use that wrapper to analyse the mass of real life data for the speed of each C and assembly routine you get there.

in fact in this case these cores being new, its a very effective way to get working AVX speed result's for a given core today as x264/checkasm include that in the latest git now, can you do that ASAP and make it a default run option and make a section on openbenchmarking for the raw checkasm --bench output at least

real life data from a current x264/checkasm git pull is far more interesting than any other app/benchmark as its the only one today that's got masses of fully tested assembly and is maintained and patched when bug's appear or new core's come on line.

and its a simple report and give temporary remote shell access to the core x264 assembly dev's if you cant git format patch/fix it yourself, they like feedback and especially checkasm --bench result's for new cores too.

Knuckles/thalin perhaps you two can also do a basic git pull of x264 compile and do a checkasm --bench and put them here/on a permanent http://pastebin.com link