Today, NVIDIA would announce their brand new GeForce GTX 1050 series graphics cards for budget gamers. The new graphics cards are based on the Pascal core architecture that delivers a leap in gaming performance over Maxwell based graphics cards along with increased power efficiency.
NVIDIA GeForce GTX 1050 Ti and GeForce GTX 1050 Announced
Both cards, the GeForce GTX 1050 Ti and GeForce GTX 1050 utilize the GP107 GPU. While the announcement is planned for today, both cards won't be available in retail market till 25th of October. The reference solutions will feature a very nice SFF design that won't use any external power connector and would be able to run on an existing power supply with ease.
NVIDIA GeForce GTX 1050 Ti – Official Price of $139 US, October 25th Launch
The NVIDIA GeForce GTX 1050 Ti features 768 CUDA Cores. The core comes packed with 48 TMUs and 32 ROPs. The chip is clocked at 1318 MHz core and 1392 MHz boost frequency which is just around a 250 MHz jump over the GM107 GPU. The texture fill rate of the chip goes up to 84 GTexel/s (almost twice of GM107).The pixel fill rate is maintained at 41.3 GPixel/s that is a good increase over Maxwell. The card should also feature 4 GB of GDDR5 memory clocked at 7 GHz. This gives us 112 GB/s bandwidth along the narrow 128-bit bus interface.
The card will be priced at $139 US which is a really sweet price considering that it only costs $20 more than the Radeon RX 460 yet going to be faster. The card will feature the same TDP as the Radeon RX 460’s Polaris 11 core, coupled with all the enhancements Pascal brings for gamers. This card will be available in various custom models on launch and we can expect those to follow the reference pricing.
NVIDIA GeForce GTX 1050 – Official Price of $109 US, October 25th Launch
Moving on to the next variant, we have the GTX 1050. The non-Ti variant features a cut down, Pascal based GP107 core. It has specifications configured at 640 CUDA cores, 40 TMUs and 32 ROPs. It will have a few bits disabled here and there, the clock speeds are maintained at 1354 MHz and 1455 MHz boost clocks. The card will be available in both 2 GB models.
Priced at $109 US, this model can be a effective solution against the Radeon RX 460 which has the same price point. The card will also feature a 75W TDP which means no extra power connector would be required. We will see some models not even closing in on the 75W limit while boosting past the reference clock speeds. Display connectors for the reference variants include three DP 1.4a, a single HDMI and a single DVI connector.
NVIDIA GP107 Utilizes Samsung's 14nm FinFET Process Node
One of the major changes that the GP107 GPU gets is the 14nm FinFET node. The chip is manufactured by Samsung and is the only chip in the Pascal lineup to feature a different process node compared to the rest of the lineup. The 14nm FinFET node may be one reason why we are looking at lower clocks on the GP107 GPU compared to the rest of the lineup. But at the same time, these cards are constrained due to their 75W TDP.
The switch to 14nm FF is still an interesting move and we look forward to see the overclocking and power efficiency results of Pascal 14nm process compared to AMD's GCN 14nm process designs.
NVIDIA GeForce 10 Pascal Family
Graphics Card Name | NVIDIA GeForce GTX 1050 2 GB | NVIDIA GeForce GTX 1050 3 GB | NVIDIA GeForce GTX 1050 Ti | NVIDIA GeForce GTX 1060 3 GB | NVIDIA GeForce GTX 1060 5 GB | NVIDIA GeForce GTX 1060 6 GB | NVIDIA GeForce GTX 1070 | NVIDIA GeForce GTX 1070 Ti | NVIDIA GeForce GTX 1080 | NVIDIA Titan X | NVIDIA GeForce GTX 1080 Ti | NVIDIA Titan Xp |
---|---|---|---|---|---|---|---|---|---|---|---|---|
Graphics Core | GP107 | GP107 | GP107 | GP106 / GP104 | GP106 | GP106 / GP104 | GP104 | GP104 | GP104 | GP102 | GP102 | GP102 |
Process Node | 14nm FinFET | 14nm FinFET | 14nm FinFET | 16nm FinFET | 16nm FinFET | 16nm FinFET | 16nm FinFET | 16nm FinFET | 16nm FinFET | 16nm FinFET | 16nm FinFET | 16nm FinFET |
Die Size | 132mm2 | 132mm2 | 132mm2 | 200mm2 | 200mm2 | 200mm2 | 314mm2 | 314mm2 | 314mm2 | 471mm2 | 471mm2 | 471mm2 |
Transistors | 3.3 Billion | 3.3 Billion | 3.3 Billion | 4.4 Billion | 4.4 Billion | 4.4 Billion | 7.2 Billion | 7.2 Billion | 7.2 Billion | 12 Billion | 12 Billion | 12 Billion |
CUDA Cores | 640 CUDA Cores | 768 CUDA Cores | 768 CUDA Cores | 1152 CUDA Cores | 1280 CUDA Cores | 1280 CUDA Cores | 1920 CUDA Cores | 2432 CUDA Cores | 2560 CUDA Cores | 3584 CUDA Cores | 3584 CUDA Cores | 3840 CUDA Cores |
Base Clock | 1354 MHz | 1392 MHz | 1290 MHz | 1506 MHz | 1506 MHz | 1506 MHz | 1506 MHz | 1607 MHz | 1607 MHz | 1417 MHz | 1480 MHz | 1480 MHz |
Boost Clock | 1455 MHz | 1518 MHz | 1392 MHz | 1708 MHz | 1708 MHz | 1708 MHz | 1683 MHz | 1683 MHz | 1733 MHz | 1530 MHz | 1583 MHz | 1582 |
FP32 Compute | 1.8 TFLOPs | 2,3 TFLOPs | 2.1 TFLOPs | 4.0 TFLOPs | 4.4 TFLOPs | 4.4 TFLOPs | 6.5 TFLOPs | 8.1 TFLOPs | 9.0 TFLOPs | 11 TFLOPs | 11.5 TFLOPs | 12.5 TFLOPs |
VRAM | 2 GB GDDR5 | 3 GB GDDR5 | 4 GB GDDR5 | 3 GB GDDR5 | 6 GB GDDR5 | 6 GB GDDR5/X | 8 GB GDDR5/X | 8 GB GDDR5 | 8 GB GDDR5X | 12 GB GDDR5X | 11 GB GDDR5X | 12 GB GDDR5X |
Memory Speed | 7 Gbps | 7 Gbps | 7 Gbps | 8 Gbps | 8 Gbps | 9 Gbps / 10 Gbps | 8 Gbps | 8 Gbps | 11 Gbps | 10 Gbps | 11 Gbps | 11.4 Gbps |
Memory Bandwidth | 112 GB/s | 84 GB/s | 112 GB/s | 192 GB/s | 160 GB/s | 224 GB/s / 240 GB/s | 256 GB/s | 256 GB/s | 352 GB/s | 480 GB/s | 484 GB/s | 547 GB/s |
Bus Interface | 128-bit bus | 96-bit bus | 128-bit bus | 192-bit bus | 160-bit bus | 192-bit bus | 256-bit bus | 256-bit bus | 256-bit bus | 384-bit bus | 352-bit bus | 384-bit bus |
Power Connector | None | None | None | Single 6-Pin Power | Single 6-Pin Power | Single 6-Pin Power | Single 8-Pin Power | Single 8-Pin Power | Single 8-Pin Power | 8+6 Pin Power | 8+6 Pin Power | 8+6 Pin Power |
TDP | 75W | 75W | 75W | 120W | 120W | 120W | 150W | 180W | 180W | 250W | 250W | 250W |
Display Outputs | 1x Display Port 1.4 1x HDMI 2.0b 1x DVI | 1x Display Port 1.4 1x HDMI 2.0b 1x DVI | 1x Display Port 1.4 1x HDMI 2.0b 1x DVI | 3x Display Port 1.4 1x HDMI 2.0b 1x DVI | 3x Display Port 1.4 1x HDMI 2.0b 1x DVI | 3x Display Port 1.4 1x HDMI 2.0b 1x DVI | 3x Display Port 1.4 1x HDMI 2.0b 1x DVI | 3x Display Port 1.4 1x HDMI 2.0b 1x DVI | 3x Display Port 1.4 1x HDMI 2.0b 1x DVI | 3x Display Port 1.4 1x HDMI 2.0b 1x DVI | 3x Display Port 1.4 1x HDMI 2.0b | 3x Display Port 1.4 1x HDMI 2.0b |
Launch Date | October 2016 | May 2018 | October 2016 | September 2016 | August 2018 | July 2016 | June 2016 | October 2017 | May 2016 | August 2016 | March 2017 | April 2017 |
Launch Price | $109 US | $119 US-$129 US | $139 US | $199 US | TBD | $249 US | $349 US | $449 US | $499 US | $1200 US | $699 US | $1200 US |
NVIDIA GeForce GTX 1050 Ti and GTX 1050 Gaming Performance Results
Coming to the performance numbers, the GeForce GTX 1050 official performance slides reveal it to be up to 2.5x faster than the GTX 650. Now its really odd that NVIDIA would use such an old graphics card to make a comparison with their 2016 card. But, there are many users who still own the card and NVIDIA is basically showing the upgrade advantages that their new cards bring to users who are still running GTX 650 class cards.
Overall, the GTX 1050 will compete against the Radeon RX 460 as mentioned above. The performance results for the GTX 1050 Ti are more interesting since they are covered by a Chinese review site. The site used a AIB model, manufactured by GALAX and compared it against the GTX 950 and GTX 960 cards.
GALAX GeForce GTX 1050 Ti Dual Graphics Card:
The card packs a custom design PCB that does use a 6-Pin power connector. It comes with a 3+1 phase PWM that offers superior overclocking performance compared to reference variants. Display outputs include dual DVI and a single HDMI / DP 1.4 port. The cooler is a dual fan design that pushes heat to a large aluminum based fin block. Heat is dissipated from the core and VRAM through a single heatpipe that makes direct contact with their surface.
This variant is also factory overclocked and comes with faster clock speeds of 1354 MHz base and 1468 MHz boost. These are a good improvement over the reference clocks of 1290 MHz base and 1382 MHz boost. It's time to talk about gaming performance and from the looks of it, the card is even faster than the GTX 960 that is a good sign for budget builders. Not only is the card more power efficient but also faster than the GM206 Maxwell card.
GALAX GeForce GTX 1050 Ti Synthetic Performance:
GALAX GeForce GTX 1050 Ti Gaming Performance:
Gainward GeForce GTX 1050 Ti EX Gaming Performance:
These results do look great but the more surprising fact is that the card runs cool too. During Furmark load test, the GPU didn't break the 56C barrier even when it was running past its boost clock. Total system power consumption at idle was rated at 73W and 170W at full load. This indicates that you won't need a PSU that is greater than 500W when using a Pascal based GP107 card.