Here is (probably) every claim made about Fermi or related products made by Charlie in his articles. Post will be updated when reviews come out so we can see his track record. Some details may not actually appear in reviews and some will only emerge when stock does/doesn't become availible, but we should be able to tell whether he's had insider info or just made everything up.
[x] = Confirmed, [O] = Wrong, [?] = Don't Know
A look at the Nvidia GT300 architecture (May 14, 2009)
Miracles happen, GT300 tapes out! (July 29, 2009)
Four more GT300 variants tip up (August 5, 2009)
GT300 to have an NVIO chip (August 13, 2009)
Nvidia GT300 yields are under 2% (September 15, 2009)
Nvidia kills GTX285, GTX275, GTX260, abandons the mid and high end market (October 6, 2009)
Nvidia finally gets Fermi A2 taped out (November 2, 2009)
Fermi massively misses clock targets (November 16, 2009)
Fermi A3 silicon is in the oven (December 10, 2009)
Nvidia castrates Fermi to 448SPs (December 21, 2009)
Nvidia GF100 pulls 280W and is unmanufacturable (January 17, 2010)
Nvidia's Fermi GTX480 is broken and unfixable (February 17, 2010)
SemiAccurate gets some GTX480 scores (February 20, 2010)
Nvidia threatens it's partners at CeBIT (March 2, 2010)
SemiAccurate wrong about Nvidia 480GTX power use (March 12, 2010)
Nvidia tapes out GF108 (March 17, 2010)
Nvidia forces garbage on those wanting GTX480s (March 23, 2010)
Nvidia bends the definition of honesty in GTX480 benches (March 23, 2010)
--
A look at the Nvidia GT300 architecture (May 14, 2009)
[x] Nvidia says October 15 launch date, he disagrees
With no spins and perfect execution, he says November
With one spin, you're into next year (into Q1)
With two spins, you'll have a hard time hitting Q1
Two spins is the most likely looking at past products
[x] Won't come close to R870 [This means the dual-card which we now know as 5970, not the RV870 5870]
Whole article focuses on how the chip is focused on GPGPU, many months before Nvidia announce it as such
Miracles happen, GT300 tapes out! (July 29, 2009)
[?] Late July tapeout
Mid-December for first parts on shelves if no new spins, add 8 weeks per spin [1 spin means February, 2 spins
means April]
[?] Die size of 530mm^2
[x] "Vapourware for 2009"
Four more GT300 variants tip up (August 5, 2009)
[?] Four derivative parts, none taped out by then
GT300 to have an NVIO chip (August 13, 2009)
[?] GT300 has an NVIO chip
Nvidia GT300 yields are under 2% (September 15, 2009)
[?] First A1 silicon back in early September
[?] Low single-digit yields for A1 stepping
[?] 104 die candidates per wafer
Nvidia kills GTX285, GTX275, GTX260, abandons the mid and high end market (October 6, 2009)
[x] All mentioned parts soon to be EOL [in retrospect, he's still saying they did stop production of new GT200 parts and what we see in the channel is very small numbers of warehouse stock coming out, which matches up with the poor stock situation]
[?] No Fermi derivatives taped out
[?] Now claiming 530mm^2 to be a minimum estimate, now claims 23.x by 23.x mm^2
Nvidia finally gets Fermi A2 taped out (November 2, 2009)
[?] A2 taped out a few weeks previously; A2 samples in December
Risk wafers. If A2 was OK then February [matches with earlier estimate for one spin]
If A3 needed then put into March for samples/paper launch
Claims Nvidia is estimating March internally, implying he believes March to be the most likely date
[?] No Fermi derivatives taped out
Fermi massively misses clock targets (November 16, 2009)
[?] Still claiming >530mm^2 die size
[x] 20% clockspeed miss [taking into account later claims of 1500MHz shaders being the internal target, that means 1200MHz.] [They did get 1400MHz, but not at 512 shaders. It would have been 1200MHz at 512]
Fermi A3 silicon is in the oven (December 10, 2009)
[?] Nvidia begins an A3 stepping
[?] First silicon to be back in early January
If risk wafers are still valid, then late February (6+2 weeks). If not, then late March (10+2 weeks).
[?] First A3 silicon able to be shown at CES (no guarantee, just estimating from timing)
[x] Best case: Feb 1; Worst case: April 1 Average case: mid-March. Thinks A4 is unlikely.
[?] Clocks for A2 are 500MHz half-core implying 1000MHz
- A3 will up clocks.
[x] Says that a 500MHz/1000MHz/512SP Fermi would barely beat the 5870 (Since a 1400MHz/480 has a 10-15% lead, a 1000MHz/512SP would beat about level with a 5870)
[?] 'Alarming' yields on A2 [EDIT: Let's say this means single-digit]
Nvidia castrates Fermi to 448SPs (December 21, 2009)
[x] Fermi will only have 448 SPs on Tesla variants.
[x] Says that a 448 SP version will only barely fit in 225W TDP
Speculates that since Tesla is really expensive and small volume, you'd think they would have their best bins in there. As a result, he doesn't expect any consumer versions to also be only 448 shaders and hot.
Fermi may beat Cypress by a little, but more expensive and much hotter
Nvidia GF100 pulls 280W and is unmanufacturable (January 17, 2010)
[?] Revised die size estimate of 550mm^2 (on forums he says initial estimate was only 23.x mm^2 by 23.x mm^2, not precise, and he said the lower figure earlier but new sources mean that .x is higher so therefore ~550.)
Repeats claim of 104 die candidates per wafer
[?] Says a 512SP version of GF100 would pull 280W.
[x] Says initial GF100 chips will be 448 shaders and downclocked considerably. Initial target was 1500-1600MHz but shipping cards will be 1400MHz halo part and 1200MHz 'volume bin'. (Update: and indeed, the 470 is 1250MHz and the 480 1400MHz. If the 480 has real availibility I'll revert this)
[?] Mentions the 'voltage versus amperage' thing contributing to high power consumption
[x] Says no Fermi derivatives will come out before ATI completes its Evergreen lineup
[x] AIBs will get samples in late Feb, March launch
Nvidia's Fermi GTX480 is broken and unfixable (February 17, 2010)
[?] Top bin will launch with 448 shaders and 1200MHz shader clock. A3 did not up clock speeds. (Depends on what he meant by top bin)
[?] Single digit yields
[?] Internal expectations were 1500-1600MHz.
- Reaffirms 280W power draw.
[o] Estimates performance of 448 shaders / 1200MHz as 12% better than the 5870 (was actually worse than he predicted)
SemiAccurate gets some GTX480 scores (February 20, 2010)
[o] GTX480 has 512 shaders, 1200 or 1250MHz shader clock
[x] GTX470 has 448 shaders, 1250MHz shader clock
[o] GTX480 is ~5% faster than a HD5870 (actual: 10-15%, but then he was saying that for different specs to the launch card so it probably works out)
[x] GTX480 will beat an HD 5970 in Unigine on highly tesselated segments
[x] This performance will not be reflected in any other game with tesselation
[?] Nvidia will only have 5000-8000 GTX 480s on launch and will not be producing any more
Nvidia threatens it's partners at CeBIT (March 2, 2010)
[x] GTX470 will perform like an HD 5850
SemiAccurate wrong about Nvidia 480GTX power use (March 12, 2010)
[?] Fermi Tesla cards will have a TDP of 275W (Note: he clarified on forum that this figure was not for the 480, only Tesla)
Nvidia tapes out GF108 (March 17, 2010)
[?] GF108 taped out, will be out in late July / early August
[?] Other derivatives not taped out yet
Nvidia forces garbage on those wanting GTX480s (March 23, 2010)
[?] Retailers must purchase Fermi cards bundles of 10 GTX470s and 10 GTX480s. For each of the bundles, they have to buy 20 G210s, 20 GT220s, 20 GT240s and 20 GTS250s.
Nvidia bends the definition of honesty in GTX480 benches (March 23, 2010)
[?] GTX 480 specs revised to 1401MHz shader clock but only 480 shaders.
[x] The dishonesty in Dirt2 benches (read article for explanation) (Those sites that ran Dirt2 making sure the 480 was in DX11 showed parity, those that used a timedemo causing DX9 showed massive Nvidia lead.)
[x] = Confirmed, [O] = Wrong, [?] = Don't Know
A look at the Nvidia GT300 architecture (May 14, 2009)
Miracles happen, GT300 tapes out! (July 29, 2009)
Four more GT300 variants tip up (August 5, 2009)
GT300 to have an NVIO chip (August 13, 2009)
Nvidia GT300 yields are under 2% (September 15, 2009)
Nvidia kills GTX285, GTX275, GTX260, abandons the mid and high end market (October 6, 2009)
Nvidia finally gets Fermi A2 taped out (November 2, 2009)
Fermi massively misses clock targets (November 16, 2009)
Fermi A3 silicon is in the oven (December 10, 2009)
Nvidia castrates Fermi to 448SPs (December 21, 2009)
Nvidia GF100 pulls 280W and is unmanufacturable (January 17, 2010)
Nvidia's Fermi GTX480 is broken and unfixable (February 17, 2010)
SemiAccurate gets some GTX480 scores (February 20, 2010)
Nvidia threatens it's partners at CeBIT (March 2, 2010)
SemiAccurate wrong about Nvidia 480GTX power use (March 12, 2010)
Nvidia tapes out GF108 (March 17, 2010)
Nvidia forces garbage on those wanting GTX480s (March 23, 2010)
Nvidia bends the definition of honesty in GTX480 benches (March 23, 2010)
--
A look at the Nvidia GT300 architecture (May 14, 2009)
[x] Nvidia says October 15 launch date, he disagrees
With no spins and perfect execution, he says November
With one spin, you're into next year (into Q1)
With two spins, you'll have a hard time hitting Q1
Two spins is the most likely looking at past products
[x] Won't come close to R870 [This means the dual-card which we now know as 5970, not the RV870 5870]
Whole article focuses on how the chip is focused on GPGPU, many months before Nvidia announce it as such
Miracles happen, GT300 tapes out! (July 29, 2009)
[?] Late July tapeout
Mid-December for first parts on shelves if no new spins, add 8 weeks per spin [1 spin means February, 2 spins
means April]
[?] Die size of 530mm^2
[x] "Vapourware for 2009"
Four more GT300 variants tip up (August 5, 2009)
[?] Four derivative parts, none taped out by then
GT300 to have an NVIO chip (August 13, 2009)
[?] GT300 has an NVIO chip
Nvidia GT300 yields are under 2% (September 15, 2009)
[?] First A1 silicon back in early September
[?] Low single-digit yields for A1 stepping
[?] 104 die candidates per wafer
Nvidia kills GTX285, GTX275, GTX260, abandons the mid and high end market (October 6, 2009)
[x] All mentioned parts soon to be EOL [in retrospect, he's still saying they did stop production of new GT200 parts and what we see in the channel is very small numbers of warehouse stock coming out, which matches up with the poor stock situation]
[?] No Fermi derivatives taped out
[?] Now claiming 530mm^2 to be a minimum estimate, now claims 23.x by 23.x mm^2
Nvidia finally gets Fermi A2 taped out (November 2, 2009)
[?] A2 taped out a few weeks previously; A2 samples in December
Risk wafers. If A2 was OK then February [matches with earlier estimate for one spin]
If A3 needed then put into March for samples/paper launch
Claims Nvidia is estimating March internally, implying he believes March to be the most likely date
[?] No Fermi derivatives taped out
Fermi massively misses clock targets (November 16, 2009)
[?] Still claiming >530mm^2 die size
[x] 20% clockspeed miss [taking into account later claims of 1500MHz shaders being the internal target, that means 1200MHz.] [They did get 1400MHz, but not at 512 shaders. It would have been 1200MHz at 512]
Fermi A3 silicon is in the oven (December 10, 2009)
[?] Nvidia begins an A3 stepping
[?] First silicon to be back in early January
If risk wafers are still valid, then late February (6+2 weeks). If not, then late March (10+2 weeks).
[?] First A3 silicon able to be shown at CES (no guarantee, just estimating from timing)
[x] Best case: Feb 1; Worst case: April 1 Average case: mid-March. Thinks A4 is unlikely.
[?] Clocks for A2 are 500MHz half-core implying 1000MHz
- A3 will up clocks.
[x] Says that a 500MHz/1000MHz/512SP Fermi would barely beat the 5870 (Since a 1400MHz/480 has a 10-15% lead, a 1000MHz/512SP would beat about level with a 5870)
[?] 'Alarming' yields on A2 [EDIT: Let's say this means single-digit]
Nvidia castrates Fermi to 448SPs (December 21, 2009)
[x] Fermi will only have 448 SPs on Tesla variants.
[x] Says that a 448 SP version will only barely fit in 225W TDP
Speculates that since Tesla is really expensive and small volume, you'd think they would have their best bins in there. As a result, he doesn't expect any consumer versions to also be only 448 shaders and hot.
Fermi may beat Cypress by a little, but more expensive and much hotter
Nvidia GF100 pulls 280W and is unmanufacturable (January 17, 2010)
[?] Revised die size estimate of 550mm^2 (on forums he says initial estimate was only 23.x mm^2 by 23.x mm^2, not precise, and he said the lower figure earlier but new sources mean that .x is higher so therefore ~550.)
Repeats claim of 104 die candidates per wafer
[?] Says a 512SP version of GF100 would pull 280W.
[x] Says initial GF100 chips will be 448 shaders and downclocked considerably. Initial target was 1500-1600MHz but shipping cards will be 1400MHz halo part and 1200MHz 'volume bin'. (Update: and indeed, the 470 is 1250MHz and the 480 1400MHz. If the 480 has real availibility I'll revert this)
[?] Mentions the 'voltage versus amperage' thing contributing to high power consumption
[x] Says no Fermi derivatives will come out before ATI completes its Evergreen lineup
[x] AIBs will get samples in late Feb, March launch
Nvidia's Fermi GTX480 is broken and unfixable (February 17, 2010)
[?] Top bin will launch with 448 shaders and 1200MHz shader clock. A3 did not up clock speeds. (Depends on what he meant by top bin)
[?] Single digit yields
[?] Internal expectations were 1500-1600MHz.
- Reaffirms 280W power draw.
[o] Estimates performance of 448 shaders / 1200MHz as 12% better than the 5870 (was actually worse than he predicted)
SemiAccurate gets some GTX480 scores (February 20, 2010)
[o] GTX480 has 512 shaders, 1200 or 1250MHz shader clock
[x] GTX470 has 448 shaders, 1250MHz shader clock
[o] GTX480 is ~5% faster than a HD5870 (actual: 10-15%, but then he was saying that for different specs to the launch card so it probably works out)
[x] GTX480 will beat an HD 5970 in Unigine on highly tesselated segments
[x] This performance will not be reflected in any other game with tesselation
[?] Nvidia will only have 5000-8000 GTX 480s on launch and will not be producing any more
Nvidia threatens it's partners at CeBIT (March 2, 2010)
[x] GTX470 will perform like an HD 5850
SemiAccurate wrong about Nvidia 480GTX power use (March 12, 2010)
[?] Fermi Tesla cards will have a TDP of 275W (Note: he clarified on forum that this figure was not for the 480, only Tesla)
Nvidia tapes out GF108 (March 17, 2010)
[?] GF108 taped out, will be out in late July / early August
[?] Other derivatives not taped out yet
Nvidia forces garbage on those wanting GTX480s (March 23, 2010)
[?] Retailers must purchase Fermi cards bundles of 10 GTX470s and 10 GTX480s. For each of the bundles, they have to buy 20 G210s, 20 GT220s, 20 GT240s and 20 GTS250s.
Nvidia bends the definition of honesty in GTX480 benches (March 23, 2010)
[?] GTX 480 specs revised to 1401MHz shader clock but only 480 shaders.
[x] The dishonesty in Dirt2 benches (read article for explanation) (Those sites that ran Dirt2 making sure the 480 was in DX11 showed parity, those that used a timedemo causing DX9 showed massive Nvidia lead.)
Last edited: