NVIDIA Slaughters AMD Catalyst On Linux In OpenGL 4.x Micro-Benchmarks

[Daktyl198]

I am pretty happy with 14.6. (Almost) no reason to complain.

Like I said, that is all based on what I've heard. I personally only have Intel graphics in my laptop, so I have no experience with either of those GPU vendors on non-Windows machines.

[molecule-eye]

So AMD loses badly on some synthetic tests created by nvidia. What does this say for real world performance for real world consumers? Nothing?

[xpander]

So AMD loses badly on some synthetic tests created by nvidia. What does this say for real world performance for real world consumers? Nothing?

a lot.. in real world its not that huge difference..but if highest end AMD GPU gets beaten by midrange nvidia...something must be terribly wrong

[Mat2]

Calm down. These benchmarks were written by a NVIDIA guy so they *may* not be objective.

[Daktyl198]

a lot.. in real world its not that huge difference..but if highest end AMD GPU gets beaten by midrange nvidia...something must be terribly wrong

Again, an NVidia employee wrote this test, and he targeted NVidia cards specifically...

[dungeon]

Again, an NVidia employee wrote this test, and he targeted NVidia cards specifically...

Yep apitest is just writted by Nvidia for one GDC session to show that there is already "fast path" in their OpenGL dirver .





etc. http://www.slideshare.net/CassEverit...river-overhead

Just to point out... when they say "OpenGL", they mean our OpenGL implementation ;D.

[log0]

a lot.. in real world its not that huge difference..but if highest end AMD GPU gets beaten by midrange nvidia...something must be terribly wrong

This benchmark tests the driver, the implementation/performance of a certain API subset, not the gpu performance!

[Britoid]

DirectX on a nVidia card outperforms Mantle on a similar spec AMD card.

Still waiting for AMD Drivers to not cause broken cursor on Windows with a multiple monitor setup.

[grndzro]

I wonder how many of those tests have alternative implementations using AMD extensions.

A benchmark made by Nvidia should be taken with a huge grain of salt.

[brad0]

Still waiting for AMD Drivers to not cause broken cursor on Windows with a multiple monitor setup.

Still waiting for good open source NVIDIA drivers so I can use their hardware, until then its a paper weight.