AMD Radeon RX 580 vs NVIDIA GeForce GTX 970

Comparative analysis of AMD Radeon RX 580 and NVIDIA GeForce GTX 970 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: PassMark - G3D Mark, PassMark - G2D Mark, 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), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps), 3DMark Fire Strike - Graphics Score.

AMD Radeon RX 580

NVIDIA GeForce GTX 970

Differences

Reasons to consider the AMD Radeon RX 580

Videocard is newer: launch date 2 year(s) 6 month(s) later
Around 20% higher core clock speed: 1257 MHz vs 1050 MHz
Around 14% higher boost clock speed: 1340 MHz vs 1178 MHz
1770.3x more texture fill rate: 192.96 GTexel/s vs 109 billion / sec
Around 38% higher pipelines: 2304 vs 1664
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 14 nm vs 28 nm
2x more maximum memory size: 8 GB vs 4 GB
1142.9x more memory clock speed: 8000 MHz vs 7.0 GB/s
Around 37% better performance in Geekbench - OpenCL: 39028 vs 28498
Around 10% better performance in CompuBench 1.5 Desktop - Face Detection (mPixels/s): 116.142 vs 105.107
Around 6% better performance in CompuBench 1.5 Desktop - T-Rex (Frames/s): 9.235 vs 8.737
2.4x better performance in CompuBench 1.5 Desktop - Video Composition (Frames/s): 84.034 vs 35.714
Around 24% better performance in CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s): 607.721 vs 490.688
2.7x better performance in 3DMark Fire Strike - Graphics Score: 1005 vs 369

Specifications (specs)
Launch date	18 April 2017 vs 19 September 2014
Core clock speed	1257 MHz vs 1050 MHz
Boost clock speed	1340 MHz vs 1178 MHz
Texture fill rate	192.96 GTexel/s vs 109 billion / sec
Pipelines	2304 vs 1664
Manufacturing process technology	14 nm vs 28 nm
Maximum memory size	8 GB vs 4 GB
Memory clock speed	8000 MHz vs 7.0 GB/s
Benchmarks
PassMark - G2D Mark	767 vs 766
Geekbench - OpenCL	39028 vs 28498
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	116.142 vs 105.107
CompuBench 1.5 Desktop - T-Rex (Frames/s)	9.235 vs 8.737
CompuBench 1.5 Desktop - Video Composition (Frames/s)	84.034 vs 35.714
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	607.721 vs 490.688
GFXBench 4.0 - T-Rex (Frames)	3349 vs 3340
GFXBench 4.0 - T-Rex (Fps)	3349 vs 3340
3DMark Fire Strike - Graphics Score	1005 vs 369

Reasons to consider the NVIDIA GeForce GTX 970

632.3x better floating-point performance: 3,920 gflops vs 6.2 TFLOPs
Around 25% lower typical power consumption: 148 Watt vs 185 Watt
Around 9% better performance in PassMark - G3D Mark: 9640 vs 8827
Around 20% better performance in CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s): 1225.96 vs 1022.932
Around 2% better performance in GFXBench 4.0 - Car Chase Offscreen (Frames): 11499 vs 11281
Around 2% better performance in GFXBench 4.0 - Car Chase Offscreen (Fps): 11499 vs 11281

Specifications (specs)
Floating-point performance	3,920 gflops vs 6.2 TFLOPs
Thermal Design Power (TDP)	148 Watt vs 185 Watt
Benchmarks
PassMark - G3D Mark	9640 vs 8827
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1225.96 vs 1022.932
GFXBench 4.0 - Car Chase Offscreen (Frames)	11499 vs 11281
GFXBench 4.0 - Manhattan (Frames)	3698 vs 3695
GFXBench 4.0 - Car Chase Offscreen (Fps)	11499 vs 11281
GFXBench 4.0 - Manhattan (Fps)	3698 vs 3695

Compare benchmarks

GPU 1: AMD Radeon RX 580
GPU 2: NVIDIA GeForce GTX 970

PassMark - G3D Mark

GPU 1

GPU 2

8827

9640

PassMark - G2D Mark

GPU 1

GPU 2

767

766

Geekbench - OpenCL

GPU 1

GPU 2

39028

28498

CompuBench 1.5 Desktop - Face Detection (mPixels/s)

GPU 1

GPU 2

116.142

105.107

CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)

GPU 1

GPU 2

1022.932

1225.96

CompuBench 1.5 Desktop - T-Rex (Frames/s)

GPU 1

GPU 2

9.235

8.737

CompuBench 1.5 Desktop - Video Composition (Frames/s)

GPU 1

GPU 2

84.034

35.714

CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)

GPU 1

GPU 2

607.721

490.688

GFXBench 4.0 - Car Chase Offscreen (Frames)

GPU 1

GPU 2

11281

11499

GFXBench 4.0 - Manhattan (Frames)

GPU 1

GPU 2

3695

3698

GFXBench 4.0 - T-Rex (Frames)

GPU 1

GPU 2

3349

3340

GFXBench 4.0 - Car Chase Offscreen (Fps)

GPU 1

GPU 2

11281

11499

GFXBench 4.0 - Manhattan (Fps)

GPU 1

GPU 2

3695

3698

GFXBench 4.0 - T-Rex (Fps)

GPU 1

GPU 2

3349

3340

3DMark Fire Strike - Graphics Score

GPU 1

GPU 2

1005

369

Name	AMD Radeon RX 580	NVIDIA GeForce GTX 970
PassMark - G3D Mark	8827	9640
PassMark - G2D Mark	767	766
Geekbench - OpenCL	39028	28498
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	116.142	105.107
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	1022.932	1225.96
CompuBench 1.5 Desktop - T-Rex (Frames/s)	9.235	8.737
CompuBench 1.5 Desktop - Video Composition (Frames/s)	84.034	35.714
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	607.721	490.688
GFXBench 4.0 - Car Chase Offscreen (Frames)	11281	11499
GFXBench 4.0 - Manhattan (Frames)	3695	3698
GFXBench 4.0 - T-Rex (Frames)	3349	3340
GFXBench 4.0 - Car Chase Offscreen (Fps)	11281	11499
GFXBench 4.0 - Manhattan (Fps)	3695	3698
GFXBench 4.0 - T-Rex (Fps)	3349	3340
3DMark Fire Strike - Graphics Score	1005	369

Compare specifications (specs)

	AMD Radeon RX 580	NVIDIA GeForce GTX 970
Essentials
Architecture	GCN 4.0	Maxwell 2.0
Code name	Polaris 20	GM204
Design	Radeon RX 500 Series
GCN generation	4th Gen
Launch date	18 April 2017	19 September 2014
Launch price (MSRP)	$229	$329
Place in performance rating	341	371
Price now	$169.99	$407.76
Type	Desktop	Desktop
Value for money (0-100)	76.21	28.59
Technical info
Boost clock speed	1340 MHz	1178 MHz
Compute units	36
Core clock speed	1257 MHz	1050 MHz
Floating-point performance	6.2 TFLOPs	3,920 gflops
Manufacturing process technology	14 nm	28 nm
Pipelines	2304	1664
Pixel fill rate	42.88 GP/s
Render output units	32
Stream Processors	2304
Texture fill rate	192.96 GTexel/s	109 billion / sec
Texture Units	144
Thermal Design Power (TDP)	185 Watt	148 Watt
Transistor count	5,700 million	5,200 million
CUDA cores		1664
Maximum GPU temperature		98 °C
Video outputs and ports
Display Connectors	1x HDMI, 3x DisplayPort	1x DVI, 1x HDMI, 3x DisplayPort, Dual Link DVI-I, HDMI 2.0, 3x DisplayPort 1.2
DisplayPort support
Dual-link DVI support
HDMI
VGA
Audio input for HDMI		Internal
G-SYNC support
HDCP
Maximum VGA resolution		2048x1536
Multi monitor support
Compatibility, dimensions and requirements
Bridgeless CrossFire
Interface	PCIe 3.0 x16	PCIe 3.0 x16
Length	241 mm	10.5" (26.7 cm)
Recommended system power (PSU)	500 Watt	500 Watt
Supplementary power connectors	1x 8-pin	2x 6-pins
Bus support		PCI Express 3.0
Height		4.376" (11.1 cm)
SLI options		4x
API support
DirectX	12	12.0 (12_1)
OpenCL	2.0
OpenGL	4.5	4.4
Vulkan
Memory
Maximum RAM amount	8 GB	4 GB
Memory bandwidth	256 GB/s	224 GB / s
Memory bus width	256 bit	256 Bit
Memory clock speed	8000 MHz	7.0 GB/s
Memory type	GDDR5	GDDR5
Shared memory		0
Technologies
4K H264 Decode
4K H264 Encode
AMD Eyefinity
AMD Radeon™ Chill
AMD Radeon™ ReLive
AppAcceleration
CrossFire
FreeSync
H265/HEVC Decode
H265/HEVC Encode
HDMI 4K Support
LiquidVR
PowerTune
TrueAudio
Unified Video Decoder (UVD)
Video Code Engine (VCE)
Virtual Super Resolution (VSR)
VR Ready
3D Vision
Adaptive Vertical Sync
CUDA
GameStream
GameWorks
GeForce Experience
GeForce ShadowPlay
GPU Boost
SLI
Surround