Radeon HD 6620G vs RX 580
Aggregate performance score
We've compared Radeon RX 580 with Radeon HD 6620G, including specs and performance data.
RX 580 outperforms HD 6620G by a whopping 2503% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 259 | 1144 |
| Place by popularity | 1 | not in top-100 |
| Cost-effectiveness evaluation | 15.09 | no data |
| Power efficiency | 8.47 | 1.72 |
| Architecture | GCN 4.0 (2016−2020) | TeraScale 2 (2009−2015) |
| GPU code name | Polaris 20 | Sumo |
| Market segment | Desktop | Laptop |
| Release date | 18 April 2017 (7 years ago) | 7 December 2011 (13 years ago) |
| Launch price (MSRP) | $229 | no data |
Cost-effectiveness evaluation
The higher the performance-to-price ratio, the better. We use the manufacturer's recommended prices for comparison.
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 | 2304 | 400 |
| Core clock speed | 1257 MHz | 444 MHz |
| Boost clock speed | 1340 MHz | no data |
| Number of transistors | 5,700 million | 1,178 million |
| Manufacturing process technology | 14 nm | 32 nm |
| Power consumption (TDP) | 185 Watt | 35 Watt |
| Texture fill rate | 193.0 | 8.880 |
| Floating-point processing power | 6.175 TFLOPS | 0.3552 TFLOPS |
| ROPs | 32 | 8 |
| TMUs | 144 | 20 |
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).
| Laptop size | no data | medium sized |
| Interface | PCIe 3.0 x16 | IGP |
| Length | 241 mm | no data |
| Width | 2-slot | no data |
| Supplementary power connectors | 1x 8-pin | no data |
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 | System Shared |
| Maximum RAM amount | 8 GB | System Shared |
| Memory bus width | 256 Bit | System Shared |
| Memory clock speed | 2000 MHz | System Shared |
| Memory bandwidth | 256.0 GB/s | no data |
| Shared memory | - | + |
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 | 1x HDMI, 3x DisplayPort | No outputs |
| HDMI | + | - |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (12_0) | 11.2 (11_0) |
| Shader Model | 6.4 | 5.0 |
| OpenGL | 4.6 | 4.4 |
| OpenCL | 2.0 | 1.2 |
| Vulkan | 1.2.131 | N/A |
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.
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.
3DMark 11 Performance GPU
3DMark 11 is an obsolete DirectX 11 benchmark by Futuremark. It used four tests based on two scenes, one being few submarines exploring the submerged wreck of a sunken ship, the other is an abandoned temple deep in the jungle. All the tests are heavy with volumetric lighting and tessellation, and despite being done in 1280x720 resolution, are relatively taxing. Discontinued in January 2020, 3DMark 11 is now superseded by Time Spy.
3DMark Vantage Performance
3DMark Vantage is an outdated DirectX 10 benchmark using 1280x1024 screen resolution. It taxes the graphics card with two scenes, one depicting a girl escaping some militarized base located within a sea cave, the other displaying a space fleet attack on a defenseless planet. It was discontinued in April 2017, and Time Spy benchmark is now recommended to be used instead.
Gaming performance
Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.
Average FPS across all PC games
Here are the average frames per second in a large set of popular games across different resolutions:
| Full HD | 97
+646%
| 13
−646%
|
| 1440p | 43
+4200%
| 1−2
−4200%
|
| 4K | 37
+3600%
| 1−2
−3600%
|
Cost per frame, $
| 1080p | 2.36 | no data |
| 1440p | 5.33 | no data |
| 4K | 6.19 | no data |
FPS performance in popular games
Full HD
Low Preset
| Atomic Heart | 55−60
+1833%
|
3−4
−1833%
|
| Counter-Strike 2 | 120−130
+3000%
|
4−5
−3000%
|
| Cyberpunk 2077 | 45−50
+2200%
|
2−3
−2200%
|
Full HD
Medium Preset
| Atomic Heart | 55−60
+1833%
|
3−4
−1833%
|
| Battlefield 5 | 124
+3000%
|
4−5
−3000%
|
| Counter-Strike 2 | 120−130
+3000%
|
4−5
−3000%
|
| Cyberpunk 2077 | 45−50
+2200%
|
2−3
−2200%
|
| Far Cry 5 | 83
+2667%
|
3−4
−2667%
|
| Fortnite | 153
+2960%
|
5−6
−2960%
|
| Forza Horizon 4 | 108
+2060%
|
5−6
−2060%
|
| Forza Horizon 5 | 65−70
+3350%
|
2−3
−3350%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 85
+963%
|
8−9
−963%
|
| Valorant | 150−160
+413%
|
30−33
−413%
|
Full HD
High Preset
| Atomic Heart | 55−60
+1833%
|
3−4
−1833%
|
| Battlefield 5 | 102
+3300%
|
3−4
−3300%
|
| Counter-Strike 2 | 120−130
+3000%
|
4−5
−3000%
|
| Counter-Strike: Global Offensive | 240−250
+1009%
|
21−24
−1009%
|
| Cyberpunk 2077 | 45−50
+2200%
|
2−3
−2200%
|
| Dota 2 | 110−120
+792%
|
12−14
−792%
|
| Far Cry 5 | 76
+3700%
|
2−3
−3700%
|
| Fortnite | 106
+2550%
|
4−5
−2550%
|
| Forza Horizon 4 | 101
+1920%
|
5−6
−1920%
|
| Forza Horizon 5 | 65−70
+3350%
|
2−3
−3350%
|
| Grand Theft Auto V | 77
+3750%
|
2−3
−3750%
|
| Metro Exodus | 48
+4700%
|
1−2
−4700%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 70
+775%
|
8−9
−775%
|
| The Witcher 3: Wild Hunt | 72
+1340%
|
5−6
−1340%
|
| Valorant | 150−160
+413%
|
30−33
−413%
|
Full HD
Ultra Preset
| Battlefield 5 | 93
+3000%
|
3−4
−3000%
|
| Cyberpunk 2077 | 45−50
+2200%
|
2−3
−2200%
|
| Dota 2 | 110−120
+792%
|
12−14
−792%
|
| Far Cry 5 | 71
+3450%
|
2−3
−3450%
|
| Forza Horizon 4 | 82
+1540%
|
5−6
−1540%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 49
+513%
|
8−9
−513%
|
| The Witcher 3: Wild Hunt | 44
+780%
|
5−6
−780%
|
| Valorant | 150−160
+413%
|
30−33
−413%
|
Full HD
Epic Preset
| Fortnite | 80
+2567%
|
3−4
−2567%
|
1440p
High Preset
| Counter-Strike 2 | 45−50
+4500%
|
1−2
−4500%
|
| Counter-Strike: Global Offensive | 150−160
+3750%
|
4−5
−3750%
|
| Grand Theft Auto V | 35−40
+3700%
|
1−2
−3700%
|
| Metro Exodus | 28
+2700%
|
1−2
−2700%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+2063%
|
8−9
−2063%
|
| Valorant | 190−200
+2657%
|
7−8
−2657%
|
1440p
Ultra Preset
| Battlefield 5 | 60−65
+2950%
|
2−3
−2950%
|
| Cyberpunk 2077 | 21−24 | 0−1 |
| Far Cry 5 | 45−50
+4800%
|
1−2
−4800%
|
| Forza Horizon 4 | 55−60
+2650%
|
2−3
−2650%
|
| The Witcher 3: Wild Hunt | 35−40
+3500%
|
1−2
−3500%
|
1440p
Epic Preset
| Fortnite | 50−55
+5000%
|
1−2
−5000%
|
4K
High Preset
| Atomic Heart | 16−18 | 0−1 |
| Counter-Strike 2 | 21−24 | 0−1 |
| Grand Theft Auto V | 57
+280%
|
14−16
−280%
|
| Metro Exodus | 18 | 0−1 |
| The Witcher 3: Wild Hunt | 27
+2600%
|
1−2
−2600%
|
| Valorant | 120−130
+2380%
|
5−6
−2380%
|
4K
Ultra Preset
| Battlefield 5 | 37
+3600%
|
1−2
−3600%
|
| Counter-Strike 2 | 21−24 | 0−1 |
| Cyberpunk 2077 | 9−10 | 0−1 |
| Dota 2 | 70−75
+3500%
|
2−3
−3500%
|
| Far Cry 5 | 26
+2500%
|
1−2
−2500%
|
| Forza Horizon 4 | 41
+4000%
|
1−2
−4000%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 18
+800%
|
2−3
−800%
|
4K
Epic Preset
| Fortnite | 23
+1050%
|
2−3
−1050%
|
This is how RX 580 and HD 6620G compete in popular games:
- RX 580 is 646% faster in 1080p
- RX 580 is 4200% faster in 1440p
- RX 580 is 3600% faster in 4K
Here's the range of performance differences observed across popular games:
- in Fortnite, with 1440p resolution and the Epic Preset, the RX 580 is 5000% faster.
All in all, in popular games:
- Without exception, RX 580 surpassed HD 6620G in all 32 of our tests.
Pros & cons summary
| Performance score | 19.78 | 0.76 |
| Recency | 18 April 2017 | 7 December 2011 |
| Chip lithography | 14 nm | 32 nm |
| Power consumption (TDP) | 185 Watt | 35 Watt |
RX 580 has a 2502.6% higher aggregate performance score, an age advantage of 5 years, and a 128.6% more advanced lithography process.
HD 6620G, on the other hand, has 428.6% lower power consumption.
The Radeon RX 580 is our recommended choice as it beats the Radeon HD 6620G in performance tests.
Be aware that Radeon RX 580 is a desktop card while Radeon HD 6620G is a notebook one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
