FP32 IS THE ONLY PRECISION ROW. NVIDIA prints 8873 GFLOPs for this card in its own GP104 whitepaper, footnoted "based on GPU Boost Clock", and prints nothing else: no FP16, no FP64, no INT8, on any page of that document, on the product page, or in the launch press release. The catalog's two existing Pascal GeForce rows, GeForce GTX 1080 Ti and TITAN Xp, carry FP32 alone for exactly this reason, and the Turing whitepaper's GTX 1080 Ti comparison column goes further and marks the non-Tensor FP16 row NA. The CUDA C++ Programming Guide does give compute capability 6.1 a 1/64 half-precision and 1/32 double-precision ratio, but that is an architectural rate rather than a specification of this card, and applying it here while the sibling rows have nothing would answer the same question two ways. See the header of this migration. REFUSED: FP16, FP64, INT8, and the card dimensions, which the whitepaper does not print.

NVIDIA GeForce GTX 1080 8GB

Pascal PCIe 2016 16nm Spec confidence: Official
FP32
8.9
TFLOPS
Memory
8 GB
GDDR5X
Bandwidth
320 GB/s
memory
TDP
180 W
49.3 FP32 dense TFLOPS/kW of TDP
Download datasheet

Overview

The GeForce GTX 1080 is the card that defined the Pascal generation, and it is in this database as the mainstream reference point below the GTX 1080 Ti: 2,560 CUDA cores across 20 SMs at a 1,733 MHz boost for 8.87 TFLOPS FP32, with 8 GB of GDDR5X, the first memory of its kind to ship, running at 10 Gbps on a 256-bit bus for 320 GB/s, all inside 180 W. Against a modern accelerator the arithmetic is not the interesting number; the absence is. There are no Tensor Cores here, no structured sparsity, and no usable half-precision path at all, which is why NVIDIA published a single-precision figure for this card and nothing else. Anything that runs in FP16 or INT8 on a later card runs in FP32 here, at 8.87 TFLOPS, and the 8 GB frame buffer decides what fits before the throughput ever does.

Performance

Peak theoretical throughput by precision type

PrecisionPeak
FP64
No verified data available
FP32
32-bit floating point
8.9TFLOPS
TF32
No verified data available
BF16
No verified data available
FP16
No verified data available
FP8
No verified data available
FP6
No verified data available
FP4
No verified data available
INT8
No verified data available

Every figure here is dense. The vendor documents no structured (2:4) sparsity mode for this part, so there is no second number to quote.

Specifications

Architecture

Pascal

Form Factor

PCIe

Launch Year

2016

Process Node

16nm

Memory

8 GB GDDR5X

Bandwidth

320 GB/s

TDP

180 W

Max power

180 W

Transistors

7.2 billion

CUDA Cores

2,560

Spec Confidence

Official

Full Specifications

Compute Engine
CUDA Cores 2,560
Streaming Multiprocessors 20
Base Clock 1.61 GHz
Boost Clock 1.73 GHz
Chip Design
Transistors 7.2 billion
Die Size 314 mm²
Process Node 16nm
Memory
Memory 8 GB
Memory Type GDDR5X
Bandwidth 320 GB/s
Interface Width 256-bit
Memory Clock 10 GT/s
Interconnect & I/O
PCIe 3.0 x16
Cache
L2 Cache 2 MB
Power & Thermal
TDP 180 W
Max power 180 W
Power Connector 8-pin
Cooling Active
Enterprise Features
ECC Memory No
Sparsity No
Compute APIs CUDA, DirectX 12, Vulkan, OpenGL
Physical & Media
Width 2-slot
General
Form Factor PCIe
Architecture Pascal
Process Node 16nm
Launch Year 2016

Datasheet & Resources

Data Provenance

Every figure traced to a source

Primary Source

Publisher
NVIDIA
Published
No verified data available

Data Quality

Spec confidence
Official
Clock basis
Boost
Core precisions with figures
1 of 9
Normalization
All values in TFLOPS

Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.

Browse GPU Cloud Providers

Similar GPUs

NVIDIA Titan Xp 12GB

PCIe · 2017
FP32: 12 TFLOPS
Compare vs Titan Xp

NVIDIA Tesla P40 24GB

PCIe · 2016
FP32: 12 TFLOPS
Compare vs Tesla P40

NVIDIA P100 SXM2 16GB

SXM · 2016
FP32: 11 TFLOPS
Compare vs P100

NVIDIA P100 PCIe 16GB

PCIe · 2016
FP32: 9.3 TFLOPS
Compare vs P100

Frequently Asked Questions

How many TFLOPS does the NVIDIA GeForce GTX 1080 have?

The NVIDIA GeForce GTX 1080 delivers 8.9 TFLOPS FP32 at peak. Flopper does not currently have verified FP16 and FP8 throughput figures for it.

What is the power consumption of the NVIDIA GeForce GTX 1080?

The NVIDIA GeForce GTX 1080 has a TDP (Thermal Design Power) rating of 180 watts.

How much memory does the NVIDIA GeForce GTX 1080 have?

The NVIDIA GeForce GTX 1080 is equipped with 8 GB of memory with 320 GB/s of memory bandwidth.

What architecture is the NVIDIA GeForce GTX 1080 based on?

The NVIDIA GeForce GTX 1080 is based on the Pascal architecture, launched in 2016.

Stay Updated on GPU Releases

Get notified when new GPUs are added or specifications are updated.

Loading verification...

No spam, unsubscribe anytime.

Back to GPUs