NVIDIA GeForce GTX 1060 Full Specifications Detailed – 2 GHz Overclocking Potential, GP106 GPU Block Diagram Pictured, 200mm2 Size

Author Photo
Jul 10, 2016
32Shares
Submit

The final specifications of NVIDIA’s GeForce GTX 1060 graphics card have been confirmed through our sources. The GeForce GTX 1060 is the latest entry in the GeForce 10 family which features the 16nm FinFET based Pascal architecture to deliver a big increase in performance and efficiency over its predecessors. Aimed at the budget gaming market, the GTX 1060 would offer competitive performance at its starting price of $249 US.

The NVIDIA GeForce GTX 1060 will be hitting the competition at $249 US.

NVIDIA GeForce GTX 1060 Official Specification Confirmed – Features 4.4 Billion Transistors on a 200mm2 Die

NVIDIA announced their GeForce GTX 1060 graphics card a few days back and allowed sites to publish official specifications along with pricing details. Even with specifications out, there is still a lot of stuff about the GP106 GPU core that remains a mystery and we will be revealing that right now. It should first be pointed out that the GeForce GTX 1060 6 GB would be shipping at a price of $249 US for non-reference and $299 US for the original Founders Edition (reference) variant.

NVIDIA GeForce GTX 1060 Full Slide Deck:

NVIDIA’s GeForce GTX 1060 is based on the GP106 GPU core. The GP106 GPU features a die size of 200mm2 which makes it 14% smaller than the GM206 GPU and 57% smaller than the GP104 GPU. The GP106 houses total of 4.4 Billion transistors which are 1.4 Billion more transistors compared to the GM206 GPU. The NVIDIA GeForce GTX 1060 features the full version of the GP106 GPU so next up, we will detail the block diagram of this graphics chip.

NVIDIA GP106-400-A1 GPU Block Diagram:

The NVIDIA GP106-400-A1 GPU block consists of 2 GPC (Graphics Processing Clusters). Each GPU houses five SM (Streaming Multiprocessor) units. Each SM consists of 128 CUDA cores which means that the full chip features 1280 CUDA cores. Each SM has 8 TMUs (Texture Mapping Units) which give us 80 TMUs on the chip while each GPC is attached to 24 ROPs (Raster Operating Units) providing a total of 48 ROPs. Each SM consists of 256 KB of register file capacity, a 96 KB shared memory unit and 48 KB of total L1 cache storage.

The GP106 GPU lies at the heart of the GeForce GTX 1060 graphics card.

The chip also comes with six 32-bit memory controllers which make up the 192-bit bus interface. This allows the card to feature either a 6 GB or 3 GB memory buffer. Each 32-bit memory controller is feature 256 KB L2 cache and the entire design features a total of 1536 KB of L2 cache for the memory bus and 48 ROPs.

The NVIDIA GP106 GPU features a die size of 200mm2 and holds 4.4 Billion transistors.

The new Pascal GPUs feature the latest Polymorph Engine 4.0 which allows significant geometry enhancements in VR and Surround Display applications. Utilizing the new engine is the Simultaneous Multi-Projection tech that reduces geometry work by up to 32X. The Pascal architecture also provides significant amounts of memory conservation through delta color compression which can provide up to 20% more effective bandwidth than what’s originally featured on the card.

It’s also true that the GeForce GTX 1060 doesn’t feature SLI support since NVIDIA is now focusing multi-GPU efforts on the high-end section. The card however does support MDA mode or LDA explicit mode in certain DirectX 12 applications where multiple GeForce GTX 1060 cards could be combined to deliver better graphics performance throughput.

NVIDIA GeForce GTX 1060 High-Resolution Picture Gallery:

NVIDIA GeForce GTX 1060 Final Specifications:

Now coming to the specifications of the card itself, the GeForce GTX 1060 is indeed everything what we have been hearing for a few days. It has 1280 CUDA cores, 80 TMUs and 48 ROPs. The GTX 1060 is clocked at speeds of 1506 MHz base and 1708 MHz boost clock which delivers a texture fill rate of 120.5 GTexels/s. The GeForce GTX 1060 also features a 6 GB GDDR5 VRAM buffer that runs across a 192-bit bus interface. The memory is configured to run at 8000 MHz which is the fastest speed available for GDDR5 memory. GDDR5X is the next phase for GDDR5 memory but comes at a higher manufacturing costs which are not feasible for cards lined up in the budget market.

The GP106 GPU is a very efficient core and features a TDP of just 120W which is the same as its GM206 GPU based predecessor (GTX 960). The card is powered by a single 6-Pin connector while custom models with enhanced PCB and cooling will feature either single 8-Pin or dual 6-Pin connector configurations. The GTX 1060 also features three Display Port 1.4, a single HDMI 2.0b and DVI port for display outputs.

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 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 1060 Is The Third Pascal GPU To Break The 2 GHz Barrier – Impressive Clock Numbers

The NVIDIA GeForce GTX 1060 reference models, also known as the Founders Edition, features a enhanced design scheme. The body was made using faceted die cast aluminum finish to add durability and strength to this card. The enhanced cooler allows the card to keep cool and steady even in brutal overclocking loads as such, the card houses a heatsink that is 50% larger than the heatsink used on GTX 960 offering more surface area for the heat to transfer load. The heatsink itself is a matte black coated aluminum design that features two copper heatpipes that are cooled by the single radial fan on the card.

The PCB on the card uses dual-FETs for both memory and GPU which is a plus over the previous reference designs. These have been used on all Pascal based cards along with low impedance power delivery network regulators and custom voltage regulators for the best current flow and stability.

The dual gate MOSFET is essentially a form of MOSFET where two gates are fabricated along the length of the channel – one after the other. In this way, both gates affect the level of current flowing between the source and drain. In effect, the dual gate MOSFET operation can be considered the same as two MOSFET devices in series. Both gates affect the overall MOSFET operation and hence the output. via Radio Electronics

The Dual-FET design on Pascal cards delivers stability and maximum power delivery for 2 GHz overclocks.

This allows the GeForce GTX 1060 to deliver the same overclocking potential as its siblings based on the high end GP104 GPU. Internal testing reveals that 2 GHz overclocking figures would be a common sight on both reference and custom variants but I would suggest waiting for the official reviews for more detail info on the overclocking sector of this card.

NVIDIA GeForce GTX 1060 2 GHz Overclock Demo:

NVIDIA GeForce GTX 1060 2 GHz Overclock

NVIDIA GeForce GTX 1060 reference and custom models would be available readily on 19th July for prices starting at $249 US. The card will also be available in 3 GB variants which will ship for an even lower price point. We will have more info on the card along with a custom model round up in a few days.

Submit