AMD Bulldozer Dual-Interlagos Benchmarks On Linux

[[Knuckles]]

the core counts are arbitrary I just think it would be interesting to see how it scales up, if this test is scaling with 99% efficiency that is not so good for bulldozer, but if there is a large decline as cores go up then that could be good news.

Thought this test may have already answered my question as it is single threaded (http://openbenchmarking.org/result/1...IV-HIMENUBUL97)

That is bad news for bulldozer as that shows about 1/2 the single threaded performance compared to sandy bridge. (2600k gets about 345 in that test where as a 3.6ghz bulldozer would get ~180)

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.

[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 $@ $(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?