NVIDIA GeForce GTX 1080 Final Specifications and Launch Presentation

Published: 15th May 2016, 19:05 GMT

Today we have final specifications of GeForce GTX 1080.

NVIDIA GeForce GTX 1080

GeForce_GTX_1080_Front

NVIDIA GTX 1080 is the first graphics card from GeForce 1000, or as NVIDIA calls it 10 Series, based on 16nm FinFET architecture called Pascal. New card is clocked at 1607 MHz with boost clock up to 1733 MHz, however actual clock will vary depending on application.

NVIDIA GTX 1080 is equipped with one 8-pin power connectors and TDP is rated at 180W, and from what I heard, actual power consumption should not exceed this value in gaming.

NVIDIA GeForce GTX 1080 Specifications
May 15th 2016GeForce GTX 1080GeForce GTX 980 TiGeForce GTX 980
Fabrication Node16nm FinFET28nm28nm
ArchitecturePascalMaxwellMaxwell
Die Size314 mm2601 mm2398 mm2
GPU GP104-400GM200-310GM204-400
Transistors7.2 b8.0 b5.2 b
Transistors per mm2~22.9 m~13.3 m~13.1 m
Streaming Multiprocessors20 2216
CUDA Cores256028162048
TMUs160176128
ROPs649664
TFLOPs8.2 TFLOPs5.6 TFLOPs4.6 TFLOPS
Memory Type8GB GDDR5X6GB GDDR54GB GDDR5
Base Clock1607 MHz1000 MHz1127 MHz
Boost Clock 1733 MHz1076 MHz1216 MHz
Memory Clock1250 MHz1750 MHz1750 MHz
Effective Memory Clock10000 MHz7000 MHz7000 MHz
Memory Bus256-bit384-bit256-bit
Memory Bandwidth320 GB/s337 GB/s224 GB/s
TDP180W250W165W 
Power Connectors1x 8pin1x 6pin + 1x 8pin2x 6pin
MSRP$599
$699 FE
$649$549

Pascal GP104 GPU

NVIDIA GeForce GTX 1080 has 160 TMUs and 64 ROPs. This was actually confirmed earlier by GPU-Z update, but today our knowledge is based on official GPU diagram, which looks like this:

NVIDIA GP104 Block Diagram

NVIDIA GP104 Block Diagram

As you can see Pascal GP104 is split into four blocks (Graphics Processing Clusters), each GPC has 5 Streaming Multiprocessors and each SM has two blocks of 64 CUDA cores, so this gives us total of 2560 CUDA Cores. As a side note, GP100 only has one block of 64 CUDAs per SM.

Interestingly the number of ROPs has not changed since GTX 980, which means GTX 980 Ti still has 32 ROPs more, and therefore GTX 1080 has 64 ROPs.

The die area of GP104 GPU is 314 mm2, which is right in-between GM204 and GM206. Despite smaller GPU we have 2 billion transistors more than GM204. Also the density of transistors increased by 10 million per mm2 to almost 23 million.

8GB GDDR5X Memory

NVIDIA GeForce GTX 1080 is the first commercial graphics card to utilize GDDR5X memory. This technology enables higher bandwidth on shorter interfaces, and since GP104 is equipped with eight 32-bit memory controllers (total of 256-bit), the maximum bandwidth should oscillate at around 320 GB/s. This value comes from very high memory frequency which is 1250 MHz (10 GHz effective).

NVIDIA GeForce GTX 1080 GDDR5X

Pascal Memory Compression

Pascal GP104 brings new memory compression technology. Fourth Generation Delta Color Compression is said to deliver 1.7 times of GTX 980 effective bandwidth. However without NVIDIA’s own tools this value is impossible to confirm and probably should be taken with a grain of salt.

NVIDIA GeForce GTX 1080 Pascal Bandwidth Reduction NVIDIA GeForce GTX 1080 Maxwell Memory Compression NVIDIA GeForce GTX 1080 Pascal Memory Compression (2)NVIDIA GeForce GTX 1080 Pascal Memory Compression

NVIDIA GeForce GTX 1080 Display Support

NVIDIA GeForce GTX 1080NVIDIA GeForce GTX 980
Number of Active Heads44
Number of Connectors66
Maximum Resolution7680 x 4320 @ 60 Hz
(requires 2 DP 1.3 connectors)
5120 x 3200 @ 60 Hz
(requires 2 DP 1.2)
Digital ProtocolsHDMI 2.0b with HDCP 2.2,
DP (DP 1.2 certified,
DP 1.3 Ready,
DP 1.4 Ready)
LVDS, TMDS/HDMI 2.0
DP 1.2

NVIDIA GeForce GTX 1080 Display Revolution

NVIDIA GeForce GTX 1080 Video Support

NVIDIA GeForce GTX 1080NVIDIA GeForce GTX 980
H.264 EncodeYes (2x 4K @ 60 Hz)Yes
H.264 DecodeYes (2x 4K @ 120 Hz up 240 Mbps)Yes
HEVC EncodeYes (2x 4K @ 60 Hz)Yes
HEVC DecodeYes (2x 4K @ 120 Hz /
8K @ 30 Hz up 320 Mbps)
No
10-bit HEVC EncodeYesNo
10-bit HEVC DecodeYesNo
12-bit HEVC DecodeYesNo
MPEG2 DecodeYesYes
VP9 DecodeYes (2x 4K @ 120 Hz up 320 Mbps)No

NVIDIA Fast Sync

NVIDIA GeForce GTX 1080 also brings new technology called Fast Sync. We can’t give you any details right now, but judging from the graphs, this technology allows much faster frame rendering (30-40ms) compared to Vsync (90-110 ms). My understanding is that this technology is trying to bring better user experience in VR by replacing VSync.

VSYNC ONVSYNC OFFFAST SYNC
Flow ControlBackpressureNoneNone
LatencyHighLowLow
TearingHighTearingNone

NVIDIA Pascal High-Bandwidth SLI Bridge

GeForce 10 Series based on Pascal architecture also deliver new connection method for multi-GPU configurations. By utilizing both SLI fingers new bridge delivers higher throughput between GPUs. This technology will improve experience at higher resolutions. In fact NVIDIA even has its own recommendation table for those looking into GTX 1080 SLI:

19×1025×14 @ 60 Hz25×14 @ 120 Hz4K5KSurround
Standard BridgeXX
LED BridgeXXXX
HB BridgeXXXXXX

NVIDIA GeForce GTX 1080 SLI HB Bridge

GPU Boost 3.0

NVIDIA GeForce GTX 1080 GPU Boost 3

NVIDIA GeForce GTX 1080 Pascal Crafted for speed

NVIDIA GeForce GTX 1080 Performance

During official presentation Jen-Hsun Huang said that GTX 1080 is faster than GTX 980 SLI. This is true but only when Virtual Reality is considered. In real world gaming scenario performance is almost comparable (this will be confirmed by reviews), but it is definitely not faster, at least not in all games.

NVIDIA GeForce GTX 1080 Crafted for speed

 NVIDIA GeForce GTX 1080 HDR

NVIDIA GeForce GTX 1080 HDR

NVIDIA GeForce GTX 1080 GAMESTREAM HDR

NVIDIA GeForce GTX 1080 HDR GameStream

NVIDIA GeForce GTX 1080 Preemption in VR – Pascal

NVIDIA GeForce GTX 1080 Preemption in VR Pascal NVIDIA GeForce GTX 1080 Pascal Preemption NVIDIA GeForce GTX 1080 Preeemption in VR

NVIDIA GeForce GTX 1080 Simultaneous Multi-Projection

If you are confused what Simultaneous Multi-Projection really is, then this slide should give you a straight answer. Think of this as a technology that saves GPU from rendering pixels that would not even be displayed in the final picture. Geometry is applied before final image is fully rendered, as opposed to applying geometry after picture ends its route in rendering pipeline.

NVIDIA GeForce GTX 1080 Simultaneous Multi Projection (2) NVIDIA GeForce GTX 1080 Simultaneous Multi Projection

Asynchronous Computing

NVIDIA GeForce GTX 1080 Async Compute

NVIDIA GeForce GTX 1080 Pascal Dynamic Load Balancing


by WhyCry

Previous Post
NVIDIA GeForce GTX 1080 OpenCL performance leaked
  Next Post
NVIDIA GeForce GTX 1080 full presentation






Back to Top ↑