|
Message-ID: <20150831073501.GA10959@openwall.com> Date: Mon, 31 Aug 2015 10:35:01 +0300 From: Solar Designer <solar@...nwall.com> To: john-dev@...ts.openwall.com Subject: Re: PHC: Argon2 on GPU Agnieszka, On Mon, Aug 31, 2015 at 10:26:43AM +0300, Solar Designer wrote: > Looks like we need a script to test many LWS/GWS combinations. I am > running a simple script (testing 128 combinations) against Argon2d on > TITAN X now (and we'll probably need to test many more once we have > improved the code some further, since the current code is obviously > still far from optimized and thus might not be worth a lot of tuning and > benchmarking effort). No luck improving upon your TITAN X result in this way yet, but I'll post what was tried anyway. I ran this script: [solar@...er run]$ cat try.sh #!/bin/sh for LWS in `seq 1 128`; do GWS=$[$LWS * 24] while [ $GWS -lt 1536 ]; do GWS=$[$GWS * 2] done echo $LWS $GWS export LWS GWS ./john -test -format=argon2d-opencl -dev=4 -v=4 done like this: [solar@...er run]$ ./try.sh | tee -a try4.log Then analyzed the log like this: [solar@...er run]$ fgrep Many try4.log | sort -k3 -rn | head Many salts: 8045 c/s real, 7969 c/s virtual Many salts: 7831 c/s real, 7763 c/s virtual Many salts: 7747 c/s real, 7680 c/s virtual Many salts: 7733 c/s real, 7733 c/s virtual Many salts: 7714 c/s real, 7714 c/s virtual Many salts: 7712 c/s real, 7779 c/s virtual Many salts: 7698 c/s real, 7698 c/s virtual Many salts: 7680 c/s real, 7680 c/s virtual Many salts: 7663 c/s real, 7663 c/s virtual Many salts: 7663 c/s real, 7596 c/s virtual The top two entries are: [solar@...er run]$ grep -B6 'Many .*8045' try4.log 88 2112 Benchmarking: argon2d-opencl [Blake2 OpenCL]... memory per hash : 1.50 MB using different password for benchmarking DONE Speed for cost 1 (t) of 1, cost 2 (m) of 1536, cost 3 (l) of 1 Many salts: 8045 c/s real, 7969 c/s virtual [solar@...er run]$ grep -B6 'Many .*7831' try4.log 93 2232 Benchmarking: argon2d-opencl [Blake2 OpenCL]... memory per hash : 1.50 MB using different password for benchmarking DONE Speed for cost 1 (t) of 1, cost 2 (m) of 1536, cost 3 (l) of 1 Many salts: 7831 c/s real, 7763 c/s virtual The next few are for nearby LWS values as well. Alexander
Powered by blists - more mailing lists
Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.