Bondrewd
Veteran
He's been dropping Ampere spec sheets since early 2019.Who is this twitter user and what's their track record?
Accurate to a T.
He's been dropping Ampere spec sheets since early 2019.Who is this twitter user and what's their track record?
There's Raja in the architecture day stream talking (with a smile) about still having scars on his back for trying to bring expensive like HBM to gaming at least twice." (timestamp 1:26:48)I believe Raja said, in an Intel video, that he learned that hbm was costly, something like that. But I didn't remember the word "regret".
Who would have thought that "organic substrate" was such a literal thing.There's Raja in the architecture day stream talking (with a smile) about still having scars on his back for trying to bring expensive like HBM to gaming at least twice." (timestamp 1:26:48)
So "GA104 can't beat it". Big Navi is faster than RTX 3070, mkay.
Who is this twitter user and what's their track record?
This doesn't look very convincing. The number of SPs for each SKU should be locked in during design years ago.Well, according to his ~14 months old leak:
RTX 3090 has 5248, so it corresponds well. RTX 3080 has 4352, so Nvidia maybe decided to make it more powerful than the GA103's configuration (3840) allowed.
- GA102 = 5376 SPs / 384bit
- GA103 = 3840 SPs / 320bit
- GA104 = 3072 SPs / 256bit
- GA106 = 1920 SPs / 192bit
- GA107 = 1280 SPs / 128bit
Was one who created the whole Nvidia-Samsung 10/8nm train, retweeted this latest RTX/DLS/Control/Wolf. bs. Other than that he's been... vague?
And exactly because of that Nvidia couldn't change configuration of GA103 and used cut-down version of GA102 instead.This doesn't look very convincing. The number of SPs for each SKU should be locked in during design years ago.
After the "Poor Volta" debacle it's great to see AMD shut their mouth and hopefully just let the product speak for itself. Early over-hyped marketing makes for disappointment if the product doesn't deliver. Plus they're just probably waiting to see Nvidia's hand.Oh yeah, makes me wish AMD was less lazy with their marketing.
After the "Poor Volta" debacle it's great to see AMD shut their mouth and hopefully just let the product speak for itself. Early over-hyped marketing makes for disappointment if the product doesn't deliver.
AMD shut their mouth? Really!!!
What about the constant talk/articles about Big-Navi being the 2080Ti killer that I have seen like forever.
Yeah but they're not talking their stellar track record CPUs either.After the "Poor Volta" debacle it's great to see AMD shut their mouth and hopefully just let the product speak for itself
No one knows.when is AMD’s?
None of that is AMD, they've mentioned their Q4 lineup (not even all of it) thrice during three ER calls. That's it.What about the constant talk/articles about Big-Navi being the 2080Ti killer that I have seen like forever.
Their CFO also said the high-end part launches before consoles, and that's roughly it.All comparisons AMD did regarding RDNA2 were relative to their own previous products, so far. At some point Lisa Su said their GPUs in 2020 would be competitive in the high end, and that's all.