CMP 40HX vs Tesla K80

Place in the ranking	358	264
Place by popularity	not in top-100	not in top-100
Cost-effectiveness evaluation	no data	26.69
Power efficiency	3.48	8.01
Architecture	Kepler 2.0 (2013−2015)	Turing (2018−2022)
GPU code name	GK210	TU106
Market segment	Workstation	Workstation
Release date	17 November 2014 (10 years ago)	25 February 2021 (3 years ago)
Launch price (MSRP)	no data	$699

Cost-effectiveness evaluation

The higher the performance-to-price ratio, the better. We use the manufacturer's recommended prices for comparison.

no data

Detailed specifications

General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.

Pipelines / CUDA cores	2496 ×2	2304
Core clock speed	562 MHz	1470 MHz
Boost clock speed	824 MHz	1650 MHz
Number of transistors	7,100 million	10,800 million
Manufacturing process technology	28 nm	12 nm
Power consumption (TDP)	300 Watt	185 Watt
Texture fill rate	171.4 ×2	237.6
Floating-point processing power	4.113 TFLOPS ×2	7.603 TFLOPS
ROPs	48 ×2	64
TMUs	208 ×2	144
Tensor Cores	no data	288
Ray Tracing Cores	no data	36

Form factor & compatibility

Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

Interface	PCIe 3.0 x16	PCIe 3.0 x16
Length	267 mm	229 mm
Width	2-slot	2-slot
Supplementary power connectors	1x 8-pin	1x 8-pin

VRAM capacity and type

Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.

Memory type	GDDR5	GDDR6
Maximum RAM amount	12 GB ×2	8 GB
Memory bus width	384 Bit ×2	256 Bit
Memory clock speed	1253 MHz	1750 MHz
Memory bandwidth	240.6 GB/s ×2	448.0 GB/s

Connectivity and outputs

Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.

Display Connectors

No outputs

API and SDK compatibility

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectX	12 (11_1)	12 Ultimate (12_2)
Shader Model	5.1	6.6
OpenGL	4.6	4.6
OpenCL	1.2	3.0
Vulkan	1.1.126	1.2
CUDA	3.7	7.5
DLSS	-	+

Synthetic benchmark performance

Non-gaming benchmark results comparison. The combined score is measured on a 0-100 point scale.

Combined synthetic benchmark score

This is our combined benchmark score.

Tesla K80 14.87

CMP 40HX 21.10
+41.9%

Passmark

This is the most ubiquitous GPU benchmark. It gives the graphics card a thorough evaluation under various types of load, providing four separate benchmarks for Direct3D versions 9, 10, 11 and 12 (the last being done in 4K resolution if possible), and few more tests engaging DirectCompute capabilities.

Tesla K80 5852

CMP 40HX 8301
+41.8%

Gaming performance

Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.

Pros & cons summary

Performance score	14.87	21.10
Recency	17 November 2014	25 February 2021
Maximum RAM amount	12 GB	8 GB
Chip lithography	28 nm	12 nm
Power consumption (TDP)	300 Watt	185 Watt

Tesla K80 has a 50% higher maximum VRAM amount.

CMP 40HX, on the other hand, has a 41.9% higher aggregate performance score, an age advantage of 6 years, a 133.3% more advanced lithography process, and 62.2% lower power consumption.

The CMP 40HX is our recommended choice as it beats the Tesla K80 in performance tests.