[HN Gopher] Evaluating Graviton 2 for data-intensive application... ___________________________________________________________________ Evaluating Graviton 2 for data-intensive applications: Arm vs. Intel comparison Author : Aissen Score : 37 points Date : 2022-04-05 18:45 UTC (4 hours ago) (HTM) web link (redpanda.com) (TXT) w3m dump (redpanda.com) | CyanLite2 wrote: | cliff notes? | | Site seems to have been hugged to death | pzarex wrote: | Link works for me... | | TL;DR, Arm instances give better bang for the buck... | bhouston wrote: | Interesting to see that it has higher throughput per $. That is | the most important fact. | zokier wrote: | Of course more perf/$ is the whole selling point of graviton so | it would be pretty big failure somewhere if that were not the | case | BeeOnRope wrote: | Yes, but I think one thing that is interesting here is that | these Graviton 2 instance types also offer, for example, | better IO throughput or storage/$ even though the CPU | architecture doesn't obviously affect that (i.e., it's not | like you get access to a new source of quality NAND chips to | build SSDs when you switch your CPU). | | Another thing I found interesting was that the porting | process was painless for this native application. There are | lots of examples of quick wins on Graviton for interpreted or | bytecode/JIT'd languages where the runtime exists on Arm and | the software just works, but porting a complex native | application would seem to pose more problems. In our case, | however, it was quite straightforward (more than I would have | expected). | agallego wrote: | perf is important, but predictability of the SSD perf is | honestly just (if not more) valuable, specially when you have | to build SLA's for your products. | BeeOnRope wrote: | Yeah, these instance types look strong and it seems that Amazon | is also innovating in the local storage space as well as I | don't find many of the usual gotchas with SSDs there (long GC | pauses, etc). | | We may be moving to a future where cloud hardware stops being | "just OK" and a low maintenance version of what you could build | yourself, but actually offering unobtainable-by-mere-mortals | hardware and firmware (we are already seeing this for e.g. with | quantum computing options in the cloud and even arguably GPUs | and ML accelerators). | ceeplusplus wrote: | It is still vastly cheaper to buy your own GPUs and ML | accelerators than to rent from cloud providers for any | reasonable level of utilization (i.e. not a hobby). | BeeOnRope wrote: | My point was that there are accelerators in the cloud which | are not available to purchase by the general public and for | a time the same applied also to GPUs in a practical sense | (i.e., GPUs were being sold in principle but were out of | stock for months on end). | | Depending on your individual time value of money, it can | make sense to rent even a high rate so you can access this | hardware _now_. | ip26 wrote: | I'm excited on behalf of the scientists I know for cloud | HPC. | | I see a lot of " _develop program locally on tiny subset of | data_ " followed by " _how the hell am I ever going to run | the full model for the final run on all the data!?_ " | | A couple hours machine time leased on a behemoth is really | the ticket, and not really that expensive. | zozbot234 wrote: | The cost of data egress from the cloud really limits its | potential for most HPC applications, though. The "free" | or reasonable-cost tiers are okay for small-scale toy | use, but not much more than that. | sharpy wrote: | Recently worked on migrating a number of services (largely CPU | bound) to Graviton 2. It was a bit of hit and mess. For some | services, it worked great. Very negligible hit to performance, | and since equivalent Graviton2 instances cost 20% less, it was a | no brainer. Others needed a little bit of rewrite. There were | also a couple that just didn't see good performance on ARM (very | branchy code) | BeeOnRope wrote: | Interesting. Other than branchy-ness, was there anything else | you think correlated to poorer performance on Graviton 2. | ceeplusplus wrote: | Branchy-ness usually also correlates with cache friendliness | (e.g. branchy code is usually a server app calling lots of | different functions, with lots of virtual function calls), | and Graviton2 has an abnormally small L3 cache relative to | its x86 competitors. If I had to hazard a guess I'd say | heavily vectorized code will also perform worse especially | compared to Intel instances where you have AVX-512. | BeeOnRope wrote: | I wrote this, happy for any feedback or to answer any question | about the methodology or otherwise. | | One thing note is that the headline difference between these | instances types is the CPU architecture, the value offered by | these instance types is as much about how many IOPS and how much | SSD space EC2 chooses to offer for each family, especially for | this IO-bound benchmark. | | It is entirely plausible that EC2 will offer more hardware bang- | for-buck on Graviton instances in an effort to encourage adoption | so we can't necessarily draw a strong conclusion about the future | of the Arm vs x86 battle on the server CPU front since Amazon is | not an Arms-length entity here (pun intended). | Uehreka wrote: | One bit of feedback, it's a good idea to put "higher is better" | or "lower is better" on graph axes. | BeeOnRope wrote: | Thanks, this is great feedback that I'll implement next time. | You are right that it is not always obvious especially when | talking about both throughput (higher is better) and latency | (lower is better) in the same post. ___________________________________________________________________ (page generated 2022-04-05 23:01 UTC)