french toast
Veteran
What? Is that not what you said in my quote?
113 seconds and process as many frames as possible in that time frame. .. seems spot on to me mate.
Kishonti GFXbench
- Thread starter Ailuros
- Start date
What? Is that not what you said in my quote?
113 seconds and process as many frames as possible in that time frame. .. seems spot on to me mate.
It's not a time limit, it's the duration of an animation sequence (warrior in shiny armour explores an ancient temple, a fight ensues). All GPUs complete the animation sequence in 113 seconds, but some render the animation more fluid than others. The 100th frame on one GPU can be a totally different point in animation time than the 100th frame on another GPU since the animation is time based, not frame based.
On The Verge's Tegra 4 video, they (nvidia) use a GLBenchmark test that I haven't seen before C24Z16 Offscreen ECT1, how does that compare with the regular C24Z16 Offscreen in terms of performance?
From 1.10 onwards
http://www.youtube.com/watch?v=asQUdRKYVrQ
From 1.10 onwards
http://www.youtube.com/watch?v=asQUdRKYVrQ
ETC is a texture compression, different vendors support different TCs, probably nvidia monitoring perf with different TC algoritms to be sure that they do not loosing anywhere, so nothing special here
Tis is the 1st Mali-450MP I've seen posted.
http://www.glbenchmark.com/phonedetails.jsp?benchmark=glpro25&D=Huawei+U9510+(Mali-450+MP)
Looks like a low core count.
Running on a Huawei device. I wonder is this a hisilicon soc? are there any announced mali-450MP socs ?
http://www.glbenchmark.com/phonedetails.jsp?benchmark=glpro25&D=Huawei+U9510+(Mali-450+MP)
Looks like a low core count.
Running on a Huawei device. I wonder is this a hisilicon soc? are there any announced mali-450MP socs ?
I'm not entirely sure what you mean, but it is my understanding that all interested IHVs try to contribute in the best way possible for GLB development. When 2.5 launched it was quite a bit steeper in the geometry department than it ended up to be and I guess that Kishonti might have received quite a few protests about it (if not from all of them) and trimmed it down a bit.
If you mean that IHVs optimize their drivers for it, I'd be very surprised if they wouldn't.
Nebuchadnezzar
Legend
Is the T-Rex demo extremely shader heavy that the scores have been scrambled up that much between architectures?
AFAIK there have been very significant changes since I left IMG, so it's likely different and doesn't have a single huge bottleneck anymore, but in an early version, I tried disabling the foliage (many alpha tested layers with an ALU-heavy pixel shader) by modifying the vertex shader to output a dummy position. The overall performance of the entire benchmark increased by about 3x on all handheld architectures.
Also somewhat annoying that the Exynos Galaxy S4 (and maybe other Android SGX devices?) fails to compile all the GLB2.7 shaders so it's impossible to benchmark. James, this is a disgrace, how dare you prioritise compiler optimisation over bugfixing! Oh wait, oops
Well first DXBenchmark2.7 from Kishonti are also available now: https://dxbenchmark.com/result.jsp
Tegra3 seems to come along ahead the Adreno225 unlike GLB2.7; oh and a HD7970 is about 8.6x times faster than the current fastest Intel HD4000. Nothing unexpected really
Tegra3 seems to come along ahead the Adreno225 unlike GLB2.7; oh and a HD7970 is about 8.6x times faster than the current fastest Intel HD4000. Nothing unexpected really
330 gets about 30% higher sore in 2.7 than ipad4
http://glbenchmark.com/phonedetails.jsp?D=LG+D801&benchmark=glpro27
http://glbenchmark.com/phonedetails.jsp?D=LG+D801&benchmark=glpro27
http://forum.beyond3d.com/showthread.php?t=61025&page=15
Judging from the fillrate results only (which doesn't guarantee anything as the S800 obviously has more bandwidth too than a S600) the 330 might be clocked at ~480MHz and not at the 450MHz the Qualcomm roadmap indicated.
french toast
Veteran
Im quite shocked at that to be honest...still outside of shader optimised code sgx 554 mp4 pulls ahead...not unexpectedly considering it has Something daft like 8 tmus and more rops.
Hmm, a Snapdragon 800 clocked at only 1.7 GHz, smells fishy. Either the HPM process is not yielding the results they expected, or this is the Nexus 5 prototype which would still be a good boost over the N4, and not cane the battery.
Its not the Nexus, the build name suggests its the LG Optimus G2 for t-mobile
Nexus 4 had mako/occam codenames, this fits in with LGs product line rather than Nexus series
And other than fansites trolling for hits, it has never really been confirmed that LG has the contract this year
Impressive result relatively speaking, but still completely unplayable at these framerates. Using the 2.5 benchmark that is at least on the verge of being playable in terms of framerates, note that the SGX 554MP4 in ipad 4 appears to be about 20% faster in GLBenchmark 2.5 Egypt HD Offscreen (1080p) than the Adreno 330 used in this LG device (notice that the LG device tested here appears to have a 1080p screen resolution, so the 2.5 Egypt HD Onscreen score will be approximately equal to the 2.5 Egypt HD Offscreen (1080p) score).
Similar threads
