AMD Radeon Pro W6800 vs NVIDIA GeForce RTX 3090

Comparative analysis of AMD Radeon Pro W6800 and NVIDIA GeForce RTX 3090 videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory. Benchmark videocards performance analysis: PassMark - G2D Mark, PassMark - G3D Mark, GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - T-Rex (Fps), Geekbench - OpenCL, 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), 3DMark Fire Strike - Graphics Score.

AMD Radeon Pro W6800

NVIDIA GeForce RTX 3090

Differences

Reasons to consider the AMD Radeon Pro W6800

Videocard is newer: launch date 9 month(s) later
Around 49% higher core clock speed: 2075 MHz vs 1395 MHz
Around 48% higher boost clock speed: 2507 MHz vs 1695 MHz
Around 8% higher texture fill rate: 601.7 GTexel/s vs 556.0 GTexel/s
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 7 nm vs 8 nm
Around 33% higher maximum memory size: 32 GB vs 24 GB
Around 64% higher memory clock speed: 2000 MHz (16 Gbps effective) vs 1219 MHz (19.5 Gbps effective)

Specifications (specs)
Launch date	8 Jun 2021 vs 1 Sep 2020
Core clock speed	2075 MHz vs 1395 MHz
Boost clock speed	2507 MHz vs 1695 MHz
Texture fill rate	601.7 GTexel/s vs 556.0 GTexel/s
Manufacturing process technology	7 nm vs 8 nm
Maximum memory size	32 GB vs 24 GB
Memory clock speed	2000 MHz (16 Gbps effective) vs 1219 MHz (19.5 Gbps effective)
Benchmarks
GFXBench 4.0 - Manhattan (Frames)	3717 vs 3713
GFXBench 4.0 - Manhattan (Fps)	3717 vs 3713
GFXBench 4.0 - T-Rex (Frames)	3357 vs 3354
GFXBench 4.0 - T-Rex (Fps)	3357 vs 3354

Reasons to consider the NVIDIA GeForce RTX 3090

2.7x more pipelines: 10496 vs 3840
Around 29% lower typical power consumption: 350 Watt vs 450 Watt
Around 13% better performance in PassMark - G2D Mark: 1051 vs 934
Around 35% better performance in PassMark - G3D Mark: 26818 vs 19919
Around 59% better performance in GFXBench 4.0 - Car Chase Offscreen (Frames): 33398 vs 20988
Around 59% better performance in GFXBench 4.0 - Car Chase Offscreen (Fps): 33398 vs 20988
Around 43% better performance in Geekbench - OpenCL: 188320 vs 131707

Specifications (specs)
Pipelines	10496 vs 3840
Thermal Design Power (TDP)	350 Watt vs 450 Watt
Benchmarks
PassMark - G2D Mark	1051 vs 934
PassMark - G3D Mark	26818 vs 19919
GFXBench 4.0 - Car Chase Offscreen (Frames)	33398 vs 20988
GFXBench 4.0 - Car Chase Offscreen (Fps)	33398 vs 20988
Geekbench - OpenCL	188320 vs 131707

Compare benchmarks

GPU 1: AMD Radeon Pro W6800
GPU 2: NVIDIA GeForce RTX 3090

PassMark - G2D Mark

GPU 1

GPU 2

934

1051

PassMark - G3D Mark

GPU 1

GPU 2

19919

26818

GFXBench 4.0 - Car Chase Offscreen (Frames)

GPU 1

GPU 2

20988

33398

GFXBench 4.0 - Car Chase Offscreen (Fps)

GPU 1

GPU 2

20988

33398

GFXBench 4.0 - Manhattan (Frames)

GPU 1

GPU 2

3717

3713

GFXBench 4.0 - Manhattan (Fps)

GPU 1

GPU 2

3717

3713

GFXBench 4.0 - T-Rex (Frames)

GPU 1

GPU 2

3357

3354

GFXBench 4.0 - T-Rex (Fps)

GPU 1

GPU 2

3357

3354

Geekbench - OpenCL

GPU 1

GPU 2

131707

188320

Name	AMD Radeon Pro W6800	NVIDIA GeForce RTX 3090
PassMark - G2D Mark	934	1051
PassMark - G3D Mark	19919	26818
GFXBench 4.0 - Car Chase Offscreen (Frames)	20988	33398
GFXBench 4.0 - Car Chase Offscreen (Fps)	20988	33398
GFXBench 4.0 - Manhattan (Frames)	3717	3713
GFXBench 4.0 - Manhattan (Fps)	3717	3713
GFXBench 4.0 - T-Rex (Frames)	3357	3354
GFXBench 4.0 - T-Rex (Fps)	3357	3354
Geekbench - OpenCL	131707	188320
CompuBench 1.5 Desktop - Face Detection (mPixels/s)		732.196
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)		7585.258
CompuBench 1.5 Desktop - T-Rex (Frames/s)		63.011
CompuBench 1.5 Desktop - Video Composition (Frames/s)		247.569
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)		2441.384
3DMark Fire Strike - Graphics Score		19875

Compare specifications (specs)

	AMD Radeon Pro W6800	NVIDIA GeForce RTX 3090
Essentials
Architecture	RDNA 2.0	Ampere
Code name	Navi 21	GA102
Launch date	8 Jun 2021	1 Sep 2020
Launch price (MSRP)	$2249	$1499
Place in performance rating	108	40
Type		Desktop
Technical info
Boost clock speed	2507 MHz	1695 MHz
Compute units	60
Core clock speed	2075 MHz	1395 MHz
Manufacturing process technology	7 nm	8 nm
Peak Double Precision (FP64) Performance	1203 GFLOPS (1:16)	556.0 GFLOPS (1:64)
Peak Half Precision (FP16) Performance	38.51 TFLOPS (2:1)	35.58 TFLOPS (1:1)
Peak Single Precision (FP32) Performance	19.25 TFLOPS	35.58 TFLOPS
Pipelines	3840	10496
Pixel fill rate	240.7 GPixel/s	189.8 GPixel/s
Texture fill rate	601.7 GTexel/s	556.0 GTexel/s
Thermal Design Power (TDP)	450 Watt	350 Watt
Transistor count	26800 million	28300 million
Video outputs and ports
Display Connectors	6x mini-DisplayPort	1x HDMI, 3x DisplayPort
Compatibility, dimensions and requirements
Form factor	Dual-slot
Height	50 mm (2 inches)	138 mm (5.4 inches)
Interface	PCIe 4.0 x16	PCIe 4.0 x16
Length	267 mm (10.5 inches)	313 mm (12.3 inches)
Recommended system power (PSU)	850 Watt	750 Watt
Supplementary power connectors	2x 8-pin	1x 12-pin
Width	120 mm (4.7 inches)	Triple-slot
API support
DirectX	12.2	12.2
OpenCL	2.1	2.0
OpenGL	4.6	4.6
Shader Model	6.5	6.5
Vulkan
Memory
Maximum RAM amount	32 GB	24 GB
Memory bandwidth	512 GB/s	936.2 GB/s
Memory bus width	256 bit	384 bit
Memory clock speed	2000 MHz (16 Gbps effective)	1219 MHz (19.5 Gbps effective)
Memory type	GDDR6	GDDR6X