News Posts matching #GP107

Return to Keyword Browsing

NVIDIA GeForce MX350 and MX330 Surface, Pascal Based Entry mGPUs

NVIDIA's GeForce MX-series mobile GPU line exists so notebook manufacturers can put the NVIDIA logo on their products and boast of gaming capabilities. The company is giving finishing touches to its new GeForce MX330 and MX350 chips, based on the "Pascal" architecture. The MX330 is the company's second rebrand of the MX150 that's based on the 14 nm "GP108" silicon. It's equipped with 384 CUDA cores, and up to 2 GB of GDDR5 memory across a 64-bit wide memory interface. NVIDIA increased the clock speeds to 1531 MHz base, and 1594 MHz GPU Boost (compared to 1227/1468 MHz of the MX150), while remaining in the 25 W TDP envelope.

The MX350, on the other hand, is based on the 14 nm "GP107" silicon, is equipped with 640 CUDA cores, and 2 GB of GDDR5 memory across the same 64-bit bus width as the MX330; but has aggressive power-management that lends it a TDP of just 20 W, despite 66% more CUDA cores than the MX330. Both chips are easily capable of handling non-gaming tasks on typical 1080p / 1440p notebooks; but can game only at 720p thru 1080p, with low-to-mid settings.

NVIDIA to Reuse Pascal for Mobility-geared MX300 Series

NVIDIA will apparently still be using Pascal when they launch their next generation of low-power discrete graphics solutions for mobile systems. The MX300 series will replace the current crop of MX200 series (segregated in three products in the form of the MX230, MX250 10 W and MX250 25 W). The new MX300 keeps the dual-tiered system, but ups the ante on the top of the line MX350. Even though it's still Pascal, on a 14 nm process, the MX350 should see an increase in CUDA cores to 640 (by using NVIDIA's Pascal GP107 chip) from the MX250's 384. Performance, then, should be comparable to the NVIDIA GTX 1050.

The MX330, on the other hand, will keep specifications of the MX250, which signals a tier increase from the 256 execution units in the MX230 to 384. This should translate to appreciable performance increases for the new MX300 series, despite staying on NVIDIA's Pascal architecture. The new lineup is expected to be announced on February.

NVIDIA "Pascal" Based Mining GPU Lineup Detailed

GPU-accelerated crypto-currency mining poses a threat to the consumer graphics industry, yet the revenues it brings to GPU manufacturers are hard to turn away. The more graphics cards are bought up by crypto-currency miners, the fewer there are left for gamers and the actual target-audience of graphics cards. This is particularly bad for AMD, as fewer gamers have Radeon graphics cards as opposed to miners; which means game developers no longer see AMD GPU market-share as an amorphous trigger to allocate developer resources in optimizing their games to AMD architectures.

To combat this, both AMD and NVIDIA are innovating graphics cards designed specifically for crypto-currency mining. These cards are built to a cost, lack display outputs, and have electrical and cooling mechanisms designed for 24/7 operation, even if not living up to the durability standards of real enterprise-segment graphics cards, such as Radeon Pro series or Quadro. NVIDIA's "Pascal" GPU architecture is inherently weaker than AMD's "Polaris" and older Graphics CoreNext architectures at Ethereum mining, owing in part to Pascal's lack of industry-standard asynchronous compute. This didn't deter NVIDIA from innovating a lineup of crypto-mining SKUs based on its existing "Pascal" GPUs. These include the NVIDIA P104 series based on the "GP104" silicon (on which the GTX 1080 and GTX 1070 are based); and P106 series based on the "GP106" silicon (GTX 1060 series is based on this chip). NVIDIA didn't tap into its larger "GP102" or smaller "GP107" chips, yet.

Inno3D Intros GeForce GTX 1050 Ti Single-slot Graphics Card

Inno3D rolled out a single-slot GeForce GTX 1050 Ti graphics card (model: N105T2-1SDV-M5CM). The card combines NVIDIA reference PCB for the GTX 1050 Ti, with a single slot cooling solution. This cooler consists of a lateral-blower which pushes air through a dense aluminium channel heatsink, with copper base-plate over the GPU. The card relies on the PCI-Express slot for all its power.

Based on the 16 nm GP107 silicon, the GTX 1050 Ti features 768 CUDA cores, 48 TMUs, 32 ROPs, and a 128-bit wide GDDR5 memory interface. The Inno3D GTX 1050 Ti single-slot card sticks to NVIDIA-reference clock speeds of 1291 MHz core, 1392 MHz GPU Boost, and 7.00 GHz (GDDR5-effective) memory. Display outputs include one each of DisplayPort 1.4, HDMI 2.0b, and dual-link DVI. The company didn't reveal pricing.

NVIDIA Announces GeForce GTX 1050 Mobile and GTX 1050 Ti Mobile

NVIDIA today announced the mobile variants of GeForce GTX 1050 and GeForce GTX 1050 Ti. Not only do the two SKUs feature unchanged core-configurations from their desktop counterparts, but also feature higher clock speeds. The GTX 1050 Ti Mobile ships with 1493 MHz core and 1620 MHz GPU Boost (compared to 1290/1392 MHz of the desktop GTX 1050 Ti); while the GTX 1050 Mobile ships with 1354/1493 MHz (compared to 1354/1455 MHz of its desktop sibling). Both SKUs are being offered to notebook designers with up to 4 GB of GDDR5 memory.

Based on the 14 nm GP107 silicon, the GeForce GTX 1050 Ti Mobile features 768 CUDA cores, 48 TMUs, 32 ROPs, and a 128-bit wide GDDR5 memory interface. The GTX 1050 Mobile is based on the same silicon, but features 640 CUDA cores, 40 TMUs, 32 ROPs, and 128-bit wide GDDR5 memory interface. At the 2017 International CES expo, various notebook designers are expected to unveil gaming notebooks with these two chips. The GTX 1050 Ti is being mooted as being ideal for notebooks with 1080p displays, while the GTX 1050 Mobile is targeted at 1600x900 displays.

NVIDIA GeForce GTX 1050 Ti and GTX 1050 Now Available

NVIDIA announced retail availability of its GeForce GTX 1050 Ti and GTX 1050 graphics cards. Targeting two key sub-$200 price-points, and positioned as gateways to competitive e-Sports gaming, the two chips compete with AMD Radeon RX 460 and RX 470, and exploit a vast price/performance gap between the two. The GTX 1050 Ti starts at USD $139.99, while the GTX 1050 starts at $109.99. Since there are no reference-design cards, all cards available from today are custom-design implementations of all shapes and sizes.

The GTX 1050 Ti and GTX 1050 are based on the new "GP107" silicon, NVIDIA's first built on the 14 nm FinFET process. Both chips are implementations of NVIDIA "Pascal" architecture. The GTX 1050 Ti features 768 CUDA cores, 48 TMUs, 32 ROPs, and 4 GB of GDDR5 memory across a 128-bit wide interface. The GTX 1050, on the other hand, features 640 CUDA cores, 40 TMUs, 32 ROPs, and 2 GB of GDDR5 memory across the 128-bit memory bus. Both cards have their TDP rated at 75W.

GIGABYTE Announces its GeForce GTX 1050 Series

GIGABYTE, the world's leading premium gaming hardware manufacturer, today introduced both GeForce GTX 1050 Ti and GTX 1050 graphics cards based on the Pascal GP107 core architecture. Equipped with 4GB of 128-bit GDDR5 memory, GIGABYTE GTX 1050 Ti series comes in 4 models with enthusiast' favored G1 GAMING edition leading the charge, followed by the WINDFORCE OC edition, the dual-fan OC edition, and the single-fan D5 edition. The GTX 1050 lineup will feature 2GB of GDDR5 memory and offered in the same 4 variants as well. The vast array of graphics arsenal is set to provide gamers with maximum performance for diverse PC build requirements at various budget ranges.

Powered by the Super Overclocked GPU, the G1 GAMING edition ups the ante with hefty overclocks right out of the box, together with the signature WINDFORCE cooling and RGB Illumination for gamers who crave superior cooling and boost in performances with style. Through GIGABYTE's GPU Gauntlet Sorting technology, the top-notch GPU cores built in the G1 GAMING cards push overclocking capability to the limit without compromising the system reliability. The ultra-durable components augmented with 4+1 phase design make the MOSFET working at a lower temperature to provide more stable voltage output for superior overclocking.

NVIDIA Announces the GeForce GTX 1050 and GeForce GTX 1050 Ti

NVIDIA today announced the GeForce GTX 1050 and GeForce GTX 1050 Ti, its two new mainstream graphics cards based on the new GP107 silicon, the smallest chip based on the "Pascal" architecture. The two are designed with sufficient power for MOBA games at HD and Full-HD resolutions, respectively. The GeForce GTX 1050 is priced at USD $109, while the GTX 1050 Ti goes for $139.

The GeForce GTX 1050 Ti features 768 CUDA cores spread across 6 streaming multiprocessors, 48 TMUs, 32 ROPs, and 4 GB of GDDR5 memory across a 128-bit wide memory interface. The core is clocked at 1290 MHz, with maximum GPU Boost frequency of 1392 MHz, and memory at 7.00 GHz, working out to 112 GB/s memory bandwidth. The GTX 1050 features 640 CUDA cores across 5 streaming multiprocessors, 40 TMUs, 32 ROPs, and 2 GB of GDDR5 memory across the 128-bit memory interface. This card is clocked slightly higher, with 1354 MHz core, 1455 MHz GPU Boost, and 7.00 GHz memory. The two cards will be available from 25th October, 2016.

ASUS GeForce GTX 1050 Ti Expedition Graphics Card Pictured

Here's the first picture of an ASUS-branded, custom-design GeForce GTX 1050 Ti graphics card, and debut of a new brand extension by the company - Expedition. A picture of its packaging was leaked to the web, revealing a new cooler design by the company. This unnamed cooler appears to feature a monolithic aluminium heatsink (made out of a single piece of metal, likely with a copper core), ventilated by a pair of fans. The card offers 4 GB of GDDR5 memory across the GP107 silicon's 128-bit wide memory bus. ASUS is also rumored to be working on an ROG Strix graphics card based on this GPU.

NVIDIA GP107 GPU Built on Samsung 14 nm Node?

Could the upcoming "GP107" ASIC by NVIDIA be its first on the 14 nanometer silicon fabrication process? That's what 3DCenter.org uncovered. Informed sources tell the German tech-site that the GP107 could be the first GPU built by NVIDIA's partnership with Samsung Electronics, after it emerged that the Korean silicon giant could manufacture certain GeForce "Pascal" GPUs on its 14 nm LPP (low-power plus) node. There's also talk of NVIDIA optical-shrinking its existing GeForce Pascal chips to 14 nm, built by Samsung.

The GP107 silicon will power two known mid-range desktop SKUs slated for launch later this month, the GeForce GTX 1050 Ti, and the GTX 1050. Bound for mid-October, the GTX 1050 Ti features 768 CUDA cores, 48 TMUs, 32 ROPs, and a 128-bit GDDR5 memory interface holding 4 GB of memory; with GPU clocks above the 1.50 GHz mark. The GTX 1050, on the other hand, could launch in late-October, featuring 640 CUDA cores, 40 TMUs, 32 ROPs, and 2 GB of GDDR5 memory across the chip's 128-bit memory interface, with the possibility of custom-design 4 GB SKUs. NVIDIA is targeting the $150 and $120 price-points with these SKUs. The company could also work on mobile SKUs based on the chip.

NVIDIA Readies Two GeForce GTX 1050 Variants

NVIDIA is preparing not one, but two variants of the GeForce GTX 1050 mid-range graphics cards. The two will launch in October 2016, beginning with the faster GeForce GTX 1050 Ti around mid-October, and the cheaper GeForce GTX 1050 (non-Ti) some time in late-October. Both SKUs will be based on the new GP107 silicon, with the GTX 1050 Ti maxing it.

The GeForce GTX 1050 Ti is expected to be endowed with 768 CUDA cores, 48 TMUs, and 32 ROPs; with clock speeds of 1290 MHz core, 1382 MHz GPU Boost, and 7.00 GHz (GDDR5-effective) memory. This SKU will feature 4 GB of GDDR5 memory across a 128-bit wide memory interface. The GTX 1050, on the other hand, will feature 640 CUDA cores, 40 TMUs, an unknown number of ROPs, 1354 MHz core, 1455 MHz GPU Boost, and just 2 GB of GDDR5 memory across the chip's 128-bit memory interface. The GTX 1050 Ti could target the $150 price-point, while the GTX 1050 could take aim at $120.
Return to Keyword Browsing