![]() ![]() Sure hope so, but probably not with the current generation of silicon. Even the fastest GPU won't help you if transferring the data takes a fraction of a second. requires large amounts of data to be transferred to and from GPU quickly the delay can be noticeable with the usual PCIe bottleneck. Unified memory and large caches help too, especially with video work. There are other ways to estimate performance for these tasks though, e.g. Of course, I fully agree that Geekbench is not really useful for creatives, simply because creative workflows are usually connected to specific software suites. That's not the usual definition of sustained performance (aside of course things like rendering or encoding). Is this really the case though? I was always under impression that creative workflows are about bursty workflows - applying user-initiated processing steps which should ideally get completed as quickly as possible. At the same time Apple excels at many real-world tasks such as code compilation or scientific computations.īTW, the problem with “faster memory” you mention was in Geekbench 3. You cant win them all, there are choices to be made. Apple CPUs simply do not have the raw clocks, per-instruction SIMD throughout or cache bandwidth of x86 CPUs - and these things contribute to why Apple can be as fast with 5 watts of power as Intel is with 20 or more watts of power in general purpose processing. In part, this is a deliberate choice on Apples side in order to make their systems more energy efficient. Second, we know very well why Apple Silicon performs poorly in Cinebench. So Geekbench actually overestimates x86 performance under sustained scenario. This is primarily a problem with x86 CPUs where “base” and “boost” clock can vary by up to 40-50%. Not quite sure what you are arguing for? First, Apple Silicon does not suffer much from throttling under sustained operation because its dynamic clock range is much lower. Hence we know the performance disparity between devices A and B is twice as large with the GB6 tasks than the GB5 tasks. ![]() That means device B is twice as fast as A on the GB5 tasks, but four times as fast on the GB6 tasks. purely for illustration): Suppose devices A and B respectively score 10 in GB5, and 20 in GB6. This is independent of which benchmark you're in, or what device was used to calibrate it.Ĭonsequently (using simple nos. Then device B's score for that task will be twice that of device A's. Making this more explicit: Assuming Primate's phrasing properly describes how they are generating their scores, the following would hold: Suppose, on a specific task, completion takes device A 20 seconds and device B 10 seconds. Since the scores are proportional to speed of task completion ("double the score is double the performance") in both GB5 and GB6, the respective devices used as baselines in GB5 and GB6 have no effect on the performance ratios. non-distributed tests within their MT benchmark.Ĭlick to expand.Nope. It comes down to the relative number of distributed vs. We might run the same program on several different targets, or several different variant programs on a single target.Īnd I wouldn't be so quick to say GB is now testing for the 80% case, since the overwhelming majority of programs remain single-threaded. And when we're doing development work on our local machines, we're doing exactly the same thing. My university's computer clusters are filled by people who are each doing exactly what I describe-running as many single-threaded jobs as the clusters' schedulers will allow. You're making a common mistake-assuming workflows outside your personal experience aren't "real world". Click to expand.This is typical for many scientists who do computer modeling, and write our own code*. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |