<app_config>
<app_version>
<app_name>setiathome_v8</app_name>
<plan_class>cuda50</plan_class>
<avg_ncpus>0.2</avg_ncpus>
<ngpus>0.33</ngpus>
</app_version>
<app_version>
<app_name>setiathome_v8</app_name>
<plan_class>cuda42</plan_class>
<avg_ncpus>0.2</avg_ncpus>
<ngpus>0.33</ngpus>
</app_version>
<app_version>
<app_name>setiathome_v8</app_name>
<plan_class>cuda32</plan_class>
<avg_ncpus>0.2</avg_ncpus>
<ngpus>0.33</ngpus>
</app_version>
<app_version>
<app_name>astropulse_v7</app_name>
<plan_class>opencl_nvidia_100</plan_class>
<avg_ncpus>0.2</avg_ncpus>
<ngpus>0.5</ngpus>
</app_version>
</app_config>

<app>
<name>setiathome_v8</name>
<gpu_versions>
<gpu_usage>1.0</gpu_usage>
<cpu_usage>1.0</cpu_usage>
</gpu_versions>
</app>
For a system with 1 GPUs: 1 GPU tasks would run & 1 CPU cores would be reserved.
For a system with 2 GPUs: 2 GPU tasks would run & 2 CPU cores would be reserved.

. . Thanks for your reply, the quote above was just to test the list function.
[/list]

<app>
	<name>setiathome_v8</name>
	<gpu_versions>
		<gpu_usage>1.0</gpu_usage>
		<cpu_usage>1.0</cpu_usage>
	</gpu_versions>
</app>

• For a system with 1 GPUs: 1 GPU tasks would run & 1 CPU cores would be reserved.
  
• For a system with 2 GPUs: 2 GPU tasks would run & 2 CPU cores would be reserved.
  

. . Thanks for your reply, the quote above was just to test the list function.

247 /* 6/9 (pentium-m "banias"), 6/13 (pentium-m "dothan"), and 6/14 (core1 "yonah")
248 * theoretically support sse2, but it's significantly slower than mmx for
249 * almost all of x264's functions, so let's just pretend they don't. */

You can mix and match. Use the 'Quote' reply button to see the code behind this.

<app>
	<name>setiathome_v8</name>
	<gpu_versions>
		<gpu_usage>1.0</gpu_usage>
		<cpu_usage>1.0</cpu_usage>
	</gpu_versions>
</app>

• For a system with 1 GPUs: 1 GPU tasks would run & 1 CPU cores would be reserved.
  
• For a system with 2 GPUs: 2 GPU tasks would run & 2 CPU cores would be reserved.
  

. . Thanks for your reply, the quote above was just to test the list function.

247 /* 6/9 (pentium-m "banias"), 6/13 (pentium-m "dothan"), and 6/14 (core1 "yonah")
248 * theoretically support sse2, but it's significantly slower than mmx for
249 * almost all of x264's functions, so let's just pretend they don't. */

I've now got a bench report back from Mr. Kevvy, with a very clear outcome:

SSE2 is indeed poor on that chip, with our apps especially at VLAR and VHAR. Base SSE is even worse - which somewhat vindicates the author of that comment.

But SSE3 is running well, significantly faster than stock at all ARs and with good Q.

So I'll see what I can do to make the detection work normally on this hardware too. Anyone still running a banias or a pentium-m we could test?

247 /* 6/9 (pentium-m "banias"), 6/13 (pentium-m "dothan"), and 6/14 (core1 "yonah")
248 * theoretically support sse2, but it's significantly slower than mmx for
249 * almost all of x264's functions, so let's just pretend they don't. */

I've now got a bench report back from Mr. Kevvy, with a very clear outcome:

SSE2 is indeed poor on that chip, with our apps especially at VLAR and VHAR. Base SSE is even worse - which somewhat vindicates the author of that comment.

But SSE3 is running well, significantly faster than stock at all ARs and with good Q.

So I'll see what I can do to make the detection work normally on this hardware too. Anyone still running a banias or a pentium-m we could test?

I still have a Pentium M, Dothan, notebook. It is limited to SSE & SSE2.

247 /* 6/9 (pentium-m "banias"), 6/13 (pentium-m "dothan"), and 6/14 (core1 "yonah")
248 * theoretically support sse2, but it's significantly slower than mmx for
249 * almost all of x264's functions, so let's just pretend they don't. */

I've now got a bench report back from Mr. Kevvy, with a very clear outcome:

SSE2 is indeed poor on that chip, with our apps especially at VLAR and VHAR. Base SSE is even worse - which somewhat vindicates the author of that comment.

But SSE3 is running well, significantly faster than stock at all ARs and with good Q.

So I'll see what I can do to make the detection work normally on this hardware too. Anyone still running a banias or a pentium-m we could test?

I still have a Pentium M, Dothan, notebook. It is limited to SSE & SSE2.

May I FTP you a win32 installer for testing, please? I now have one which should detect and report CPU capabilities accurately on those CPUs (full gory details of that saga on application, later).

Anyone still running a banias or a pentium-m we could test?

I still have a Pentium M, Dothan, notebook. It is limited to SSE & SSE2.

May I FTP you a win32 installer for testing, please? I now have one which should detect and report CPU capabilities accurately on those CPUs (full gory details of that saga on application, later).

I'm game. Do you need a secure place to send it? I made an account on my server for lunatics use several years ago when the kwsn site was having issues. I'll have to see if I can find the password for the account.

Thanks - looking good so far. Mr. Kevvy said that he would check it out when he gets home from work - that usually means overnight for me, because of time zones. Edit - he's just reported that SSE3 is showing up as well.

I'll fix the typos, but probably not bother with a public release until we can cure some of the obesity by dropping MB_v7 support. I'll have to decide what to do about the missing SSSE3, SSE4.1, and SSE4.2 apps then - I may be able to debug a 9KB DLL, but I don't think I'm up to full app optimisation yet.

Thanks - looking good so far. Mr. Kevvy said that he would check it out when he gets home from work - that usually means overnight for me, because of time zones. Edit - he's just reported that SSE3 is showing up as well.

I'll fix the typos, but probably not bother with a public release until we can cure some of the obesity by dropping MB_v7 support. I'll have to decide what to do about the missing SSSE3, SSE4.1, and SSE4.2 apps then - I may be able to debug a 9KB DLL, but I don't think I'm up to full app optimisation yet.

. . Please advise if and when you do such a wonderful thing. I would be most keen to run it.

Stephen

    . . Please advise if and when you do such a wonderful thing. I would be most keen to run it.

    Stephen


You can watch the sticky thread Optimised Applications and Other Binaries for announcements of official installer releases.

    . . Please advise if and when you do such a wonderful thing. I would be most keen to run it.

    Stephen


You can watch the sticky thread Optimised Applications and Other Binaries for announcements of official installer releases.

. . I had a look, how is it sticky?

.

A thread marked as "sticky", by a moderator, is one that always appears first in a specific topic. Unless you have checked "Don't move sticky posts to top" in your settings.

They also get different icons.

. . Hello Richard,

. . Does today's announcement mean extra headaches for you? Now that the promised reason for V8 release has come to be, do you expect any issues?

Stephen

Dont worry.
The apps are tested with GBT tasks.