AMD Radeon Pro W6800X Duo vs NVIDIA GeForce GTX 960

Comparative analysis of AMD Radeon Pro W6800X Duo and NVIDIA GeForce GTX 960 videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory, Technologies. Benchmark videocards performance analysis: GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - T-Rex (Fps), Geekbench - OpenCL, PassMark - G3D Mark, PassMark - G2D Mark, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s), CompuBench 1.5 Desktop - T-Rex (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), 3DMark Fire Strike - Graphics Score.

AMD Radeon Pro W6800X Duo

NVIDIA GeForce GTX 960

Differences

Reasons to consider the AMD Radeon Pro W6800X Duo

Videocard is newer: launch date 6 year(s) 6 month(s) later
Around 60% higher core clock speed: 1800 MHz vs 1127 MHz
Around 68% higher boost clock speed: 1975 MHz vs 1178 MHz
6583.3x more texture fill rate: 474.0 GTexel/s vs 72 billion / sec
3.8x more pipelines: 3840 vs 1024
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 7 nm vs 28 nm
16x more maximum memory size: 32 GB vs 2 GB
285.7x more memory clock speed: 2000 MHz (16 Gbps effective) vs 7.0 GB/s
6.7x better performance in Geekbench - OpenCL: 125290 vs 18642

Specifications (specs)
Launch date	3 Aug 2021 vs 22 January 2015
Core clock speed	1800 MHz vs 1127 MHz
Boost clock speed	1975 MHz vs 1178 MHz
Texture fill rate	474.0 GTexel/s vs 72 billion / sec
Pipelines	3840 vs 1024
Manufacturing process technology	7 nm vs 28 nm
Maximum memory size	32 GB vs 2 GB
Memory clock speed	2000 MHz (16 Gbps effective) vs 7.0 GB/s
Benchmarks
Geekbench - OpenCL	125290 vs 18642

Reasons to consider the NVIDIA GeForce GTX 960

3.3x lower typical power consumption: 120 Watt vs 400 Watt
Around 32% better performance in GFXBench 4.0 - Manhattan (Frames): 3691 vs 2786
Around 32% better performance in GFXBench 4.0 - Manhattan (Fps): 3691 vs 2786
Around 49% better performance in GFXBench 4.0 - T-Rex (Frames): 3335 vs 2243
Around 49% better performance in GFXBench 4.0 - T-Rex (Fps): 3335 vs 2243

Specifications (specs)
Thermal Design Power (TDP)	120 Watt vs 400 Watt
Benchmarks
GFXBench 4.0 - Manhattan (Frames)	3691 vs 2786
GFXBench 4.0 - Manhattan (Fps)	3691 vs 2786
GFXBench 4.0 - T-Rex (Frames)	3335 vs 2243
GFXBench 4.0 - T-Rex (Fps)	3335 vs 2243

Compare benchmarks

GPU 1: AMD Radeon Pro W6800X Duo
GPU 2: NVIDIA GeForce GTX 960

GFXBench 4.0 - Manhattan (Frames)

GPU 1

GPU 2

2786

3691

GFXBench 4.0 - Manhattan (Fps)

GPU 1

GPU 2

2786

3691

GFXBench 4.0 - T-Rex (Frames)

GPU 1

GPU 2

2243

3335

GFXBench 4.0 - T-Rex (Fps)

GPU 1

GPU 2

2243

3335

Geekbench - OpenCL

GPU 1

GPU 2

125290

18642

Name	AMD Radeon Pro W6800X Duo	NVIDIA GeForce GTX 960
GFXBench 4.0 - Manhattan (Frames)	2786	3691
GFXBench 4.0 - Manhattan (Fps)	2786	3691
GFXBench 4.0 - T-Rex (Frames)	2243	3335
GFXBench 4.0 - T-Rex (Fps)	2243	3335
Geekbench - OpenCL	125290	18642
PassMark - G3D Mark		6080
PassMark - G2D Mark		673
CompuBench 1.5 Desktop - Face Detection (mPixels/s)		73.733
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)		792.44
CompuBench 1.5 Desktop - T-Rex (Frames/s)		4.888
CompuBench 1.5 Desktop - Video Composition (Frames/s)		35.338
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)		200.825
GFXBench 4.0 - Car Chase Offscreen (Frames)		7218
GFXBench 4.0 - Car Chase Offscreen (Fps)		7218
3DMark Fire Strike - Graphics Score		2284

Compare specifications (specs)

	AMD Radeon Pro W6800X Duo	NVIDIA GeForce GTX 960
Essentials
Architecture	RDNA 2.0	Maxwell 2.0
Code name	Navi 21	GM206
Launch date	3 Aug 2021	22 January 2015
Launch price (MSRP)	$4999	$199
Place in performance rating	503	504
Type	Workstation	Desktop
Price now		$229.99
Value for money (0-100)		34.63
Technical info
Boost clock speed	1975 MHz	1178 MHz
Compute units	60
Core clock speed	1800 MHz	1127 MHz
Manufacturing process technology	7 nm	28 nm
Peak Double Precision (FP64) Performance	948.0 GFLOPS (1:16)
Peak Half Precision (FP16) Performance	30.34 TFLOPS (2:1)
Peak Single Precision (FP32) Performance	15.17 TFLOPS
Pipelines	3840	1024
Pixel fill rate	189.6 GPixel/s
Texture fill rate	474.0 GTexel/s	72 billion / sec
Thermal Design Power (TDP)	400 Watt	120 Watt
Transistor count	26800 million	2,940 million
CUDA cores		1024
Floating-point performance		2,413 gflops
Video outputs and ports
Display Connectors	1x HDMI, 4x Thunderbolt	Dual Link DVI-I, HDMI 2.0, 3x DisplayPort 1.2, 1x DVI, 1x HDMI, 3x DisplayPort
Audio input for HDMI		Internal
HDCP
Maximum VGA resolution		2048x1536
Multi monitor support
Compatibility, dimensions and requirements
Interface	PCIe 4.0 x16	PCIe 3.0 x16
Length	267 mm (10.5 inches)	9.5" (24.1 cm)
Recommended system power (PSU)	800 Watt	400 Watt
Supplementary power connectors	None	1x 6-pins
Width	Quad-slot
Bus support		PCI Express 3.0
Height		4.376" (11.1 cm)
SLI options		2x
API support
DirectX	12.2	12.0 (12_1)
OpenCL	2.1
OpenGL	4.6	4.4
Shader Model	6.5
Vulkan
Memory
Maximum RAM amount	32 GB	2 GB
Memory bandwidth	512 GB/s	112 GB / s
Memory bus width	256 bit	128 Bit
Memory clock speed	2000 MHz (16 Gbps effective)	7.0 GB/s
Memory type	GDDR6	GDDR5
Shared memory		0
Technologies
CUDA
GameStream
GameWorks
GeForce ShadowPlay
GPU Boost