GeForce GTX 880 | KitGuru https://www.kitguru.net KitGuru.net - Tech News | Hardware News | Hardware Reviews | IOS | Mobile | Gaming | Graphics Cards Fri, 27 Feb 2015 02:56:32 +0000 en-US hourly 1 https://wordpress.org/?v=6.4.3 https://www.kitguru.net/wp-content/uploads/2021/06/cropped-KITGURU-Light-Background-SQUARE2-32x32.png GeForce GTX 880 | KitGuru https://www.kitguru.net 32 32 Overclocker sets new GPU clock-rate record with GeForce GTX 980 https://www.kitguru.net/components/graphic-cards/anton-shilov/overclocker-sets-new-gpu-frequency-record-with-geforce-gtx-980/ https://www.kitguru.net/components/graphic-cards/anton-shilov/overclocker-sets-new-gpu-frequency-record-with-geforce-gtx-980/#respond Sat, 07 Feb 2015 01:43:33 +0000 http://www.kitguru.net/?p=234545 A top overclocker has managed to set a new frequency record for graphics processing units after he pushed GPU frequency of EVGA GeForce GTX 980 Classified all the way to 2250MHz. The incredibly high clock-rate also allowed him to set a new 3DMark FireStrike Extreme record for single-GPU setups. Steponz, a leading overclocker from the U.S., …

The post Overclocker sets new GPU clock-rate record with GeForce GTX 980 first appeared on KitGuru.]]>
A top overclocker has managed to set a new frequency record for graphics processing units after he pushed GPU frequency of EVGA GeForce GTX 980 Classified all the way to 2250MHz. The incredibly high clock-rate also allowed him to set a new 3DMark FireStrike Extreme record for single-GPU setups.

Steponz, a leading overclocker from the U.S., has managed to overclock his EVGA GeForce GTX 980 Classified ACX 2.0 4GB graphics card to 2250MHz for the GPU and 8712MHz for GDDR5 memory. The graphics board was cooled down using liquid nitrogen (LN2).

steponz_evga_overclocking_ln2_nitrogen_geforce_gtx_980

At present 2.25GHz is the world’s record clock-rate for any graphics processing unit, which is 49MHz higher than the previous record set by Vince “K|NGP|N” Lucido several months ago. Unfortunately, the frequency of GDDR5 memory did not make it to 9GHz, another record set by Mr. Lucido last November using the same graphics card.

image_id_1337566

Using a test-rig powered by an Intel Core i7-5960X processor clocked at 5.815GHz (also cooled-down using liquid nitrogen), a Gigabyte X99 SOC Champion mainboard and 16GB of 3.10GHz DDR4 memory, Steponz scored 10075 points in 3DMark FireStrike Extreme benchmark, the highest result for a single-GPU setup ever achieved.

evga_geforce_gtx_980_classified_3

The EVGA GeForce GTX 980 Classified ACX 2.0 4GB graphics card is among the highest-performing GM204-based graphics adapters that money can buy. Thanks to major improvements of PCB design, the EVGA GeForce GTX 980 Classified has been the graphics card of choice of extreme overclockers for months since it has enabled great GPU and memory overclocking results.

Recently EVGA launched its new GeForce GTX 980 K|NGP|N Edition graphics card with ACX 2.0+ cooler and additional enhancements in design. It is expected that the new printed-circuit board and other tweaks will enable overclockers to further push the limits of Nvidia’s GM204 graphics processing unit.

Discuss on our Facebook page, HERE.

KitGuru Says: Looks like the EVGA GeForce GTX 980 Classified still has some overclocking potential left since nearly 50MHz frequency increase seems rather significant at such extreme clock-rates. It will be tremendously interesting to see what the EVGA GeForce GTX 980 Kingpin Edition is capable of. Vince “K|NGP|N” Lucido achieved 2.20GHz GPU clock-rate on the card relatively easy, but so far he has not publicly tried to boost the frequency further. Will it hit 2.30GHz?

The post Overclocker sets new GPU clock-rate record with GeForce GTX 980 first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/overclocker-sets-new-gpu-frequency-record-with-geforce-gtx-980/feed/ 0
EVGA unveils GeForce GTX 980 K|NGP|N ACX 2.0+ graphics card https://www.kitguru.net/components/graphic-cards/anton-shilov/evga-unveils-geforce-gtx-980-kngpn-acx-2-0-graphics-card/ https://www.kitguru.net/components/graphic-cards/anton-shilov/evga-unveils-geforce-gtx-980-kngpn-acx-2-0-graphics-card/#comments Tue, 03 Feb 2015 04:49:05 +0000 http://www.kitguru.net/?p=233595 EVGA on Monday introduced what could be the world’s most powerful graphics card based on Nvidia Corp.’s GeForce GTX 980 graphics processing unit. The new graphics board is designed to deliver extraordinary overclockability. It is expected that the new graphics adapter will set multiple performance records. The product is currently available for pre-order exclusively to …

The post EVGA unveils GeForce GTX 980 K|NGP|N ACX 2.0+ graphics card first appeared on KitGuru.]]>
EVGA on Monday introduced what could be the world’s most powerful graphics card based on Nvidia Corp.’s GeForce GTX 980 graphics processing unit. The new graphics board is designed to deliver extraordinary overclockability. It is expected that the new graphics adapter will set multiple performance records. The product is currently available for pre-order exclusively to EVGA customers.

The EVGA GeForce GTX 980 K|NGP|N graphics card is based on a custom 12-layer printed circuit board with 14+3 power phase design. Thanks to three power inputs (8pin + 8pin + 6pin) and very high-quality voltage regulation module, the card can use up to 450W of power and up to 600A current to deliver great overclockability. Default clock-rate of the GPU is 1291MHz, which is one of the highest in the industry. The graphics board can temporarily boost the frequency of the GPU to 1393MHz.

evga_geforce_gtx_980_kingpin_classified
Vince “K|NGP|N ” Lucido, a leading extreme overclocker, has managed to overclock the EVGA GTX 980 Kingpin Edition graphics card to 2.20GHz/8900MHz core/memory using liquid nitrogen, which is on par with the world's record.

evga_geforce_gtx_980_kingpin_classified_5

“The power designs for both the GPU and memory on the EVGA GeForce GTX 980 K|NGP|N graphics card should allow some insane overclocking and some of the highest clockspeeds seen to date,” said Mr. Lucido. “Also, with the new multi-color LED cooler, you can customize the look of the card to fit any system.”

evga_geforce_gtx_980_kingpin_classified_4

At present only existing owners of registered EVGA products can pre-order the unique graphics cards. Each of such adapters will be priced at $749, which is a lot for such graphics solutions. Pre-orders are scheduled to begin shipping the week of February 19th, 2015.

evga_geforce_gtx_980_kingpin_classified_3

Discuss on our Facebook page, HERE.

KitGuru Says: If you want to have the best single-chip graphics card money can buy right now, then EVGA’s GeForce GTX 980 K|NGP|N graphics adapter is among the things you should consider. Alternatively, you should wait for the new-generation GeForce GTX Titan graphics card based on the GM200 GPU.

The post EVGA unveils GeForce GTX 980 K|NGP|N ACX 2.0+ graphics card first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/evga-unveils-geforce-gtx-980-kngpn-acx-2-0-graphics-card/feed/ 4
EVGA readies new GeForce GTX 980 for extreme overclockers https://www.kitguru.net/components/graphic-cards/anton-shilov/evga-readies-new-geforce-gtx-980-for-extreme-overclockers/ https://www.kitguru.net/components/graphic-cards/anton-shilov/evga-readies-new-geforce-gtx-980-for-extreme-overclockers/#comments Sat, 03 Jan 2015 02:17:36 +0000 http://www.kitguru.net/?p=228654 Vince “K|NGP|N” Lucido, a top professional overclocker that works with EVGA, has announced on his Facebook page that EVGA is working on a new GeForce GTX 980 for extreme overclockers. The novelty is expected to beat the current flagship product from the company, the EVGA GeForce GTX 980 Classified ACX 2.0 4GB. “New year for …

The post EVGA readies new GeForce GTX 980 for extreme overclockers first appeared on KitGuru.]]>
Vince “K|NGP|N” Lucido, a top professional overclocker that works with EVGA, has announced on his Facebook page that EVGA is working on a new GeForce GTX 980 for extreme overclockers. The novelty is expected to beat the current flagship product from the company, the EVGA GeForce GTX 980 Classified ACX 2.0 4GB.

“New year for extreme overclocking graphics #comingsoon,” said the renowned overclocker.

The EVGA GeForce GTX 980 Classified ACX 2.0 features a large custom PCB with enhanced PLL circuitry, improved GPU power plane as well as ability to control voltages using Evbot accessory sold by the company. To ensure maximum overclocking potential, the graphics card is equipped with two 8-pin PCI Express auxiliary power connectors as well as the company’s own ACX 2.0 cooling system.

evga_geforce_gtx_980_classified_kingpin

The EVGA GeForce GTX 980 Classified K|NGP|N Edition is expected to feature a preinstalled dedicated PWM baseplate, voltage regulation enhancements and more. It is also likely that the card will have two 8-pin and one 6-pin PCIe power connectors that can supply (together with the PCIe x16 slot) up to 450W of power to the board.

The EVGA GeForce GTX 980 Classified is already among the highest-performing graphics card in the world thanks to 1291MHz/7GHz GPU/memory clock-rates. The card is also among the most expensive GeForce GTX 980-based solutions on the market. It costs $699. The K|NGP|N Edition graphics card will offer higher frequencies, but will also be more expensive.

Discuss on our Facebook page, HERE.

KitGuru Says: It will be extremely interesting to know how high will EVGA go with the new K|NGP|N Edition graphics card. Theoretically, a highly-overclocked GeForce GTX 980 will be able to rival Nvidia’s upcoming graphics cards based on the GM200 graphics processing unit.

The post EVGA readies new GeForce GTX 980 for extreme overclockers first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/evga-readies-new-geforce-gtx-980-for-extreme-overclockers/feed/ 2
Gigabyte sells GTX 980 WaterForce 3-way SLI kit for £2499/$2999 https://www.kitguru.net/components/graphic-cards/anton-shilov/gigabyte-starts-to-sell-geforce-gtx-980-waterforce-3-way-sli-kit-for-24992999/ https://www.kitguru.net/components/graphic-cards/anton-shilov/gigabyte-starts-to-sell-geforce-gtx-980-waterforce-3-way-sli-kit-for-24992999/#comments Thu, 11 Dec 2014 06:03:29 +0000 http://www.kitguru.net/?p=225815 Gigabyte Technology has started to sell what could be the highest-performing retail graphics processing solution ever developed. The Gigabyte GeForce GTX 980 WaterForce 3-way SLI includes three massively factory-overclocked graphics cards that are designed to work in multi-GPU mode as well as a special liquid cooling solution. But extreme performance comes at extreme price. Designed …

The post Gigabyte sells GTX 980 WaterForce 3-way SLI kit for £2499/$2999 first appeared on KitGuru.]]>
Gigabyte Technology has started to sell what could be the highest-performing retail graphics processing solution ever developed. The Gigabyte GeForce GTX 980 WaterForce 3-way SLI includes three massively factory-overclocked graphics cards that are designed to work in multi-GPU mode as well as a special liquid cooling solution. But extreme performance comes at extreme price.

Designed to deliver ultimate framerates in the latest games in ultra-high-definition resolutions, the Gigabyte GeForce GTX 980 WaterForce 3-way SLI (GV-N980X3WA-4GD) graphics board kit features default GPU clock-rates of 1228MHz/1329MHz (base/boost). Each graphics card sports 4GB of GDDR5 memory at 7GHz, three DisplayPort, one HDMI and two DVI outputs.

gigabyte_3way_sli_watercooling_1

Gigabyte’s three-card graphics product is a unique offering that is designed to provide unbeatable performance at price-points already tested by Nvidia Corp. itself with its GeForce GTX Titan Z. While potentially this three-way multi-GPU graphics kit should offer higher performance than the dual-GPU graphics card, it should be noted that far not all video games scale performance with three GPUs. As a consequence, Gigabyte’s solution will not be the absolutely best graphics sub-system possible in all cases. Still, unlike the GTX Titan Z, the GTX 980 WaterForce 3-way SLI kit features high clock-rates and will offer decent levels of performance even in case only one GPU is active, hence, in general the triple-GPU configuration should deliver high performance in almost all games.

Thanks to closed-loop liquid cooling solution, the kit only produces 30.4db of noise while fully-loaded. The 3-way SLI GeForce GTX 980 graphics processing kit runs 42.6 per cent cooler compared to reference design graphics cards while delivering up to 20 per cent higher performance.

gigabyte_3way_sli_watercooling

According to Gigabyte Technology, the WaterForce cooler is the best cooling solution for three-way SLI GeForce GTX 980 graphics sub-system, which can easily be true since there are no off-the-shelf closed-loop liquid cooling kits for three graphics cards. Each graphics board is pre-installed with its own exclusive waterblock and independent radiator connected with a pair of coolant pipes. All three 120mm radiators are placed inside the external metal watercooling box for maximum efficiency. The box sports three 120mm fans.

gigabyte_3way_sli_watercooling_2

The Gigabyte WaterForce liquid cooler features an intuitive control panel with an OLED display panel, where users can monitor and adjust all the settings about the graphics cards, including temperature, fan speed and pump speed. Moreover, the Gigabyte kit features target temperature mode that automatically adjusts fan and pump speeds to achieve user-defined temperatures.

On Wednesday Overclockers UK and Newegg began to sell/take pre-orders on the Gigabyte GeForce GTX 980 WaterForce 3-way SLI graphics cards kit at rather whopping price-points. In the U.K. the 3-way kit costs £2499.99 including VAT, whereas in the U.S. the 3-way graphics sub-system is priced at whopping $2999.99.

The GTX 980 WaterForce 3-way SLI kit (GV-N980X3WA-4GD) will eventually be available in Taiwan, Australia, China, France, Germany, Japan, Korea and Russia beginning this month.

Discuss on our Facebook page, HERE.

KitGuru Says: While the monstrous GTX 980 WaterForce 3-way SLI kit is designed to deliver ultimate gaming performance for hardcore gamers, it comes at a price that by far exceeds the cost of three GeForce GTX 980 graphics adapters. In fact, the three-way liquid cooling solution costs rather whopping $1350/£1300, an extreme price for a cooler.

The post Gigabyte sells GTX 980 WaterForce 3-way SLI kit for £2499/$2999 first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/gigabyte-starts-to-sell-geforce-gtx-980-waterforce-3-way-sli-kit-for-24992999/feed/ 7
Asustek unleashes Matrix GeForce GTX 980 with 14-phase VRM https://www.kitguru.net/components/graphic-cards/anton-shilov/asustek-unleashes-matrix-geforce-gtx-980-with-14-phase-vrm/ https://www.kitguru.net/components/graphic-cards/anton-shilov/asustek-unleashes-matrix-geforce-gtx-980-with-14-phase-vrm/#comments Thu, 04 Dec 2014 04:34:01 +0000 http://www.kitguru.net/?p=224776 The world’s record GPU frequency of 2.20GHz was set on Nvidia GeForce GTX graphics cards made by Asustek and EVGA. While it is hard to believe that the GM204 GPU can be pushed further towards 2.30GHz – 2.40GHz, the new Asus ROG Matrix Platinum GeForce GTX 980 graphics card is designed to do just that. Asustek …

The post Asustek unleashes Matrix GeForce GTX 980 with 14-phase VRM first appeared on KitGuru.]]>
The world’s record GPU frequency of 2.20GHz was set on Nvidia GeForce GTX graphics cards made by Asustek and EVGA. While it is hard to believe that the GM204 GPU can be pushed further towards 2.30GHz – 2.40GHz, the new Asus ROG Matrix Platinum GeForce GTX 980 graphics card is designed to do just that.

Asustek Computer on Wednesday unveiled its new graphics card that has all chances to become one of the best graphics cards for overclocking ever produced. The Matrix GTX 980 boasts not only a powerful DirectCU II cooling system (featuring two fans and five heat-pipes) and custom design of printed-circuit board, but it features extremely sophisticated 14-phase voltage regulator module (VRM) that can do magic things for overclocking as well as some other technologies for those, who want to push the graphics card to the extremes.

asus_rog_matrix_platinum_geforce_gtx_980_exploded

The digital 14-phase VRM is based on concrete-core chokes, solid-state black metallic capacitors and hardened MOSFETs. The board features two 8-pin PCIe auxiliary power connectors that can deliver up to 300W of power to the graphics board (in addition to 75W supplied through PCIe x16 slot) and one 4-pin Molex connector for memory defroster power loop. When cooled to sub-zero temperatures during extreme overclocking, the memory defroster keeps the memory chips just above freezing, preventing cold bugs from hindering overclocking.

asus_memory_defroster

The Asus ROG Matrix Platinum GeForce GTX 980 4GB will be the most powerful Nvidia GM204-based graphics card in Asustek’s lineup. The graphics processor of the monster graphics adapter is rated to run at up to 1342MHz out-of-the-box, a significant increase from 1216MHz recommended by Nvidia.

The ROG Matrix Platinum GTX 980 is the fourth GeForce GTX 980 graphics card in Asus’ family. The company carries a reference GeForce GTX 980, Strix GTX 980 with DirectCU II cooler and Poseidon GTX 980 featuring a hybrid cooling solution that use similar PCBs with 10-phase VRMs as well as the new ROG Matrix Platinum GTX 980 card that sports a brand-new printed-circuit board with 14-phase VRM as well as DirectCU II cooling system.

asus_rog_matrix_platinum_geforce_gtx_980_box_1

The current 2.20GHz GPU clock-rate records were set by professional overclockers using Asus Strix GTX 980 and EVGA GeForce GTX 980 Classified ACX 2.0 graphics cards that were cooled by liquid nitrogen cooling.

The Strix GTX 980 sports custom design of printed-circuit board with 10-phase digital VRM, the same one is used by Asus Poseidon GTX 980 graphics card, which has proven to be among the best in the industry. EVGA’s GTX 980 Classified sports custom PCB with 14-phase VRM, its voltages can be controlled using a special device. It will be very interesting to see whether Asustek’s engineers have managed to create a better voltage-regulating module than developers from EVGA and whether such VRM actually enables better overclocking. Will the record of 2.20GHz/9GHz (GPU/memory) stand or fall?

Discuss on our Facebook page, HERE.

KitGuru Says: While the Asus ROG Matrix Platinum GeForce GTX 980 could be the most potent GeForce GTX 980 graphics adapter, its price will likely be extremely high.

The post Asustek unleashes Matrix GeForce GTX 980 with 14-phase VRM first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/asustek-unleashes-matrix-geforce-gtx-980-with-14-phase-vrm/feed/ 1
K|NGP|N overclocks GeForce GTX 980 to record-high frequencies again https://www.kitguru.net/components/graphic-cards/anton-shilov/kngpn-overclocks-geforce-gtx-980-to-record-high-frequencies-again/ https://www.kitguru.net/components/graphic-cards/anton-shilov/kngpn-overclocks-geforce-gtx-980-to-record-high-frequencies-again/#respond Thu, 20 Nov 2014 23:59:48 +0000 http://www.kitguru.net/?p=222709 Vince “K|NGP|N” Lucido, a legendary overclocker who works with EVGA, has managed to overclock a GeForce GTX 980-based graphics card to record-high 2.20GHz/9GHz (GPU/memory) clock-rates and break a couple of world’s records in 3DMark FireStrike benchmark once again. In a bid to prove his world-class skills in overclocking, K|NGP|N pushed EVGA GeForce GTX 980 Classified …

The post K|NGP|N overclocks GeForce GTX 980 to record-high frequencies again first appeared on KitGuru.]]>
Vince “K|NGP|N” Lucido, a legendary overclocker who works with EVGA, has managed to overclock a GeForce GTX 980-based graphics card to record-high 2.20GHz/9GHz (GPU/memory) clock-rates and break a couple of world’s records in 3DMark FireStrike benchmark once again.

In a bid to prove his world-class skills in overclocking, K|NGP|N pushed EVGA GeForce GTX 980 Classified ACX 2.0 4GB graphics card all the way to 2201MHz for the GPU and whopping 9000MHz for the GDDR5 memory, making it the world’s highest-performing graphics card based on the GM204 processor. The graphics card was cooled down using liquid nitrogen (LN2).

evga_geforce_gtx_980_classified_3

Using a test-bed equipped with an Intel Core i7-5960X processor clocked at 5.775GHz, an EVGA X99 mainboard and 16GB of 3.30GHz DDR4 memory, Vince Lucido scored 20154 points in 3DMark FireStrike benchmark, the best result for a single-GPU configuration ever achieved.

The overclocker also scored 9648 points in 3DMark FireStrike Extreme, which is also the new world’s record. In a bid to pass the FireStrike Extreme test, Mr. Lucido had to drop GPU/memory clock-rates to 2171MHz/8.80GHz.

evga_geforce_gtx_22ghz_9ghz_image_id_1289864

The EVGA GeForce GTX 980 Classified ACX 2.0 4GB graphics card is among the highest-performing GM204-based graphics adapters available today. The adapter is based on a custom-designed printed circuit board with enhanced PLL circuitry, improved GPU power plane as well as ability to control voltages using Evbot accessory sold by EVGA to provide maximum overclocking potential. The GeForce GTX 980 Classified ACX 2.0 sports two 8-pin PCI Express auxiliary power connectors as well as the company’s own ACX 2.0 cooling system.

Thanks to major enhancements of PCB design, the EVGA GeForce GTX 980 Classified can not only enable great GPU overclocking results, but also has the ability to run memory at sky-high frequencies. No one has ever overclocked GDDR5 memory interface to 9GHz, but it looks like Vince “K|NGP|N” Lucido has managed to break this record as well.

Discuss on our Facebook page, HERE.

KitGuru Says: It looks like 2.20GHz is the limit for currently available GM204 graphics processing units since nobody has so far managed to overclock the GPU to a higher frequency. 2.20GHz is still unbelievable clock-rate for a GPU that contains 5.2 billion of transistors and 2048 stream processors. The graphics chip also seems to have an excellent memory controller (probably, the best in the industry at the moment) which can operate at whopping 9Gbps data-rate. It will be interesting to see whether it will be possible to overclock GDDR5 further on GM204-based graphics cards.

The post K|NGP|N overclocks GeForce GTX 980 to record-high frequencies again first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/kngpn-overclocks-geforce-gtx-980-to-record-high-frequencies-again/feed/ 0
K|NGP|N breaks 3DMark records with four GeForce GTX 980 at 2GHz https://www.kitguru.net/components/graphic-cards/anton-shilov/kngpn-and-evga-break-3dmark-records-with-four-geforce-gtx-980-at-2ghz/ https://www.kitguru.net/components/graphic-cards/anton-shilov/kngpn-and-evga-break-3dmark-records-with-four-geforce-gtx-980-at-2ghz/#comments Sat, 15 Nov 2014 02:29:28 +0000 http://www.kitguru.net/?p=222003 Vince “K|NGP|N” Lucido, one of the world’s most renowned overclockers who collaborates with EVGA these days, has set a number of world’s records when it comes to GPU frequency. He was the first to overclock a graphics processor to 2GHz and was among the first to hit 2.20GHz with Nvidia's latest GeForce GTX 980 GPU. …

The post K|NGP|N breaks 3DMark records with four GeForce GTX 980 at 2GHz first appeared on KitGuru.]]>
Vince “K|NGP|N” Lucido, one of the world’s most renowned overclockers who collaborates with EVGA these days, has set a number of world’s records when it comes to GPU frequency. He was the first to overclock a graphics processor to 2GHz and was among the first to hit 2.20GHz with Nvidia's latest GeForce GTX 980 GPU. This week K|NGP|N did not set any clock-speed records, he broke 3DMark FireStrike records instead using four GeForce GTX 980 graphics cards with 2 GHz GPUs.

Using four EVGA GeForce GTX 980 Classified ACX 2.0 4GB graphics cards overclocked to 2.0GHz/8400MHz (GPU/memory) and cooled-down using liquid nitrogen (LN2) as well as a test-bed equipped with an Intel Core i7-5960X processor clocked at 5.6GHz, an EVGA X99 mainboard and 16GB of 3.30GHz DDR4 memory, Vince “K|NGP|N” Lucido managed to set three absolute world records in 3DMark FireStrike benchmark:

  • 3DMark Fire Strike (4-way) = 40,338
  • 3DMark Fire Strike Extreme (4-way) = 28,059
  • 3DMark Fire Strike Ultra (4-way) = 16,243

evga_kingpin_geforce_gtx_980_frozen_quad_980

Thanks to massive overclocking potential of EVGA GeForce GTX 980 Classified ACX 2.0 4GB graphics card, K|NGP|N has also managed to see three records in single-GPU mode using a GeForce GTX 980 graphics card operating at 2.1GHz/8800MHz (GPU/memory):

  • 3DMark Fire Strike (single card) = 19,811
  • 3DMark Fire Strike Extreme (single card) = 9,617
  • 3DMark Fire Strike Ultra (single card) = 5,007

The EVGA GeForce GTX 980 Classified ACX 2.0 4GB graphics card is among the highest-performing GM204-based graphics adapters on the market. The board features 1291MHz/1405MHz (base/boost) GPU clock-rate, a significant increase from 1126MHz/1216MHz frequencies on reference-design GeForce GTX 980 graphics boards.

evga_kingpin_geforce_firestrike_-_4way  evga_kingpin_geforce_gtx_firestrike_-_single

To ensure maximum overclocking potential, the EVGA GeForce GTX 980 Classified ACX 2.0 uses a large custom PCB with enhanced PLL circuitry, improved GPU power plane as well as ability to control voltages using Evbot accessory sold by the company. The GeForce GTX 980 Classified ACX 2.0 sports two 8-pin PCI Express auxiliary power connectors as well as the company’s own ACX 2.0 cooling system.

“The EVGA GeForce GTX 980 Classified is an overclockers dream,” said Vince “K|NGP|N” Lucido. “The improved VRM and memory design really let Nvidia’s GTX 980 GPU stretch its wings. This card has achieved clock-speeds of 2200MHz core and 8500MHz memory single card and nearly 2100MHz core in 4-way SLI, it’s really amazing.”

Discuss on our Facebook page, HERE.

KitGuru Says: Overclocking a single graphics card to unprecedented frequencies using liquid nitrogen and playing with voltages is not an easy task. Overclocking four graphics cards using LN2 cooling and tweaking voltages to get maximum clock-rates is clearly a work of an overclocking master.

The post K|NGP|N breaks 3DMark records with four GeForce GTX 980 at 2GHz first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/kngpn-and-evga-break-3dmark-records-with-four-geforce-gtx-980-at-2ghz/feed/ 15
Asustek readies GeForce GTX 980 graphics card with hybrid cooling https://www.kitguru.net/components/graphic-cards/anton-shilov/asustek-readies-geforce-gtx-980-graphics-card-with-hybrid-cooling/ https://www.kitguru.net/components/graphic-cards/anton-shilov/asustek-readies-geforce-gtx-980-graphics-card-with-hybrid-cooling/#respond Thu, 13 Nov 2014 02:28:42 +0000 http://www.kitguru.net/?p=221650 Asustek Computer is working on what could eventually become one of the highest-performing GeForce GTX 980 graphics cards on the planet. The forthcoming Asus Poseidon GTX 980 will feature a hybrid cooling system and proprietary design of printed-circuit board to enable unprecedented overclocking potential. The Asus ROG Poseidon GTX 980 features a cooling system that …

The post Asustek readies GeForce GTX 980 graphics card with hybrid cooling first appeared on KitGuru.]]>
Asustek Computer is working on what could eventually become one of the highest-performing GeForce GTX 980 graphics cards on the planet. The forthcoming Asus Poseidon GTX 980 will feature a hybrid cooling system and proprietary design of printed-circuit board to enable unprecedented overclocking potential.

The Asus ROG Poseidon GTX 980 features a cooling system that features a custom copper waterblock (that is in direct contact with the GPU), which allows plugging tubes (using standard G¼-inch threaded fittings) from custom liquid-cooling systems, as well as a massive aluminium radiator with ultra-thin fins with heat-pipes. According to Asustek, with water-cooling, ROG Poseidon GTX 980 achieves up to 27°C-lower running temperatures than reference designs. With air-cooling, ROG Poseidon GTX 980 is also significantly cooler than graphics cards, which use Nvidia’s reference cooling systems.

asus_rog_poseidon_geforce_gtx_980

The unique graphics card from Asustek is based on custom printed-circuit board featuring 10-phase Digi+ voltage-regulation module (VRM) with solid-state black metallic capacitors, concrete-core chokes and hardened MOSFETs. Thanks to digital VRM, there is an ample room for experimental performance tuning – to levels unmatched by graphics cards based on Nvidia’s reference design. Thanks to that and advanced cooling solution, Asustek’s ROG Poseidon GTX 980 promises to be an excellent overclocker.

asus_rog_poseidon_geforce_gtx_980_2

The manufacturer does not reveal exact GPU clock-rate of the upcoming graphics card, but claims that its maximum (boost clock) frequency will be 1279MHz. 4GB of GDDR5 memory will be clocked at 7010MHz.

asus_rog_poseidon_geforce_gtx_980_1

Asustek’s ROG Poseidon GTX 980 graphics cards will be available this month worldwide. Pricing will vary.

Discuss on our Facebook page, HERE.

KitGuru Says: The new graphics card from Asustek Computer looks very interesting. It will be one of the first custom GeForce GTX 980 graphics boards on the market that is designed for extreme overclocking. How high will it go in terms of frequencies? Only time will tell!

The post Asustek readies GeForce GTX 980 graphics card with hybrid cooling first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/asustek-readies-geforce-gtx-980-graphics-card-with-hybrid-cooling/feed/ 0
Enthusiast overclocks GeForce GTX 980 to 2.20GHz, sets world’s record https://www.kitguru.net/components/graphic-cards/anton-shilov/enthusiast-overclocks-geforce-gtx-980-to-2-20ghz-sets-worlds-record/ https://www.kitguru.net/components/graphic-cards/anton-shilov/enthusiast-overclocks-geforce-gtx-980-to-2-20ghz-sets-worlds-record/#comments Thu, 02 Oct 2014 02:56:46 +0000 http://www.kitguru.net/?p=214724 Nvidia Corp.’s recently unveiled GM204 graphics processing unit and GeForce GTX 980 graphics card have proven to be excellent performers and also great overclockers. This week an enthusiast from Sweden managed to boost clock-rate of the GeForce GTX 980 graphics processing unit to whopping 2.20GHz, a new world’s record. Elmor, an overclocker from SweClockers.com team, …

The post Enthusiast overclocks GeForce GTX 980 to 2.20GHz, sets world’s record first appeared on KitGuru.]]>
Nvidia Corp.’s recently unveiled GM204 graphics processing unit and GeForce GTX 980 graphics card have proven to be excellent performers and also great overclockers. This week an enthusiast from Sweden managed to boost clock-rate of the GeForce GTX 980 graphics processing unit to whopping 2.20GHz, a new world’s record.

Elmor, an overclocker from SweClockers.com team, has managed to increase GPU clock-rate of Asus GeForce GTX 980 Direct CU II graphics card by 81.58 per cent from default, to 2208MHz. He also managed to increase effective GDDR5 memory frequency to 8392MHz, a 19.27 per cent boost. To achieve his remarkable overclocking result, Elmor used liquid nitrogen cooling. The core voltage of the GM204 GPU was 1.2120V.

Using a system based on Intel Core i7-5960X clocked at 5586MHz (also cooled by LN2), Elmor managed to score 9568 in 3DMark FireStrike Extreme, another world’s record, reports Hwbot.

nvidia_geforce_gtx_980_overclock_elmor_image_id_1258340

Earlier this year Nvidia Corp.’s GK110 graphics processing unit has managed to conquer 2.0GHz frequency, setting the world’s record. The GM204 graphics chip is smaller than the GK110 and contains fewer transistors, therefore, it is not surprising that it can work at even higher frequencies. Moreover, thanks to increased efficiency of Nvidia’s Maxwell architecture, the GM204 can actually be faster than the GK110 in benchmarks when overclocked.

nvidia_geforce_gtx_980_overclock_elmor_image_id_1258339

Discuss on our Facebook page, HERE.

KitGuru Says: Nvidia GeForce GTX 980 graphics cards have existed on the market for less than a month. Professional overclockers only start to push them to the max. Eventually, it is highly likely that the GM204 GPU will set a number of other records.

The post Enthusiast overclocks GeForce GTX 980 to 2.20GHz, sets world’s record first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/enthusiast-overclocks-geforce-gtx-980-to-2-20ghz-sets-worlds-record/feed/ 4
EVGA unleashes the world’s highest-performing GeForce GTX 980 https://www.kitguru.net/components/graphic-cards/anton-shilov/evga-unleashes-the-worlds-highest-performing-geforce-gtx-980/ https://www.kitguru.net/components/graphic-cards/anton-shilov/evga-unleashes-the-worlds-highest-performing-geforce-gtx-980/#comments Wed, 01 Oct 2014 13:28:42 +0000 http://www.kitguru.net/?p=214628 EVGA this week quietly introduced what could be the world’s highest-performing graphics card based on Nvidia Corp.’s GeForce GTX 980 graphics processing unit. The EVGA GeForce GTX 980 Classified ACX 2.0 graphics board utilizes custom printed-circuit board (PCB) that is designed with overclocking in mind. The EVGA GeForce GTX 980 Classified ACX 2.0 4GB graphics …

The post EVGA unleashes the world’s highest-performing GeForce GTX 980 first appeared on KitGuru.]]>
EVGA this week quietly introduced what could be the world’s highest-performing graphics card based on Nvidia Corp.’s GeForce GTX 980 graphics processing unit. The EVGA GeForce GTX 980 Classified ACX 2.0 graphics board utilizes custom printed-circuit board (PCB) that is designed with overclocking in mind.

The EVGA GeForce GTX 980 Classified ACX 2.0 4GB graphics card features 1291MHz/1405MHz (base/boost) GPU clock-rates, a significant increase from 1126MHz/1216MHz frequencies on reference-design GeForce GTX 980 graphics boards. To ensure further overclocking potential, the EVGA GeForce GTX 980 Classified ACX 2.0 sports two 8-pin PCI Express auxiliary power connectors (Nvidia-designed GeForce GTX 980 boards feature two 6-pin PCIe power connectors) as well as the company’s own ACX 2.0 cooling system.

evga_geforce_gtx_980_classified_1

Like previous-generation Classified-series graphics cards, the EVGA GeForce GTX 980 Classified ACX 2.0 uses a large custom PCB with enhanced PLL circuitry, improved GPU power plane as well as ability to control voltages using Evbot accessory sold by the company. All of the enhancements are designed to provide further overclocking potential for those, who need maximum performance.

It is possible that eventually EVGA releases EVGA GeForce GTX 980 Classified K|NGP|N Edition that will likely feature three aux PCIe power connectors (2*8-pin connectors and a 6-pin connector), preinstalled dedicated PWM baseplate as well as even higher clock-rates and overclocking potential.

evga_geforce_gtx_980_classified_2

Earlier this week KitGuru published a review of the Asus GTX 980 Strix OC graphics card. During the testing, the adapter was overclocked to whopping 1380MHz/1481MHz base/boost using air cooling. At such high frequencies the graphics solution almost hit 21,000 points in the graphics test of 3DMark 11 – KitGuru’s highest yet for a single GPU.

Given the enhanced design of the EVGA GeForce GTX 980 Classified ACX 2.0, it is highly likely that it will not only beat Asustek’s solution in terms of overclocking potential, but will even beat Nvidia’s GeForce GTX Titan Black in terms of performance in games.

evga_geforce_gtx_980_classified_3

Pricing of the EVGA GeForce GTX 980 Classified ACX 2.0 has not been announced yet, but do not expect it to be low.

Discuss on our Facebook page, HERE.

KitGuru Says: It is noteworthy that Nvidia’s partners decided to offer heavily-overclocked versions of its GeForce GTX 980 early in the life cycle and not to wait for 8GB versions of the boards to arrive. If you use a 4K display, it makes sense to wait for factory-overclocked Nvidia GeForce GTX 980 graphics cards with 8GB of memory. It is unclear whether such boards could further boost memory frequency, but the amount of memory itself should help to play comfortably in high resolutions.

The post EVGA unleashes the world’s highest-performing GeForce GTX 980 first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/evga-unleashes-the-worlds-highest-performing-geforce-gtx-980/feed/ 4
Recommended prices of GeForce GTX 970, 980 published https://www.kitguru.net/components/graphic-cards/anton-shilov/recommended-prices-of-geforce-gtx-970-980-published/ https://www.kitguru.net/components/graphic-cards/anton-shilov/recommended-prices-of-geforce-gtx-970-980-published/#comments Tue, 16 Sep 2014 22:59:42 +0000 http://www.kitguru.net/?p=211944 A media report has revealed recommended prices of Nvidia Corp’s forthcoming GeForce GTX 970 and GeForce GTX 980 graphics cards. As expected, the large size of the code-named GM204 graphics processing unit that powers both products does not allow to make them affordable. The GeForce GTX 980 graphics board with 4GB of GDDR5 memory will …

The post Recommended prices of GeForce GTX 970, 980 published first appeared on KitGuru.]]>
A media report has revealed recommended prices of Nvidia Corp’s forthcoming GeForce GTX 970 and GeForce GTX 980 graphics cards. As expected, the large size of the code-named GM204 graphics processing unit that powers both products does not allow to make them affordable.

The GeForce GTX 980 graphics board with 4GB of GDDR5 memory will carry recommended price tag of $599, which positions it between the GeForce GTX 780 and the GeForce GTX 780 Ti, reports 3DCenter.org. It is expected that performance of the novelty will be higher compared to the former and lower compared to the latter, given its configuration. It is expected that the GTX 980 features 2048 stream processors (SPs), 128 texture units (TUs), 64 raster operations pipelines (ROPs), 2MB L2 cache, and 256-bit memory interface.

The GeForce GTX 970 is expected to cost $399 in the U.S., which may mean that its performance will be similar to that of the GeForce GTX 770. Actual configuration of the GeForce GTX 970 GPU is unknown, but it is expected that graphics cards on its base will carry 4GB of GDDR5 memory.

nvidia_artwork

Recommended prices of the forthcoming graphics boards for Europe and the U.K. are unknown.

Nvidia did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: Keeping in mind that the price gap between the GeForce GTX 970 and 980 is around $200, expect a huge gap in performance as well.

The post Recommended prices of GeForce GTX 970, 980 published first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/recommended-prices-of-geforce-gtx-970-980-published/feed/ 26
Web-site publishes ‘final’ specifications of GeForce GTX 980 https://www.kitguru.net/components/graphic-cards/anton-shilov/web-site-publishes-final-specifications-of-geforce-gtx-980/ https://www.kitguru.net/components/graphic-cards/anton-shilov/web-site-publishes-final-specifications-of-geforce-gtx-980/#comments Tue, 16 Sep 2014 22:59:40 +0000 http://www.kitguru.net/?p=211940 Nvidia Corp.’s new high-end graphics cards – GeForce GTX 980 – are expected to be introduced in several days from now, but a media report has already revealed what is claimed to be the final specifications of the new graphics boards. The specifications of the new Maxwell architecture-based flagship graphics solution are pretty surprising. As …

The post Web-site publishes ‘final’ specifications of GeForce GTX 980 first appeared on KitGuru.]]>
Nvidia Corp.’s new high-end graphics cards – GeForce GTX 980 – are expected to be introduced in several days from now, but a media report has already revealed what is claimed to be the final specifications of the new graphics boards. The specifications of the new Maxwell architecture-based flagship graphics solution are pretty surprising.

As it appears, Nvidia’s code-named GM204 graphics processing unit is considerably more powerful than initially thought. The GM204 integrates 5.2 billion transistors and features 398 square millimetre die size, which means that it will hardly be able to address mainstream market segments any time soon due to significant manufacturing costs.

Nvidia GM204 GPU in its maximum configuration packs as many 2048 stream processors (SPs), 128 texture units (TUs), 64 raster operations pipelines (ROPs), 2MB L2 cache, and 256-bit memory interface, according to a report from VideoCardz. The chip is organized in four graphics processing clusters (GPCs), each of which featuring four streaming multiprocessor modules (SMMs). Each Maxwell SMM sports its own PolyMorph Engine 2.0 unit (one vertex fetch, one tessellator, one viewport transform, one stream output, etc.) and is divided into four blocks with their own control logic (instruction buffer, warp scheduler, dispatch unit), a register file, two TUs and 32 SPs.

nvidia_geforce_gtx_980_gfx_card

GeForce GTX 980 graphics cards made in accordance with Nvidia’s recommendations will feature 1126MHz/1216MHz base/boost clock-rate for GPU as well as 7GHz effective frequency for GDDR5 memory. The maximum single-precision floating point performance of the GTX 980 is projected to be around 4.6TFLOPS, which is significantly higher compared to that of the GK104-based GeForce GTX 770 (3.2TFLOPS), but is still lower compared to that of the GK110-powered GeForce GTX 780 Ti (5.1TFLOPS).

Thanks to 64 ROPs, the GeForce GTX 980 graphics card should perform very well in high resolutions. However, since its memory bandwidth will be limited to around 224GB/s it will hardly outperform the GeForce GTX 780 Ti or the GeForce GTX Titan Black in ultra-high-definition cases. Still, new colour compression technologies and other methods of reducing requirements for memory bandwidth could help to bring performance of the GM204-based solutions closer to that of GK110-powered graphics boards.

Nvidia did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: Nvidia’s decision to boost the size of the GM204 GPU to nearly 400 square millimeters is very surprising. The manufacturing cost of such chip may be too high to use it for mainstream graphics products that cost around $200, meanwhile, at present the company still does not have a Maxwell-based mainstream GPU. The die size of the GM204 graphics chip may give a glimpse at what to expect from Nvidia when it comes to its new top-of-the-range GPU. It is highly likely that the code-named GM200 processor’s die size will be between 550 sq.mm and 600 sq. mm., which means that it will be the world’s largest GPU ever made.

The post Web-site publishes ‘final’ specifications of GeForce GTX 980 first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/web-site-publishes-final-specifications-of-geforce-gtx-980/feed/ 48
GeForce GTX 970 graphics cards from Galaxy and Zotac pictured https://www.kitguru.net/components/graphic-cards/anton-shilov/geforce-gtx-970-graphics-cards-from-galaxy-and-zotac-pictured/ https://www.kitguru.net/components/graphic-cards/anton-shilov/geforce-gtx-970-graphics-cards-from-galaxy-and-zotac-pictured/#comments Fri, 12 Sep 2014 05:19:37 +0000 http://www.kitguru.net/?p=211422 Two web-sites have published images of graphics cards they claim to be based on Nvidia Corp’s upcoming GeForce GTX 970 graphics processor. The graphics boards feature custom designs and cooling systems. The Galaxy GeForce GTX 970 4GB graphics adapter, which photo was published by VideoCardz on Thursday, is clearly designed for enthusiasts and overclockers. The …

The post GeForce GTX 970 graphics cards from Galaxy and Zotac pictured first appeared on KitGuru.]]>
Two web-sites have published images of graphics cards they claim to be based on Nvidia Corp’s upcoming GeForce GTX 970 graphics processor. The graphics boards feature custom designs and cooling systems.

The Galaxy GeForce GTX 970 4GB graphics adapter, which photo was published by VideoCardz on Thursday, is clearly designed for enthusiasts and overclockers. The graphics card features a long printed-circuit board (PCB) with two auxiliary PCI Express power connectors (6-pin + 8-pin) as well as an advanced cooling system sporting two fans and multiple heat-pipes.

galaxy_geforce_gtx_970 galaxy_geforce_gtx_970_1

It is possible that Galaxy used PCB from the GeForce GTX 980 graphics card for its enthusiast-oriented GeForce GTX 970. Since the graphics card itself has no markings except the word “Galax”, its authenticity and even the name could not be verified.

galaxy_geforce_gtx_970_2

Another image – which allegedly depicts Zotac’s GeForce GTX 970 graphics board along with its package – has been leaked by someone from Overclock.net forums.

zotac_geforce_gtx_970

If the image is genuine, then Zotac decided to address small form-factor (SFF) systems with its GeForce GTX 970. The graphics adapter does feature a sophisticated cooler with two fans and heat-pipes, but the card itself is rather short and will thus fit into small PCs. Keeping in mind that SFF systems usually do not come with power supply units featuring 8-pin power connectors, it is more than likely that Zotac’s GeForce GTX 970 requires two 6-pin auxiliary PCIe power connectors.

Nvidia's upcoming GeForce GTX 970 and GeForce GTX 980 graphics cards are based on the code-named GM204 graphics processing unit. The chip is powered by the second-generation Maxwell architecture. The novelties are expected to be formally introduced later this month.

Nvidia, Galaxy and Zotac did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: Traditionally Nvidia used similar PCBs for its GeForce GTX *80 and *70 graphics cards since their configurations were rather similar. For some reason, this time Nvidia allows its partners to design PCBs for the GTX 970 themselves. Theoretically, this could mean that there will be very different GeForce GTX 970 graphics boards on the market, some of them will be extremely good overclockers, whereas the other will be very affordable.

The post GeForce GTX 970 graphics cards from Galaxy and Zotac pictured first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/geforce-gtx-970-graphics-cards-from-galaxy-and-zotac-pictured/feed/ 6
Nvidia’s GeForce GTX 980 will not beat GeForce GTX 780 Ti – insider https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidias-geforce-gtx-980-will-not-beat-geforce-gtx-780-ti-insider/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidias-geforce-gtx-980-will-not-beat-geforce-gtx-780-ti-insider/#comments Fri, 05 Sep 2014 22:59:08 +0000 http://www.kitguru.net/?p=210509 Nvidia Corp. is set to unveil its new-generation high-performance graphics solutions based on the code-named GM204 graphics processing units in about two weeks from now, but so far there have been no leaks indicating performance of the GeForce GTX 970 and the GeForce GTX 980 graphics cards. Luckily, a staff member of Overclockers.co.uk decided to …

The post Nvidia’s GeForce GTX 980 will not beat GeForce GTX 780 Ti – insider first appeared on KitGuru.]]>
Nvidia Corp. is set to unveil its new-generation high-performance graphics solutions based on the code-named GM204 graphics processing units in about two weeks from now, but so far there have been no leaks indicating performance of the GeForce GTX 970 and the GeForce GTX 980 graphics cards. Luckily, a staff member of Overclockers.co.uk decided to shed some light on what to expect from the novelties.

Initially Nvidia’s partners will bring GeForce GTX 970/980 graphics cards with 4GB of GDDR5 onboard, but eventually they will also release versions with 8GB of memory and custom coolers, according to Andrew “Gibbo” Gibson, a purchasing manager at Overclockers UK, who shared his educated guesses at OcUK forums. Presumably, there will be factory-overclockers versions of GeForce GTX 970/980 graphics cards as well.

The amount of rumours spread about performance of graphics cards based on the GM204 graphics chip (which were first known as the GeForce GTX 880/870/860 and later it turned out that Nvidia will call them GeForce GTX 980/970/960) was rather incredible this spring, but none of the rumours was close to reality. As expected, the GM204 is set to replace the GK104 graphics processing unit (which powers GeForce GTX 780/770/760/680/670 solutions), which is why it was naïve to expect it to outperform graphics boards based on the fully-loaded GK110 (GeForce GTX Titan Black, GeForce GTX 780 Ti).

“Speculation is [the GeForce GTX 980] replace[s] 780, not 780Ti,” said Mr. Gibson. “Performance wise, my lips are sealed on how it compares to 780Ti, but of course 980 is quicker than 780 for sure!”

The GeForce GTX 780 graphics card is based on a cut-down GK110 GPU that features 2304 stream processors (SPs), 192 texture units (TUs), 48 raster output units (ROPs) and 256-bit wide GDDR5 memory bus. The GeForce GTX 780 Ti powered by the fully-fledged GK110 graphics processor is a much more powerful graphics solution with 2880 SPs, 240 TUs, 48 ROPs and 384-bit GDDR5 memory bus.

nvidia_geforce_gtx680_kepler

Based on KitGuru’s analysis of what to expect from graphics solutions based on the GM204, the GeForce GTX 980 graphics card could be 30 per cent or even faster compared to the currently available high-end GeForce GTX solutions. However, this expectation might be too optimistic.

“Do not expect a huge leap in performance over current single GPU stuff,” said Mr. Gibson.

Nvidia did not comment on the news-story.

Comments of Andrew Gibson reflect his personal expectations and are not official statements from Overclockers UK.

Discuss on our Facebook page, HERE.

KitGuru Says: While graphics cards based on the GM204 may not represent a performance breakthrough, they will still be faster compared to today’s solutions not based on ultra-premium GK110 GPU with all the units activated.

The post Nvidia’s GeForce GTX 980 will not beat GeForce GTX 780 Ti – insider first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidias-geforce-gtx-980-will-not-beat-geforce-gtx-780-ti-insider/feed/ 31
Nvidia to skip GeForce GTX 800 series, to introduce GeForce GTX 970, GTX 980 in mid-September https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-to-skip-geforce-gtx-800-series-to-introduce-geforce-gtx-970-gtx-980-in-mid-september/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-to-skip-geforce-gtx-800-series-to-introduce-geforce-gtx-970-gtx-980-in-mid-september/#comments Fri, 29 Aug 2014 03:23:26 +0000 http://www.kitguru.net/?p=209448 Although it was expected that Nvidia Corp. would release its new GeForce GTX 800-series graphics cards for desktops this September and October, the company has decided to skip the GeForce 800 family for desktop PCs and jump straight to the GeForce 900 line of products. Model numbers of modern central processing units and graphics processing units have …

The post Nvidia to skip GeForce GTX 800 series, to introduce GeForce GTX 970, GTX 980 in mid-September first appeared on KitGuru.]]>
Although it was expected that Nvidia Corp. would release its new GeForce GTX 800-series graphics cards for desktops this September and October, the company has decided to skip the GeForce 800 family for desktop PCs and jump straight to the GeForce 900 line of products.

Model numbers of modern central processing units and graphics processing units have been criticized criticized for years since in many cases they barely reflect performance and positioning of products and in many cases cannot even determine their generation. At present Nvidia offers high-end GeForce GTX 700-series of products for desktop computers. At the same time, the company sells GeForce GTX 800M family of products for notebooks. What is rather confusing is that both lineups – the GTX 700 and the GTX 800M – are based on similar chips powered by the Kepler architecture.

In a bid to avoid confusion with its upcoming families of graphics processing units for desktop and mobile computers, Nvidia decided to sell its products powered by the second-generation Maxwell GPUs code-named GM200, GM204 and other under the GeForce 900 moniker, reports VideoCardz.

nvidia_artwork

As a result, Nvidia is now expected to formally introduce the GeForce GTX 970 and the GeForce GTX 980 graphics cards on the 19th of September, 2014. The GeForce GTX 960 is projected to arrive sometime in October.

Nvidia did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: While the idea to sell similar generation of chips under similar model numbers makes a lot of sense, it should be kept in mind that in order to complete the GeForce 900 and the GeForce 900M product lines, Nvidia will likely add old chips into new families and therefore will confuse end-users again.

The post Nvidia to skip GeForce GTX 800 series, to introduce GeForce GTX 970, GTX 980 in mid-September first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-to-skip-geforce-gtx-800-series-to-introduce-geforce-gtx-970-gtx-980-in-mid-september/feed/ 87
Nvidia GeForce GTX 800: what to expect from its specs? https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-geforce-gtx-800-what-to-expect-from-its-performance-and-specs/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-geforce-gtx-800-what-to-expect-from-its-performance-and-specs/#comments Fri, 08 Aug 2014 22:59:18 +0000 http://www.kitguru.net/?p=206623 Nvidia Corp. and its partners among makers of graphics cards are expected to release the next-generation GeForce GTX 800-series solutions sometimes in October (or even late September), according to multiple reports. But while the new graphics solutions are just a couple of months away, it is completely unknown what to expect from them. We decided …

The post Nvidia GeForce GTX 800: what to expect from its specs? first appeared on KitGuru.]]>
Nvidia Corp. and its partners among makers of graphics cards are expected to release the next-generation GeForce GTX 800-series solutions sometimes in October (or even late September), according to multiple reports. But while the new graphics solutions are just a couple of months away, it is completely unknown what to expect from them. We decided to analyze what we do know for sure about the GM204, the graphics processor that will power the new cards, and what kind of specifications and performance should we expect.

nvidia_artwork_iron

Facts we know for (almost) sure

While there are not a lot of reliable facts from sources close to Nvidia available at the moment, here is what we have found so far about the GM204 and what either is trustworthy or, at least, looks trustworthy:

  • Nvidia GM204 is based on the code-named Maxwell architecture;
  • Nvidia GM204 is made using 28nm process technology (given that multiple sources said that the GM204 is a 28nm GPU, it is most probably a fact);
  • Nvidia GM204 has die size of around 300mm² (we’ve seen the chip, we’ve discussed that performance GPUs from Nvidia feature about 300mm² die size);
  • Nvidia GM204 most likely 256-bit memory bus (we’ve seen a GM204-based card, it features 16 GDDR5 memory chips (with 16-bit or 32-bit interfaces), hence, given the size of the chip, 256-bit memory bus is a more likely option);

While we have no idea about exact specifications of the GM204, we do know specifications of the GM107 thanks to the official launch of the GeForce GTX 750-series GPUs earlier this year and hence we know something about the Maxwell architecture in general.

Maxwell architecture

Nvidia’s graphics processors consist of several key building blocks: main scheduler/dispatch processor (which Nvidia calls GigaThread Engine), GPCs [graphics processing clusters], SMMs [streaming multiprocessor module], ROPs [raster operating units], cache, memory controllers.

GeForce_GTX_750_Ti_Block_Diagram_FINAL

A block diagram of Nvidia's GM107 graphics processing unit.

The GM107 graphics processor based on the first-gen Maxwell architecture features one GPC unit, 16 ROPs (in two blocks,), 2MB L2 cache and two 64-bit memory controllers. The GPC of the GM107 consists of five SMMs. Each first-gen Maxwell SMM features its own PolyMorph Engine 2.0 unit (one vertex fetch, one tessellator, one viewport transform, one stream output, etc.) and is divided into four blocks with their own control logic (instruction buffer, warp scheduler, dispatch unit), a register file, two texture units (TUs) and 32 stream processors (SPs) (thus, each SMM features 128 SPs, 8 TUs, etc.).

nvidia_maxwell_smm

A block diagram of a Maxwell SMM

According to Nvidia, thanks to better programmability of each block within an SMM and higher utilization rate of each stream processors, the company increased the peak performance per stream processor by 35% when compared to the SPs in its chips built with the previous generation Kepler architecture. Therefore a Maxwell-based GPU with equal (or more or less equal) amount of stream processors with a Kepler-based GPU will perform around 35 per cent better.

Nvidia’s GM107 graphics processing unit features 640 SPs, 40 TUs, 16 ROPs, 2MB cache and a 128-bit memory controller. The chip contains 1.87 billion of transistors and has 148mm² die size.

What Nvidia needs from GM204?

Since the GM204 is a successor to the GK104 graphics processor (GeForce GTX 670, 680, 760 and 770) made using the same 28nm process technology, Nvidia cannot really expect it to outperform its predecessor by two times or something like that. Realistically, Nvidia needs to tangibly outperform the best GK104 by around 30 to 40 per cent. It is impossible that a 300mm² Maxwell chip could beat the GK110 GPU with 2880 stream processors (which die size is 551mm²), hence, it is not a target that the GM204 should achieve.

Possible GM204 configurations

Each architecture can be scaled to offer better performance or lower power consumption. Let’s try to assume how Nvidia could scale the GM107’s architecture to offer better performance with the GM204 while maintaining around 300mm² die size.

The easiest way to double performance of the GM107 is to double the amount of virtually everything inside: GPC, ROPs, cache, memory controllers. Such a chip would have 1280 stream processors, 80 texture units, 32 ROPs and a 256-bit memory bus. The GPU would never outperform the GK104 (1536 SPs, 128 TUs, 32 ROPs, etc.) significantly and in many cases will be behind the older solution. Therefore, it is unlikely that Nvidia will take this route. Moreover, such a chip would be significantly smaller than 300mm² since not all elements of the chip have to be doubled.

What Nvidia did with GK110 compared to the GK104 architecturally (at least when it comes to organization of execution units) was the increase of the amount of SMs [streaming multiprocessor] per GPC from two to three. The same approach could be used for the GM204 too. Nvidia could expand GPC to six SMMs and then double the amount of GPCs (and ROPs, cache, memory controllers) per chip. Such a GPU would feature 1536 SPs, 96 TUs, 32 ROPs as well as a 256-bit memory bus and could offer up to 35 per cent higher performance compared to the GK104 at the same clock-rate. The die size of such chip would probably be around 300mm², but since we do not know anything about exact sizes of the GM107’s elements, we cannot be 100 per cent sure.

Theoretically, Nvidia could put six blocks into each SMM (thus increasing the amount of SPs per SMM to 192), then double the amount of GPCs (along with ROPs, cache, memory controllers) per GPU. If Nvidia manages to do this, then the final chip would feature 1920 SPs, 120 TUs, 32 ROPs and a 256-bit memory controller. Would that all fit into a 300mm² die area? Possibly. However, since this fundamentally changes the architecture of the SMM, this could also affect efficiency of Maxwell architecture in general. Therefore, the expansion of GPC to seven SMMs (and doubling the amount of GPCs, etc.) sounds more realistic (the GPU would have 1792 SPs, 112 TUs, 32 ROPs, 256-bit memory bus).

Final words

While chip designers can do many unexpected things and sometimes even wonders, they cannot overrule the laws of physics. Engineers will not be able to squeeze 3200 stream processors into the GM204 that is made using 28nm process technology and has die size of around 300mm². Therefore, the most logical configurations of the fully-fledged GM204 (the GeForce GTX 880) are as follows:

  • 1536 SPs, 96 TUs, 32 ROPs, 256-bit memory bus
  • 1792 SPs, 112 TUs, 32 ROPs, 256-bit memory bus
  • 1920 SPs, 120 TUs, 32 ROPs, 256-bit memory bus

Of course, these specifications may be wrong as well…

Nvidia did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: Keep in mind that this news-story is highly speculative. We do not know exact sizes of Maxwell’s SMM, GPC and the un-core, therefore, take everything with a grain of salt. Nvidia has never revealed a die shot of the GM107 probably for a reason. Otherwise, it would be relatively easy to model the GM204.

The post Nvidia GeForce GTX 800: what to expect from its specs? first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-geforce-gtx-800-what-to-expect-from-its-performance-and-specs/feed/ 11
Gigabyte confirms Nvidia GeForce GTX 880 launch this fall https://www.kitguru.net/components/graphic-cards/anton-shilov/gigabyte-confirms-nvidia-geforce-gtx-880-launch-this-fall/ https://www.kitguru.net/components/graphic-cards/anton-shilov/gigabyte-confirms-nvidia-geforce-gtx-880-launch-this-fall/#comments Tue, 05 Aug 2014 22:59:46 +0000 http://www.kitguru.net/?p=206013 A representative for Gigabyte Technology has confirmed that the company plans to introduce its next-generation Nvdia GeForce GTX 880-based graphics cards this fall. The company even said that the boards will use custom coolers, which may mean that they will also be factory overclocked. In an interview with a Chinese web-site a graphics marketing director …

The post Gigabyte confirms Nvidia GeForce GTX 880 launch this fall first appeared on KitGuru.]]>
A representative for Gigabyte Technology has confirmed that the company plans to introduce its next-generation Nvdia GeForce GTX 880-based graphics cards this fall. The company even said that the boards will use custom coolers, which may mean that they will also be factory overclocked.

In an interview with a Chinese web-site a graphics marketing director at Gigabyte Technology said that the GeForce GTX 880 G1 Gaming graphics card would be released in late September, or early October, 2014. The timeframe was confirmed earlier by unofficial sources, hence, it is likely that it is correct.

Gigabyte G1 Gaming GeForce GTX 880 graphics card is projected to feature improved design (it is unclear whether the card will rely on Gigabyte’s own printed-circuit board, or will feature a reference PCB along with some improvements) with a proprietary cooling system, LED lights, metal back-plate and so on. It is highly-likely that the graphics board will be factory overclocked and will be faster than competitors.

nvidia_geforce_gtx_780_art

The fact that Nvidia will allow Gigabyte and other makers to pre-overclock the GeForce GTX 800-series graphics card means that the solutions will be positioned exactly as expected: as high-end gaming-class graphics boards. It looks like the GeForce GTX Titan-series products will remain Nvidia’s highest-performing graphics boards this year.

Nvidia GeForce GTX 800-series graphics cards will be based on the GM204 graphics processing unit, which belongs to the second-generation Maxwell family of GPUs. The GM204 is projected to be made using 28nm process technology.

Discuss on our Facebook page, HERE.

KitGuru Says: Since there are way too many confirmations about Nvidia’s plan to release three new GeForce GTX 800-series graphics cards this fall, it is highly probable that this will indeed happen. What we are not sure about is performance of the GeForce GTX 880 and how it compares to that of the GeForce GTX 780 and 780 Ti.

The post Gigabyte confirms Nvidia GeForce GTX 880 launch this fall first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/gigabyte-confirms-nvidia-geforce-gtx-880-launch-this-fall/feed/ 20
Nvidia to release three GeForce GTX 800 graphics cards this October https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-to-release-three-geforce-gtx-800-graphics-cards-this-october/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-to-release-three-geforce-gtx-800-graphics-cards-this-october/#comments Mon, 28 Jul 2014 23:00:13 +0000 http://www.kitguru.net/?p=204991 While it was expected that Nvidia Corp. plans to launch two high-end graphics cards this October, the company apparently intends to release three new products aiming different market segments that month. The launch of three new products will help Nvidia to maximize its sales later this year. Hermitage Akihabara web-site reports that Nvidia plans to …

The post Nvidia to release three GeForce GTX 800 graphics cards this October first appeared on KitGuru.]]>
While it was expected that Nvidia Corp. plans to launch two high-end graphics cards this October, the company apparently intends to release three new products aiming different market segments that month. The launch of three new products will help Nvidia to maximize its sales later this year.

Hermitage Akihabara web-site reports that Nvidia plans to introduce high-end GeForce GTX 870 and GeForce GTX 880 graphics cards based on the GM204 graphics processor in early October. In late October the company intends to release GeForce GTX 860 graphics adapter aiming mid-range market segment. It is likely that the solution will also be based on the GM204 graphics processing unit.

Keeping in mind that the GeForce GTX 860 will unlikely cost substantially more than $300/£200, it is logical to assume that the GM204 chip is not too expensive to manufacture.

nvidia_artwork_iron

What is unclear is what performance levels will be offered by the new GPUs. Theoretically, the GeForce GTX 880 should be faster than the GeForce GTX 780, however, that graphics card is based on the GK110 GPU, which is the world’s most complex graphics processor ever designed and which is probably more expensive to make than the GM204.

Nvidia’s GM204 graphics processing unit is based on the second-generation Maxwell architecture and is made using 28nm process technology.

Nvidia did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: It will be interesting to see how performance of the GM204-based graphics cards will compare against GK110-powered graphics adapters. The GeForce GTX 880 should be more powerful than the GeForce GTX 780, but its positioning will be substantially different. It will be an interesting situation if the GTX 880 ends up being slower than the GTX 780…

The post Nvidia to release three GeForce GTX 800 graphics cards this October first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-to-release-three-geforce-gtx-800-graphics-cards-this-october/feed/ 70
Nvidia to release GeForce GTX 870, GTX 880 in October or November – report https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-to-release-geforce-gtx-870-gtx-880-in-october-or-november-report/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-to-release-geforce-gtx-870-gtx-880-in-october-or-november-report/#comments Mon, 21 Jul 2014 23:06:24 +0000 http://www.kitguru.net/?p=204076 Nvidia Corp. plans to officially launch its next-generation flagship graphics offering this October or November, according to a media report. If the information is correct, then the firm will have a chance to boost its shipments this holiday season. SweClockers reports that Nvidia’s next-generation high-end graphics cards – the GeForce GTX 870 and the GTX …

The post Nvidia to release GeForce GTX 870, GTX 880 in October or November – report first appeared on KitGuru.]]>
Nvidia Corp. plans to officially launch its next-generation flagship graphics offering this October or November, according to a media report. If the information is correct, then the firm will have a chance to boost its shipments this holiday season.

SweClockers reports that Nvidia’s next-generation high-end graphics cards – the GeForce GTX 870 and the GTX 880 – will be introduced in October or November. The graphics boards are projected to be based on the code-named GM204 graphics processors and belong to the second-generation Maxwell family of solutions. The chip is said to be made using 28nm process technology.

Specifications of the GM204 chip and the GeForce GTX 870 and the GTX 880 graphics cards are unknown, but the model numbers suggest that the solutions are positioned for the high-end market. The GeForce GTX 870 and 880 are expected to be faster than the currently available GeForce GTX 780 and 780 Ti graphics cards, which means that the GM204 chip is more powerful than the code-named GK110, the most complex graphics processing unit ever designed.

nvidia_artwork

It will be interesting to see whether Nvidia’s GeForce 800-series of graphics cards will include any additional models, or will feature only two products based on the GM204 graphics processing units.

Nvidia is also rumoured to be working on the GM200 graphics processing unit that will succeed the GK110 and will be aimed not only on the market of gaming graphics cards, but also on supercomputers.

Nvidia did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: It will be interesting to see how much the new GeForce GTX graphics cards will cost. If the GM204 is more complex than the GK110, do not expect the upcoming graphics solutions to be affordable. However, based on the first photos of the GM204 published several weeks ago, the chip itself is about the size of the GK104, which means that it should not cost that much to manufacture…

The post Nvidia to release GeForce GTX 870, GTX 880 in October or November – report first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-to-release-geforce-gtx-870-gtx-880-in-october-or-november-report/feed/ 52
Nvidia may skip 20nm process technology, jump straight to 16nm https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-may-skip-20nm-process-technology-jump-straight-to-16nm/ https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-may-skip-20nm-process-technology-jump-straight-to-16nm/#comments Tue, 08 Jul 2014 22:59:29 +0000 http://www.kitguru.net/?p=202139 The exact plans of Advanced Micro Devices and Nvidia Corp. concerning the 20nm process technology from Taiwan Semiconductor Manufacturing Co. have never been publicly revealed and are not completely clear at this point. One of the reasons for that are low manufacturing yields, which forces fabless semiconductor designers to reconsider their plans; another reason is …

The post Nvidia may skip 20nm process technology, jump straight to 16nm first appeared on KitGuru.]]>
The exact plans of Advanced Micro Devices and Nvidia Corp. concerning the 20nm process technology from Taiwan Semiconductor Manufacturing Co. have never been publicly revealed and are not completely clear at this point. One of the reasons for that are low manufacturing yields, which forces fabless semiconductor designers to reconsider their plans; another reason is concern about TSMC’s ability to make enough 20nm chips, which makes chip developers review their launch schedules. However, there seems to be yet another potential reason why there are no leaks about 20nm GPUs: a new media report claims that Nvidia has simply decided to skip the 20nm technology and use the 16nm FinFET tech next year instead.

GM204: a mysterious GPU

VideoCardz web-site reports (citing a news-story from SemiAccurate web-site [which requires subscription]) that Nvidia plans to release the code-named GM204 graphics processing unit (which was previously known under the GM104 code-name) this October. Eventually four versions of the GM204-based GeForce GTX 800-series graphics cards with 1920 – 2560 stream processors (depending on the model) are expected to be available. The GM204 is projected to be made using 28nm fabrication technology. What is interesting is that Nvidia will reportedly skip the 20nm and will use 16nm fabrication process to make something that the media reports call the GM204b GPU.

Since TSMC’s woes with 20nm process technology were unexpected and the GM204 could have been redesigned to be made using 28nm process technology instead, its actual specifications and die size are unclear. If the chip integrates up to 2560 stream processors, is based on the Maxwell architecture and is made using 28nm fabrication process, then its die size should be over 500mm2. Increased efficiency of the new architecture should make the GM204 faster than the GK110, but not too dramatically, which is why it is uncertain why Nvidia wants to offer a new high-end solution that will not be significantly faster than the existing one.

nvidia_geforce_maxwell_mysterious_graphics_card_gm104_5

If the GM204 is designed to replace the GK104 GPU, is made using 28nm process technology and features around 300mm2 die size, it cannot integrate up to 2560 stream processors. Moreover, it probably does not need that many SPs to leave the GK104 (which has 1536 stream processors) behind in terms of performance. Based on what we do know about the GM204, the chip is slightly bigger than the GK104.

TSMC’s 16nm looks better than the 20nm

TSMC’s 20nm fabrication process has always been a strange one. Typically foundries offer several versions of manufacturing technologies aimed at different application: high-performance-chips, low-power chips, low-cost chips, etc. In case of 20nm TSMC only offers only one version of the process aimed at everything from low-cost system-on-chips for ultra-portable devices (such as smartphones) to high-performance processors (such as GPUs). Since there are reports about low 20nm yields at TSMC, high prices and limited production capacities available to AMD and Nvidia, it may make sense not to use this fabrication technology and jump directly to 16nm, which is set to be available for commercial chips in early 2015.

While the 16nm FinFET process technology makes more sense to use in early 2015 than the 20nm manufacturing technology, there is another reason why Nvidia could be more interested in this technology. TSMC has already developed 16nm FinFET+ fabrication process that will be utilised to make chips in volume later in 2015. In fact, TSMC expects the majority of its customers to use the 16nm FinFET+ version of the process due to its noticeable benefits compared to the original. It is interesting to note that there is a rumour about yet another 16nm process technology from TSMC called 16nm FinFET turbo. So far TSMC has not confirmed the existence of the third 16nm FinFET process.

Design rules of the 16nm FinFET and the 16nm FinFET+ are the same, everything is largely compatible. In general, 16nm FinFET designs can easily be produced on the 16nm FinFET+ node with minimal changes (if needed at all). The “plus” process is expected be fully qualified by September. TSMC’s fabs compatible with the company’s 20nm process technology are 95 per cent ready to produce chips using various versions of the company’s 16nm manufacturing technology, the company said earlier this year/

According to TSMC, 16nm FinFET+ provides up to 15 per cent performance improvement over the 16nm FinFET at the same level of power consumption. At the same clock-rate, chips produced using 16nm FinFET+ are expected to consume 30 per cent less power compared to the same chips made using 16nm FinFET.

In general, once Nvidia designs a chip for the 16nm node, it can speed it up using either the 16nm FinFET+ technology or the rumoured 16nm FinFET turbo technology, which means that the company can easily refresh its 16nm product line in 2016 by spending almost nothing on the development.

GM204b: an even more mysterious GPU

While it makes sense to skip the 20nm fabrication process for Nvidia, it is doubtful that the 16nm fabrication process will be used to produce the GM204b graphics processing unit.

If the GM204 is designed to replace the GK104 GPU and features around 300mm2 die size, it will shrink to around 150mm2 size when produced using 16nm fabrication process. While the GM204b will most probably be very cost-efficient to make, it will be rather hard to route a 256-bit GDDR5 memory bus to such a small chip. Therefore, it is more likely that Nvidia’s first 16nm GPU will be different from a simple GM204 redesigned for a different process technology.

If the GM204 is needed to replace the GK110 this year (which, as we know, it will not), then shrinking its die size from circa 500mm2 next year to around 250mm2 (in case of the GM204b) and reducing its price makes a lot of sense. However, that would create a mess on the market since there will be products with similar performance made using different process technologies and available at different price-points.

Final words

While Nvidia can theoretically skip the 20nm process technology and start to use the 16nm FinFET and derivatives, it will unlikely just redesign anything released on the 28nm node and produce it using the 16nm process technology (at least, not for the desktop market). Keeping in mind the advantages that the 16nm process technologies provide, it is more likely that Nvidia will try to release two brand-new generations of products made using 16nm FinFET and 16nm FinFET+ manufacturing processes. The company did something like that before with two generations of Fermi GPUs. If Nvidia follows such hypothetic plan, it will probably have three generations of the Maxwell-based products.

Nvidia did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: While unofficial information cannot be fully trusted, in many cases it is partly correct. While we do not know for sure whether Nvidia plans to skip TSMC’s 20nm node, we may assume that the company is not really impressed with the technology, which is why it may try to minimize its usage.

The post Nvidia may skip 20nm process technology, jump straight to 16nm first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/nvidia-may-skip-20nm-process-technology-jump-straight-to-16nm/feed/ 18
Mysterious Nvidia GeForce graphics card with 8GB of memory pictured https://www.kitguru.net/components/graphic-cards/anton-shilov/mysterious-nvidia-geforce-graphics-card-with-8gb-of-memory-pictured/ https://www.kitguru.net/components/graphic-cards/anton-shilov/mysterious-nvidia-geforce-graphics-card-with-8gb-of-memory-pictured/#comments Thu, 03 Jul 2014 19:40:00 +0000 http://www.kitguru.net/?p=201361 A Chinese web-site on Wednesday published images of an unknown Nvidia graphics card that carries a chip that is only several weeks old. It is believed that the graphics adapter is based on the code-named GM104/GM204 graphics processing unit powered by the Maxwell architecture. The graphics board is expected to become commercially available under the GeForce GTX …

The post Mysterious Nvidia GeForce graphics card with 8GB of memory pictured first appeared on KitGuru.]]>
A Chinese web-site on Wednesday published images of an unknown Nvidia graphics card that carries a chip that is only several weeks old. It is believed that the graphics adapter is based on the code-named GM104/GM204 graphics processing unit powered by the Maxwell architecture. The graphics board is expected to become commercially available under the GeForce GTX 880 name.

The picture of the graphics adapter that was published by MyDrivers is heavily masked in order to protect identity of the source and therefore we have no idea about peculiarities of the graphics card’s design. What we do know from the images of the graphics board is that it is a high-end solution that carries a lot of memory, requires up to 375W of power (it has two 6-pin and one 8-pin PCIe power connectors) and supports 3-way/4-way SLI technology. The board is not the final since it features a number of technical connectors and knobs not present on commercial products (it is also hard to believe that a single-GPU graphics card needs 375W of power), which is an indicator that the graphics adapter is months away.

nvidia_geforce_maxwell_mysterious_graphics_card_gm104

The mysterious graphics card is powered by the A1 revision an unknown graphics processing unit (marked as 1421A1 T6A996.0A0), which was made on the 21st week of the year 2014 (in late May). The chip itself is about the size of the code-named GK104 GPU, maybe a little bigger, but definitely not as big as the code-named GK110 graphics processor. The die size of approximately 300mm2 indicates that the chip is a new performance-mainstream GPU from Nvidia. Previously it was reported that the codename of the chip is either the GM104 or the GM204.

nvidia_geforce_maxwell_mysterious_graphics_card_gm104_5

The graphics card carries 16 GDDR5 memory chips from SK Hynix marked as H5GQ4H24MFR-R2C. The memory ICs feature 4Gb density and can operate at up to 7.0GHz effective data-rate. Such memory has been on the market for some time now. 16 GDDR5 chips with 4Gb density provide 8GB of memory.

nvidia_geforce_maxwell_mysterious_graphics_card_gm104_3_skhynix

Nowadays high-end graphics cards from Nvidia carry 3GB or 6GB of memory. It is logical to assume that the company’s next-generation graphics solutions will feature 8GB of memory. What is unclear is whether the new GPU features 256-bit or 512-bit memory bus. Usage of high-end GDDR5 as well as the fact that the GM104/GM204 GPU is not the top-of-the-range chip imply that the 256-bit bus is used. 7GHz GDDR5 memory could provide sufficient amount of bandwidth for the graphics processor.

nvidia_geforce_maxwell_mysterious_graphics_card_gm104_4_power nvidia_geforce_maxwell_mysterious_graphics_card_gm104_2

Traditionally, graphics chip designers use A2 revisions of their chips on commercial versions of graphics cards. Assuming that Nvidia got the A1 revision of the GM104/GM204 in late May and that it takes several months to prep a new version of the GPU, if everything goes well the company will get the final A2 revision in August or September. The company may start mass production of the new graphics processor once it ensures that the A2 works well and launch the GM104/GM204 commercially late this year.

Nvidia did not comment on the news-story.

Discuss on our Facebook page, HERE.

KitGuru Says: While it is now clear that Nvidia already has its new high-performance GPU at hands, specifications of the chip as well as manufacturing technology used to make it remain completely unknown.

The post Mysterious Nvidia GeForce graphics card with 8GB of memory pictured first appeared on KitGuru.]]>
https://www.kitguru.net/components/graphic-cards/anton-shilov/mysterious-nvidia-geforce-graphics-card-with-8gb-of-memory-pictured/feed/ 3