Tesla partners with AMD/GloFo for self driving car AI processor
Quote:
Tesla is already running tests on the first processor versions, says an insider.
Read more.
Re: Tesla partners with AMD/GloFo for self driving car AI processor
Always wondered what Jim was going to do at Tesla, its all becoming clear :)
Re: Tesla partners with AMD/GloFo for self driving car AI processor
Tesla have 'noticed' AMD compute capabilities but you will need an extra 1 hour of charge just to power it....Vega-Chronicles on wattage. Nvidia Pascal is amazing on power efficiency. I don't know what AMD is planning with Navi just maybe it will be at par with Pascal!
Re: Tesla partners with AMD/GloFo for self driving car AI processor
Quote:
Originally Posted by
lumireleon
Tesla have 'noticed' AMD compute capabilities but you will need an extra 1 hour of charge just to power it....
That you think this demonstrates a profound misunderstanding of the power curves of AMD's current processor lines.
When pushed hard to achieve peak performance yes, AMD's current CPUs and GPUs start burning a lot of power. But when you back off the clock speeds just a little, the power requirements drop exponentially. Remember that they have 32 core EPYC chips out there that can operate with TDPs as low as 140W, and ASUS have produced a laptop with an RX580 tuned to just 65W TDP. AFAIK that slow-but-wide approach is perfect for autonomous driving, which requires huge throughput of many relatively simple individual tasks.
Re: Tesla partners with AMD/GloFo for self driving car AI processor
Quote:
Originally Posted by
lumireleon
Tesla have 'noticed' AMD compute capabilities but you will need an extra 1 hour of charge just to power it....Vega-Chronicles on wattage. Nvidia Pascal is amazing on power efficiency. I don't know what AMD is planning with Navi just maybe it will be at par with Pascal!
AMD overvolted Vega and also pushed its clocks pretty high.
Essentially, you say Pascal is amazing on efficiency... that's because its made on a manuf. process optimized for high clock speeds, and in reality is just an overclocked Maxwell.
AMD made Vega on a manuf. process more suited for lower clocks.
Also, when undervolted and ovrerclocked on the core and HBM, Vega 56 beats 1080 in performance and draws less power than 1080.
Vega also reaches Pascal performance with much lower clock speeds btw... so what exactly does that tell you?
I am sick of people projecting this outdated garbage of 'Nvidia has the efficiency crown' when they don't understand the underlying manufacturing processes used behind both them and AMD and clock rates... let alone software optimizations (that can easily extract massive performance from the hardware... right now, Vega hasn't been optimized by developers at all).
Re: Tesla partners with AMD/GloFo for self driving car AI processor
....current VEGA cards are 25% more power hungry at the same performance of a comparable Nvidia Card yet they use 'efficient' HBM2
Re: Tesla partners with AMD/GloFo for self driving car AI processor
So now cryptocurrency miners will now be buying all available Tesla 3 cars pushing the prices up :)
(note to the Internet: that was a joke)
Re: Tesla partners with AMD/GloFo for self driving car AI processor
Wonder if that will ever become a thing, car based mining malware, "Car loses charge in 50 miles cant figure out why"
Re: Tesla partners with AMD/GloFo for self driving car AI processor
Quote:
Originally Posted by
Platinum
Wonder if that will ever become a thing, car based mining malware, "Car loses charge in 50 miles cant figure out why"
If it honks the horn every time it finishes a block things could get noisy :D
I suppose a hashing system could be created that targets tensor operations so that only a TPU can get good hashing rates, like the GPU optimised coins you can get.
Re: Tesla partners with AMD/GloFo for self driving car AI processor
hahaha mining craze Tesla will mine to get extra profits. (maybe AMD mines illegally the same way Google does with Chrome)
Re: Tesla partners with AMD/GloFo for self driving car AI processor
Quote:
Originally Posted by
lumireleon
... (maybe AMD mines illegally the same way Google does with Chrome)
Erm ... what? Google doesn't mine with Chrome. Even if it did it wouldn't be illegal.
You're maybe getting confused about a small number of websites that have recently added javascript mining software as an alternative to running adverts, and one third party Chrome add-in that was surreptitiously mining in the background. None of that is illegal (although some would question the ethics of running complex computations on someone else's computer without warning)...
Re: Tesla partners with AMD/GloFo for self driving car AI processor
Quote:
Originally Posted by
Platinum
Wonder if that will ever become a thing, car based mining malware, "Car loses charge in 50 miles cant figure out why"
Nothing to do with the car's processor but fill your EV with 10 or 20 mining rigs hooked up to the battery. Plug your car into one of the free charging stations. Profit.
I'm joking of course but I wouldn't put it past some people... :crazy:
Re: Tesla partners with AMD/GloFo for self driving car AI processor
Quote:
Originally Posted by
deksman2
AMD overvolted Vega and also pushed its clocks pretty high.
Essentially, you say Pascal is amazing on efficiency... that's because its made on a manuf. process optimized for high clock speeds, and in reality is just an overclocked Maxwell.
AMD made Vega on a manuf. process more suited for lower clocks.
Also, when undervolted and ovrerclocked on the core and HBM, Vega 56 beats 1080 in performance and draws less power than 1080.
Vega also reaches Pascal performance with much lower clock speeds btw... so what exactly does that tell you?
I am sick of people projecting this outdated garbage of 'Nvidia has the efficiency crown' when they don't understand the underlying manufacturing processes used behind both them and AMD and clock rates... let alone software optimizations (that can easily extract massive performance from the hardware... right now, Vega hasn't been optimized by developers at all).
I cannot help but read this quote and think of the Jeremy Clarkson Top Gear test of the Toyota prius.
This is typical fanboy AMD stuff. Your justifying your purchase. There are tiny reasons why AMD is good, but Geforce has always been better than AMD, period. Your AMD gpu might be more cost purchase/power efficient or whatever. But it is like me driving a 1.2litre comparing my mates 1.8i. Only reason to buy a Vega is ignorance or budget.
Quote:
Originally Posted by
deksman2
Also, when undervolted and ovrerclocked on the core and HBM, Vega 56 beats 1080 in performance and draws less power than 1080.
Vega also reaches Pascal performance with much lower clock speeds btw... so what exactly does that tell you?
Vega undervoltage may be in some ways better than the Nvidia gpu and there may be some tasks the AMD gpu can do better than the Nvidias such as mining. But that is like comparing the heater's in each others cars, not how they are to drive. Vega might be better at mining with undervoltage but is that going to get you 2100mhz?
(turning Dave off)
Re: Tesla partners with AMD/GloFo for self driving car AI processor
Quote:
Originally Posted by
Troopa
... This is typical fanboy AMD stuff. ...
... Geforce has always been better than AMD, period. ...
Oh, the irony... :rolleyes:
Re: Tesla partners with AMD/GloFo for self driving car AI processor
Quote:
Originally Posted by
DanceswithUnix
...
(note to the Internet: that was a joke)
Dammit. Just as I was reaching for my "World's Greatest Pedant" hat, you have to ruin it. You're no fun these days.
:D
Re: Tesla partners with AMD/GloFo for self driving car AI processor
Quote:
Originally Posted by
Saracen
.. I was reaching for my "World's Greatest Pedant" hat..
I do hope it's made out of 100% real cotton. And the single most intricately patterned hat on earth. With eye-searing contrasting colours that frustrate everyone in visual range.