Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Cloud TPUs in Beta

cloudplatform.googleblog.com

Post reply on HN
Print view View original

131–138 of 138 posts

Re: Cloud TPUs in Beta

#131

Post by whataretensors »

puzzle wrote: post #83
whataretensors wrote: post #75

Earlier quoted context omitted.

That's my point. Competitors are largely moated out by high costs of TPU production and proprietary drivers.

Why are proprietary drivers a blocker? As long as you expose the same gRPC interface, your customers don't need to know what happens behind the scenes. You could have an FPGA or a Beowulf cluster of Raspberry Pis hiding.

I should clarify. I like all the individual pieces(hardware, cloud services, grpc interface) I just wish you could opt into them independently.

Re: Cloud TPUs in Beta

#132

Post by shafyy »

danjoc wrote: post #95
shafyy wrote: post #56

Earlier quoted context omitted.

Regardless of the TOS saying that or not (I haven't read them), I can think of at least two reasons why your statement doesn't hold: 1) AI startups usually don't have a lot of value to potential acquirers based on their data, but based on other things (e.g., talent, customers, business model, platform, brand). That's like saying you shouldn't use AWS because Amazon can just steal and commercialize all your data. 2) T…

>They can surely look at it and maybe do stuff with them internally, but I am pretty sure that they can't use them commercially. How would you ever know if they did? People who worked at Google have been accused, by Google, of stealing the entire self driving car program and taking it to a competitor.

First of all, that's wrong (as another comment pointed out). Of course, the probability of them stealing your stuff is non-zero, but it's very rare. Even if you use all your own hard and software, people still can steal your stuff :-)

Re: Cloud TPUs in Beta

#133

Post by danjoc »

shafyy wrote: post #132
danjoc wrote: post #95

Earlier quoted context omitted.

>They can surely look at it and maybe do stuff with them internally, but I am pretty sure that they can't use them commercially. How would you ever know if they did? People who worked at Google have been accused, by Google, of stealing the entire self driving car program and taking it to a competitor.

First of all, that's wrong (as another comment pointed out). Of course, the probability of them stealing your stuff is non-zero, but it's very rare. Even if you use all your own hard and software, people still can steal your stuff :-)

I can be hacked by malware which can leak secrets from air gapped, Faraday caged machines. Therefore, I should put my billion dollar idea on the public cloud and just trust Google.

I shiggy diggy.

Re: Cloud TPUs in Beta

#134

Post by thousandx »

jacksmith21006 wrote: post #50
mobileexpert wrote: post #36

I assume Azure and AWS have some buddying up with Intel/Nervana and Nvidia counterstroke to Google TPUs. I can’t quite imagine what it will be though.

Amazon announced today they are working on their own TPU type chips.

Do you have a link for that?

Re: Cloud TPUs in Beta

#135

Post by jacksmith21006 »

thousandx wrote: post #134
jacksmith21006 wrote: post #50

Earlier quoted context omitted.

Amazon announced today they are working on their own TPU type chips.

Do you have a link for that?

"Amazon is reportedly following Apple and Google by designing custom AI chips for Alexa"

https://www.theverge.com/2018/2/12/17004734/amazon-custom-al...

Re: Cloud TPUs in Beta

#136

Post by trevyn »

boulos wrote: post #67

Disclosure: I work on Google Cloud. I want to highlight this paragraph from the post: > Here at Google Cloud, we want to provide customers with the best cloud for every ML workload and will offer a variety of high-performance CPUs (including Intel Skylake) and GPUs (including NVIDIA’s Tesla V100) alongside Cloud TPUs. We fundamentally want Google Cloud to be the best place to do computing. That includes AI/ML and so…

>We fundamentally want Google Cloud to be the best place to do computing.

Lower. Network. Egress. Pricing. By. Two. Orders. Of. Magnitude.

Market rate is close to $1 per TB outbound. Your rate is $80-$120 per TB. That's just embarrassing.

Re: Cloud TPUs in Beta

#137

Post by dogma1138 »

oneshot908 wrote: post #126
boulos wrote: post #120

Earlier quoted context omitted.

That doesn’t prove that the chip operates at 16 bits. For example, we could do 18-bit multipliers (or anything >= 16) and still use 16-bit floats.

ATI demonstrated FP24 was frickin' awesome over a decade and a half ago. it wouldn't surprise me in the least if you went somewhere like that, but it perplexes me as to why you think that's secret sauce in any way long after ATI nearly destroyed NVIDIA with FP24 back in the early days of DirectX 9 and NV3x.

This isn’t exactly correct. ATI pulled a “fast one” and went with 24bit despite the initial DX9 spec called for 16/32 bit floats which NVIDIA followed.

Once DX9 was split into DX9b and c that “advantage” went away and NVIDIA proved that 16/32 bit was better, something that ATI also had to adopt once MSFT told them enough is enough.

24bit is only better as long as it can do everything 32bit can do and it’s advantageous to build a hardware with 24bit FPUs instead of 32bit FPUs that can also do 2x16bit ops per cycle.

Basically if the silicon cost allow you to put far more 24bit FPUs than 32/16bit ones.

And history proved that this isn’t the case.

For gaming eventually even 2:1 FPUs went away since they are costlier than only 32bit FPUs with promotion.

Maybe in the future we’ll have a 24bit FPU that can also do 3 8bit ops or 16bit+8bit op per cycle if it will be more beneficial than the current 2:1 16/32bit model.

Re: Cloud TPUs in Beta

#138

Post by oneshot908 »

dogma1138 wrote: post #137
oneshot908 wrote: post #126

Earlier quoted context omitted.

ATI demonstrated FP24 was frickin' awesome over a decade and a half ago. it wouldn't surprise me in the least if you went somewhere like that, but it perplexes me as to why you think that's secret sauce in any way long after ATI nearly destroyed NVIDIA with FP24 back in the early days of DirectX 9 and NV3x.

This isn’t exactly correct. ATI pulled a “fast one” and went with 24bit despite the initial DX9 spec called for 16/32 bit floats which NVIDIA followed. Once DX9 was split into DX9b and c that “advantage” went away and NVIDIA proved that 16/32 bit was better, something that ATI also had to adopt once MSFT told them enough is enough. 24bit is only better as long as it can do everything 32bit can do and it’s advantageou…

I personally would stick to FP32 across the board for my ML efforts, but we have an entire cottage industry of people coming up with approximations to drive up perf and perf/W, all of which will prove irrelevant until Moore's Law runs out IMO. And even then, I'll still stick to FP32 personally. Speaking from direct experience, bulletproof mixed precision is tough.
Post reply on HN