Amd 590 vs 1070: RX 590 vs GTX 1070 Game Performance Benchmarks (i7-8700K vs i7-6700K)

GeForce GTX 1070 GDDR5X vs Radeon RX 590 : Which one is better?

Home

GPU Comparison

NVIDIA GeForce GTX 1070 GDDR5X vs AMD Radeon RX 590

VS

NVIDIA GeForce GTX 1070 GDDR5X
AMD Radeon RX 590

We compared two Desktop platform GPUs: 8GB VRAM GeForce GTX 1070 GDDR5X and 8GB VRAM Radeon RX 590 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA GeForce GTX 1070 GDDR5X’s Advantages

Boost Clock has increased by 9% (1683MHz vs 1545MHz)

Larger VRAM bandwidth (256.3GB/s vs 256.0GB/s)

Lower TDP (150W vs 175W)

AMD Radeon RX 590’s Advantages

384 additional rendering cores

Benchmark

FP16 (half)

GeForce GTX 1070 GDDR5X

0. 101 TFLOPS

Radeon RX 590
+6948%

7.119 TFLOPS

FP32 (float)

GeForce GTX 1070 GDDR5X

6.463 TFLOPS

Radeon RX 590
+10%

7.119 TFLOPS

FP64 (double)

GeForce GTX 1070 GDDR5X

0.202 TFLOPS

Radeon RX 590
+120%

0.445 TFLOPS

GeForce GTX 1070 GDDR5X

VS

Radeon RX 590

Graphics Processor

GP104

GPU Name

Polaris 30

GP104-200-A1

GPU Variant

Polaris 30 XT
(215-0922006)

Pascal

Architecture

GCN 4. 0

TSMC

Foundry

GlobalFoundries

16 nm

Process Size

12 nm

7,200 million

Transistors

5,700 million

314mm²

Die Size

232mm²

Graphics Card

Dec 2018

Release Date

Nov 2018

GeForce 10

Generation

Polaris

Desktop

Type

Desktop

PCIe 3. 0 x16

Bus Interface

PCIe 3.0 x16

Clock Speeds

1506MHz

Base Clock

1469MHz

1683MHz

Boost Clock

1545MHz

1001MHz

Memory Clock

2000MHz

Memory

8GB

Memory Size

8GB

GDDR5X

Memory Type

GDDR5

256bit

Memory Bus

256bit

256. 3 GB/s

Bandwidth

256.0 GB/s

Render Config

1920

Shading Units

2304

120

144

15

SM Count

-

-

Tensor Cores

-

-

RT Cores

-

48 KB (per SM)

L1 Cache

16 KB (per CU)

2MB

L2 Cache

2MB

Theoretical Performance

107. 7 GPixel/s

Pixel Rate

49.44 GPixel/s

202.0 GTexel/s

Texture Rate

222.5 GTexel/s

101.0 GFLOPS

FP16 (half)

7.119 TFLOPS

6.463 TFLOPS

FP32 (float)

7.119 TFLOPS

202.0 GFLOPS

FP64 (double)

445. 0 GFLOPS

Board Design

150W

TDP

175W

450W

Suggested PSU

450W

1x DVI
1x HDMI 2.0
3x DisplayPort 1.4a

Outputs

1x HDMI 2.0b
3x DisplayPort 1.4a

1x 8-pin

Power Connectors

1x 8-pin

Graphics Features

12 (12_1)

DirectX

12 (12_0)

4. 6

OpenGL

4.6

3.0

OpenCL

2.1

1.3

Vulkan

1.2

6.1

CUDA

-

6.4

Shader Model

6.4

Related GPU Comparisons

1

AMD Radeon RX 7600 XT vs
NVIDIA GeForce GTX 1070 GDDR5X

2

NVIDIA GeForce RTX 4060 Ti vs
NVIDIA GeForce GTX 1070 GDDR5X

3

NVIDIA GeForce GTX 1070 GDDR5X vs
AMD Radeon RX 7600

4

NVIDIA GeForce RTX 4070 vs
NVIDIA GeForce GTX 1070 GDDR5X

5

NVIDIA GeForce GTX 1660 SUPER vs
NVIDIA GeForce GTX 1070 GDDR5X

6

NVIDIA GeForce RTX 4060 Ti 8 GB vs
NVIDIA GeForce GTX 1070 GDDR5X

7

NVIDIA GeForce RTX 4060 vs
NVIDIA GeForce GTX 1070 GDDR5X

8

NVIDIA GeForce GTX 1070 GDDR5X vs
AMD FirePro W8100

9

NVIDIA GeForce GTX 1070 GDDR5X vs
NVIDIA GeForce 605 OEM

10

NVIDIA GeForce GTX 1070 GDDR5X vs
AMD Radeon RX 570

© 2023 — TopCPU. net  

Contact Us

Comparison AMD Radeon RX 590 vs NVIDIA GeForce GTX 1070 what is better?

General information
Price-quality ratio The sum of all the advantages of the device divided by its price. The higher the%, the better the quality per unit price in comparison with all analogues.
55.8 % 11.9 % (27.1%) better	43.9 %
Architecture
GCN 4.0	Pascal
Code name
Polaris 30	GP104
Type
Десктопная	Десктопная
Start price
279 USD -100 USD (-26.4%) better	379 USD
Number of shader processors
2304 384 (20%) better	1920
Core Frequency
1469 MGz	1506 MGz 37 MGz (2. 5%) better
Frequency in Boost mode
1545 MGz	1683 MGz 138 MGz (8.9%) better
Number of transistors
5,700 млн	7,200 млн
Technological process
12 nm -4 nm (-25%) better	16 nm
Interface
PCIe 3.0 x16	PCIe 3.0 x16
Power Consumption (TDP) The calculated heat output shows the average heat output in operation under load, the larger the value — the more the requirements for cooling and energy consumption increase.
175 Wt	150 Wt -25 Wt (-14. 3%) better
Length
241 мм	26.7 см
Additional power connectors
1x 8-pin	8-pin
G-SYNC Support NVIDIA G-SYNC technology provides a smooth gaming experience with variable refresh rates and elimination of visual artifacts.
Multi Monitor
no data	+
SLI support
no data	+
3D Vision
no data	+
GPU Boost
no data	3.0
VR Ready Technology from NVIDIA that gives manufacturers access to Multi res Shading, Context Priority and GPU Direct virtual reality technologies.
no data	+
Vulkan NVIDIA’s Vulkan technology allows developers to gain low-level GPU access to optimize graphics instructions (better than OpenGL and Direct3D APIs). It is an open, free, cross-platform standard available for all platforms.
no data	+
CUDA The presence of the CUDA architecture allows you to use applications that are optimized for parallel computing. For example, for the development and design of neural networks.
Multi-Projection NVIDIA Multi-Projection technology improves graphics performance when building virtual worlds. Images for the left and right eyes are rendered simultaneously.
no data	+
maximum temperature
no data	94 °C
Recommended power supply
no data	500 Ватт
Multi-monitor support
no data	1
Ansel
Virtual Reality
no data	+
Decred / DCR (Decred)
no data	2. 83 Gh/s
Siacoin / SC (Sia)
no data	1.75 Gh/s
Zcash / ZEC (Equihash)
no data	1 Sol/s
Bus
no data	PCIe 3.0
ShadowWorks
no data	+
Thickness
no data	2 слота
Number of CUDA cores A large number of CUDA cores increase performance in graphics computing, especially affecting anti-aliasing and lighting in games, and the speed of training neural networks.
no data	1920
Height
no data	11. 1 см
FreeSync
+	no data
DisplayPort 1.3 HBR / 1.4 HDR Ready
+	no data
Video connectors
1x HDMI, 3x DisplayPort	DP 1.42, HDMI 2.0b, Dual Link-DVI
DirectX
12 (12_0)	12 (12_1)
Floating-point performance
no data	6,463 gflops
Ethereum / ETH (DaggerHashimoto)
no data	28.69 Mh/s

Memory
Memory type
GDDR5	GDDR5
Maximum RAM amount Large amount of video memory allows you to run demanding games with a lot of textures, use high-resolution monitors, provide more opportunities for cryptocurrency mining.
8	8
Memory bus width The wider the video memory bus width, the more data is transferred to the GPU per unit of time and the better the performance in demanding games.
256 bit	256 bit
Shared memory
—	—
Memory clock speed A high memory frequency has a positive effect on the speed of a video card with a large amount of data.
8000 MGz 7992 MGz (99900%) better	8 MGz
Memory Bandwidth The higher the data transfer bandwidth, the more effective RAM your PC can use.
256	256

Comparison of AMD Radeon RX 590 and NVIDIA GeForce GTX 1070 (Desktop)

Comparative analysis of AMD Radeon RX 590 and NVIDIA GeForce GTX 1070 (Desktop) video cards by all known characteristics in the categories: General information, Specifications, Video outputs and ports, Compatibility, dimensions, requirements, API support, Memory, Technology support.
Analysis of video card performance by benchmarks: 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 590

versus

NVIDIA GeForce GTX 1070 (Desktop)

Benefits

Reasons to choose AMD Radeon RX 590

• Newer graphics card, release date difference 2 year(s) 5 month(s) )
• 1101.4 times texturing speed (a) more: 222.48 GTexel / s vs 202. 0 GTexel / s
• A newer manufacturing process for the video card allows it to be more powerful, but with lower power consumption: 12 nm vs 16 nm
• 1000 times faster memory speed: 8000 MHz vs 8 GB/s
• About 17% faster performance in Geekbench — OpenCL benchmark: 47222 vs 40527
• Performance in CompuBench 1.5 Desktop — Ocean Surface Simulation benchmark (Frames /s) about 21% more: 2083.862 vs 1718.593
• Performance in CompuBench 1.5 Desktop — T-Rex (Frames/s) about 1% more: 12.353 vs 12.283
• Performance in CompuBench 1.5 Desktop — Video Composition ( Frames/s) in 4.9times(es) more: 139.477 vs 28.289
• About 7% more performance in CompuBench 1.5 Desktop — Bitcoin Mining (mHash/s): 762.142 vs 710.366
• Performance in GFXBench 4.0 — Manhattan (Frame) benchmark s) about 1% more: 3716 vs 3691
• About 1% more performance in GFXBench 4.0 — T-Rex (Frames) benchmark: 3359 vs 3340
• About 1% more performance in GFXBench 4. 0 — Manhattan (Fps) benchmark: 3716 vs 36 91
• Performance in GFXBench 4.0 — T-Rex (Fps) about 1% higher: 3359 vs 3340

Release date	15 November 2018 vs 10 June 2016
Texturing speed	222.48 GTexel/s vs 202.0 GTexel/s
Process	12 nm vs 16 nm
Memory frequency	8000 MHz vs 8 GB/s
Geekbench — OpenCL	47222 vs 40527
CompuBench 1.5 Desktop — Ocean Surface Simulation (Frames/s)	2083.862 vs 1718.593
CompuBench 1.5 Desktop — T-Rex (Frames/s)	12. 353 vs 12.283
CompuBench 1.5 Desktop — Video Composition (Frames/s)	139.477 vs 28.289
CompuBench 1.5 Desktop — Bitcoin Mining (mHash/s)	762.142 vs 710.366
GFXBench 4.0 — Manhattan (Frames)	3716 vs 3691
GFXBench 4.0 — T-Rex (Frames)	3359 vs 3340
GFXBench 4.0 — Manhattan (Fps)	3716 vs 3691
GFXBench 4.0 — T-Rex (Fps)	3359 vs 3340

Reasons to choose NVIDIA GeForce GTX 1070 (Desktop)

• About 3% faster core clock: 1506 MHz vs 1469 MHz
• Boost core clock 9% faster: 1683 MHz vs 1545 MHz
• Performance with 910. 3x more floating point: 6,463 gflops vs 7.1 TFLOPs
• About 17% less power consumption: 150 Watt vs 175 Watt
• About 41% more performance in PassMark — G3D Mark benchmark: 13510 vs 9554
• Approximately 6% increase in PassMark — G2D Mark benchmark: 857 vs 805
• Approximately 10% increase in CompuBench 1.5 Desktop — Face Detection (mPixels/s) performance: 150.951 vs 137.469

9 0019 GFXBench performance 4.0 — Car Chase Offscreen (Frames) about 3% more: 13765 vs 13383

• GFXBench 4.0 performance — Car Chase Offscreen (Fps) about 3% more: 13765 vs 13383
• 3DMark Fire Strike — Graphics Score performance about 27% better: 6050 vs 4765

Core clock	1506 MHz vs 1469 MHz
Boost core clock	1683 MHz vs 1545 MHz
Floating point performance	6. 463 gflops vs 7.1 TFLOPs
Power consumption (TDP)	150 Watt vs 175 Watt
PassMark — G3D Mark	13510 vs 9554
PassMark — G2D Mark	857 vs 805
CompuBench 1.5 Desktop — Face Detection (mPixels/s)	150.951 vs 137.469
GFXBench 4.0 — Car Chase Offscreen (Frames)	13765 vs 13383
GFXBench 4.0 — Car Chase Offscreen (Fps)	13765 vs 13383
3DMark Fire Strike — Graphics Score	6050 vs 4765

Benchmark comparison

GPU 1: AMD Radeon RX 590
GPU 2: NVIDIA GeForce GTX 1070 (Desktop)

PassMark — G3D Mark	GPU 1 GPU 2
PassMark — G2D Mark	GPU 1 GPU 2
Geekbench — OpenCL	GPU 1 GPU 2
CompuBench 1. 5 Desktop — Face Detection (mPixels/s)	GPU 1 GPU 2	137.469 150.951
CompuBench 1.5 Desktop — Ocean Surface Simulation (Frames/s)	GPU 1 GPU 2	2083.862 1718.593
CompuBench 1.5 Desktop — T-Rex (Frames/s)	GPU 1 GPU 2	12. 353 12.283
CompuBench 1.5 Desktop — Video Composition (Frames/s)	GPU 1 GPU 2	139.477 28.289
CompuBench 1.5 Desktop — Bitcoin Mining (mHash/s)	GPU 1 GPU 2	762.142 710. 366
GFXBench 4.0 — Car Chase Offscreen (Frames)	GPU 1 GPU 2
GFXBench 4.0 — Manhattan (Frames)	GPU 1 GPU 2
GFXBench 4.0 — T-Rex (Frames)	GPU 1 GPU 2
GFXBench 4. 0 — Car Chase Offscreen (Fps)	GPU 1 GPU 2
GFXBench 4.0 — Manhattan (Fps)	GPU 1 GPU 2
GFXBench 4.0 — T-Rex (Fps)	GPU 1 GPU 2
3DMark Fire Strike — Graphics Score	GPU 1 GPU 2

Name	AMD Radeon RX 590	NVIDIA GeForce GTX 1070 (Desktop)
PassMark — G3D Mark	9554	13510
PassMark — G2D Mark	805	857
Geekbench — OpenCL	47222	40527
CompuBench 1. 5 Desktop — Face Detection (mPixels/s)	137.469	150.951
CompuBench 1.5 Desktop — Ocean Surface Simulation (Frames/s)	2083.862	1718.593
CompuBench 1.5 Desktop — T-Rex (Frames/s)	12.353	12.283
CompuBench 1.5 Desktop — Video Composition (Frames/s)	139.477	28.289
CompuBench 1.5 Desktop — Bitcoin Mining (mHash/s)	762.142	710.366
GFXBench 4.0 — Car Chase Offscreen (Frames)	13383	13765
GFXBench 4. 0 — Manhattan (Frames)	3716	3691
GFXBench 4.0 — T-Rex (Frames)	3359	3340
GFXBench 4.0 — Car Chase Offscreen (Fps)	13383	13765
GFXBench 4.0 — Manhattan (Fps)	3716	3691
GFXBench 4.0 — T-Rex (Fps)	3359	3340
3DMark Fire Strike — Graphics Score	4765	6050

Performance comparison

conveyors

AMD RX 590 or Nvidia GTX 1070 Mobile

>

AMD RX 590 vs Nvidia GTX 1070 (Mobile)

Speed in games

RX 590

11. 6 (+5%)

GTX 1070 (Mobile)

11

Performance in games and similar applications, according to our tests.

Office speed

RX 590

69 (+19%)

GTX 1070 (Mobile)

57.9

Daily productivity.

Speed ​​in heavy applications

RX 590

8.3 (+19%)

GTX 1070 (Mobile)

7

Productivity in resource-intensive professional tasks.

Data obtained from tests by users who tested their systems with and without overclocking. Thus, you see the average values ​​corresponding to the video card.

Our benchmarks

	AMD Radeon RX 590	NVIDIA GeForce GTX 1070 (Desktop)
Architecture	GCN 4. 0	Pascal
Codename	Polaris 30	GP104
Design	Radeon RX 500 Series
Production date	November 15, 2018	10 June 2016
Price at first issue date	$279	$379
Place in the ranking	218	243
Type	Desktop	Desktop
Price now		$359. 99
Price/performance ratio (0-100)		45.72
Boost core clock	1545MHz	1683 MHz
Number of Compute	36
Core frequency	1469 MHz	1506 MHz
Floating point performance	7.1 TFLOPs	6.463 gflops
Process	12nm	16nm
Pixel fill rate	49. 54GP/s
Render output units	32
Stream Processors	2304
Texturing speed	222.48 GTexel/s	202.0 GTexel/s
Texture Units	144
Power consumption (TDP)	175 Watt	150 Watt
Number of transistors	5,700 million	7,200 million
Number of CUDA conveyors		1920
Maximum temperature		94 °C
Number of shaders		1920
Video connectors	1x HDMI, 3x DisplayPort	1x DVI, 1x HDMI, 3x DisplayPort, DP 1. 42, HDMI 2.0b, Dual Link-DVI
DisplayPort support
Dual-link DVI support
HDMI
VGA
G-SYNC support
Multi-monitor support
Interface	PCIe 3.0 x16	PCIe 3.0 x16
Length	241 mm	10. 5″ (26.7cm)
Additional power connectors	1x 8-pin	8-pin
Tire		PCIe 3.0
Height		4.376″ (11.1 cm)
Recommended power supply		500 Watt
Width		2-slot
DirectX	12.0 (12_0)	12.0 (12_1)
OpenGL	4.5	4.5
Vulcan
Maximum memory size	8GB	8GB
Memory bandwidth	256 GB/s	256GB/s
Memory bus width	256bit	256 Bit
Memory frequency	8000MHz	8 GB/s
Memory type	GDDR5	GDDR5
Shared memory		0
4K h364 Decode
4K h364 Encode
h365/HEVC Decode
h365/HEVC Encode
HDMI 4K Support
3D Vision
Ansel
CUDA
GPU Boost
ShadowWorks
SLI
Virtual Reality

3D DX9

RX 590 12.3 (+22%) GTX 1070 (Mobile) 15 (+22%)

3D DX10

RX 590 14.9 (+38%) GTX 1070 (Mobile) 20. 6 (+38%)

Features

Basic

Manufacturer	AMD	Nvidia
Chip name	Polaris 30	GP104
ArchitectureCode name for the microarchitecture generation.	GCN 4.0	Pascal
Chip manufacturer A company that manufactures chips in its own factory.	GlobalFoundries	TSMC
Process The manufacturing process, measured in nanometers. The smaller the technical process, the more perfect the technology, the lower the heat dissipation and power consumption.	12 nm	16 nm
Number of transistors	5,000,000	7000000
Interface PCI Express version. It is backward compatible, which allows you to install a PCIe 4.0 video card in a motherboard with a PCIe 3.0 slot. Sometimes manufacturers cut the number of lanes, for example AMD in the RX 6500 XT, which results in performance drops of up to 10-40%, depending on the game, when running an outdated 3.0-only motherboard.	PCIe 3.0 x16	PCIe 3.0 x16
TDPThermal Design Power is an indicator that determines the heat dissipation in standard operation.	175 W.	120 W.

GPU Specifications

Base FrequencyGPU clock frequency. You cannot compare different manufacturers or generations based only on this parameter. A video card with a lower frequency may be noticeably faster due to the advantages of the architecture.	1469MHz	1442MHz
Peak frequencyThe maximum frequency that the video processor can reach.	1545MHz	1645MHz

Video memory specifications

Video memory capacity The total amount of memory that stores images displayed on the computer screen. It can also be used in some calculations and programs. The performance of the graphics accelerator does not directly depend on the size of the memory, however, this is a very important parameter.	8 GB	8 GB
Video memory frequencyDepends on the type of soldered chips.	2000 MHz 8 Gbps	2002 MHz 8 Gbps
Type of video memory Each new generation provides a twofold increase in throughput while reducing voltage and heat dissipation.	GDDR5	GDDR5
Bus width Once upon a time, a relevant characteristic, since the performance of mid-budget cards was greatly reduced, lowering the bus width. Now there are very fast GPUs with a small bus, but very high-frequency memory chips, which gives sufficient bandwidth.	256bit	256bit
Bandwidth bandwidth — an important characteristic, obtained by a simple formula bandwidth = bus width * memory frequency.	256.0 GB/s	256.3 GB/s

Supported Technologies

DirectX High Level API. Windows users can check their version by typing «dxdiag» in the start menu search. We recommend buying graphics accelerators that support the latest version at the time of purchase, so as not to face the fact that a new game does not start in a couple of years.	12 (12_0)	12 (12_1)
OpenGL Platform and language independent programming interface. Used not only for applications, but also in some great games, such as SOMA.	4.6	4.6
OpenCL Used to speed up calculations. For example, Photoshop uses OpenCL acceleration for Edge Refinement, Smart Sharpen, and Blur Gallery.	2.1	3.0
Vulkan A low-level, cross-platform API that gives developers direct access and control over the graphics accelerator. Some games allow you to choose between DirectX and Vulkan, with the latter performing better.	1.2	1.3
Shader Model Shader version is important if you want to play modern games but buy an old graphics card.	6.4	6.4

Details

Shading Units	2304	2048
TMUsTexture mapping unit — graphics card blocks that apply textures to polygons.	144	128
ROPsRender output units — rasterization units. Their number and performance directly affects the fill rate.	32	64
L1 Cache	16 KB (per CU)	48 KB (per SM)
L2 Cache	2MB	2MB

Theoretical performance

Pixel Rate	49.44 GPixel/s	105.3 GPixel/s
Texture Rate	222.5 GTexel/s	210.6 GTexel/s
FP16 (half) performance	7. 119 TFLOPS (1:1)	105.3 GFLOPS (1:64)
FP32 (float) performance	7.119 TFLOPS	6.738TFLOPS
FP64 (double) performance	445.0 GFLOPS (1:16)	210.6 GFLOPS (1:32)

The rest

Presentation datePresentation in the media, official information.	2018-11-15	2016-08-15
Generation	Polaris (RX 500)	GeForce 10 Mobile
GPU	Polaris 30XT (215-0922006)	N17E-G2-A1
Video outputs	1x HDMI 2.