Radeon R7 384 Cores (Kaveri Desktop) vs Pro Vega 56
Aggregate performance score
We've compared Radeon Pro Vega 56 with Radeon R7 384 Cores (Kaveri Desktop), including specs and performance data.
Pro 56 outperforms R7 384 Cores (Kaveri Desktop) by a whopping 1064% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
Place in the ranking | 217 | 858 |
Place by popularity | not in top-100 | not in top-100 |
Cost-effectiveness evaluation | 15.56 | no data |
Power efficiency | 10.72 | no data |
Architecture | GCN 5.0 (2017−2020) | GCN (2012−2015) |
GPU code name | Vega 10 | Kaveri Spectre |
Market segment | Mobile workstation | Desktop |
Release date | 14 August 2017 (8 years ago) | 14 January 2014 (11 years ago) |
Launch price (MSRP) | $399 | no data |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
Performance to price scatter graph
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 | 3584 | 384 |
Core clock speed | 1138 MHz | 720 MHz |
Boost clock speed | 1250 MHz | no data |
Number of transistors | 12,500 million | no data |
Manufacturing process technology | 14 nm | 28 nm |
Power consumption (TDP) | 210 Watt | no data |
Texture fill rate | 280.0 | no data |
Floating-point processing power | 8.96 TFLOPS | no data |
ROPs | 64 | no data |
TMUs | 224 | no data |
L1 Cache | 896 KB | no data |
L2 Cache | 4 MB | no data |
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).
Interface | PCIe 3.0 x16 | no data |
Supplementary power connectors | None | 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 | HBM2 | no data |
Maximum RAM amount | 8 GB | no data |
Memory bus width | 2048 Bit | no data |
Memory clock speed | 786 MHz | no data |
Memory bandwidth | 402.4 GB/s | no data |
Shared memory | - | + |
Connectivity and outputs
This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.
Display Connectors | 1x HDMI, 3x DisplayPort | no data |
HDMI | + | - |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
DirectX | 12 (12_1) | 12 (FL 12_0) |
Shader Model | 6.4 | no data |
OpenGL | 4.6 | no data |
OpenCL | 2.0 | no data |
Vulkan | 1.1.125 | - |
Synthetic benchmarks
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.
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 Fire Strike Graphics
Fire Strike is a DirectX 11 benchmark for gaming PCs. It features two separate tests displaying a fight between a humanoid and a fiery creature made of lava. Using 1920x1080 resolution, Fire Strike shows off some realistic graphics and is quite taxing on hardware.
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 | 96
+586%
| 14
−586%
|
4K | 57
+1325%
| 4−5
−1325%
|
Cost per frame, $
1080p | 4.16 | no data |
4K | 7.00 | no data |
FPS performance in popular games
Full HD
Low
Counter-Strike 2 | 160−170
+2314%
|
7−8
−2314%
|
Cyberpunk 2077 | 65−70
+1240%
|
5−6
−1240%
|
Hogwarts Legacy | 65−70
+713%
|
8−9
−713%
|
Full HD
Medium
Battlefield 5 | 110−120
+1300%
|
8−9
−1300%
|
Counter-Strike 2 | 160−170
+2314%
|
7−8
−2314%
|
Cyberpunk 2077 | 65−70
+1240%
|
5−6
−1240%
|
Far Cry 5 | 95−100
+1286%
|
7−8
−1286%
|
Fortnite | 130−140
+962%
|
12−14
−962%
|
Forza Horizon 4 | 110−120
+800%
|
12−14
−800%
|
Forza Horizon 5 | 95−100
+1483%
|
6−7
−1483%
|
Hogwarts Legacy | 65−70
+713%
|
8−9
−713%
|
PLAYERUNKNOWN'S BATTLEGROUNDS | 120−130
+823%
|
12−14
−823%
|
Valorant | 190−200
+334%
|
40−45
−334%
|
Full HD
High
Battlefield 5 | 110−120
+1300%
|
8−9
−1300%
|
Counter-Strike 2 | 160−170
+2314%
|
7−8
−2314%
|
Counter-Strike: Global Offensive | 270−280
+448%
|
50−55
−448%
|
Cyberpunk 2077 | 65−70
+1240%
|
5−6
−1240%
|
Dota 2 | 107
+312%
|
24−27
−312%
|
Far Cry 5 | 95−100
+1286%
|
7−8
−1286%
|
Fortnite | 130−140
+962%
|
12−14
−962%
|
Forza Horizon 4 | 110−120
+800%
|
12−14
−800%
|
Forza Horizon 5 | 95−100
+1483%
|
6−7
−1483%
|
Grand Theft Auto V | 100−110
+1067%
|
9
−1067%
|
Hogwarts Legacy | 65−70
+713%
|
8−9
−713%
|
Metro Exodus | 65−70
+1600%
|
4−5
−1600%
|
PLAYERUNKNOWN'S BATTLEGROUNDS | 120−130
+823%
|
12−14
−823%
|
The Witcher 3: Wild Hunt | 116
+1189%
|
9−10
−1189%
|
Valorant | 190−200
+334%
|
40−45
−334%
|
Full HD
Ultra
Battlefield 5 | 110−120
+1300%
|
8−9
−1300%
|
Cyberpunk 2077 | 65−70
+1240%
|
5−6
−1240%
|
Dota 2 | 102
+292%
|
24−27
−292%
|
Far Cry 5 | 95−100
+1286%
|
7−8
−1286%
|
Forza Horizon 4 | 110−120
+800%
|
12−14
−800%
|
Hogwarts Legacy | 65−70
+713%
|
8−9
−713%
|
PLAYERUNKNOWN'S BATTLEGROUNDS | 120−130
+823%
|
12−14
−823%
|
The Witcher 3: Wild Hunt | 64
+611%
|
9−10
−611%
|
Valorant | 190−200
+334%
|
40−45
−334%
|
Full HD
Epic
Fortnite | 130−140
+962%
|
12−14
−962%
|
1440p
High
Counter-Strike 2 | 65−70
+1050%
|
6−7
−1050%
|
Counter-Strike: Global Offensive | 210−220
+1005%
|
18−20
−1005%
|
Grand Theft Auto V | 55−60
+5700%
|
1−2
−5700%
|
Metro Exodus | 40−45 | 0−1 |
PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+661%
|
21−24
−661%
|
Valorant | 220−230
+887%
|
21−24
−887%
|
1440p
Ultra
Battlefield 5 | 80−85
+1250%
|
6−7
−1250%
|
Cyberpunk 2077 | 30−35
+1500%
|
2−3
−1500%
|
Far Cry 5 | 70−75
+1650%
|
4−5
−1650%
|
Forza Horizon 4 | 80−85
+1233%
|
6−7
−1233%
|
Hogwarts Legacy | 30−35
+1033%
|
3−4
−1033%
|
The Witcher 3: Wild Hunt | 50−55
+1633%
|
3−4
−1633%
|
1440p
Epic
Fortnite | 75−80
+1400%
|
5−6
−1400%
|
4K
High
Counter-Strike 2 | 30−35
+1500%
|
2−3
−1500%
|
Grand Theft Auto V | 55−60
+269%
|
16−18
−269%
|
Hogwarts Legacy | 18−20
+1800%
|
1−2
−1800%
|
Metro Exodus | 24−27
+1200%
|
2−3
−1200%
|
The Witcher 3: Wild Hunt | 42
+1300%
|
3−4
−1300%
|
Valorant | 180−190
+1285%
|
12−14
−1285%
|
4K
Ultra
Battlefield 5 | 45−50
+1075%
|
4−5
−1075%
|
Counter-Strike 2 | 30−35
+1500%
|
2−3
−1500%
|
Cyberpunk 2077 | 14−16 | 0−1 |
Dota 2 | 96
+1271%
|
7−8
−1271%
|
Far Cry 5 | 35−40
+3600%
|
1−2
−3600%
|
Forza Horizon 4 | 50−55
+2600%
|
2−3
−2600%
|
Hogwarts Legacy | 18−20
+1800%
|
1−2
−1800%
|
PLAYERUNKNOWN'S BATTLEGROUNDS | 35−40
+1067%
|
3−4
−1067%
|
4K
Epic
Fortnite | 35−40
+1067%
|
3−4
−1067%
|
This is how Pro Vega 56 and R7 384 Cores (Kaveri Desktop) compete in popular games:
- Pro Vega 56 is 586% faster in 1080p
- Pro Vega 56 is 1325% faster in 4K
Here's the range of performance differences observed across popular games:
- in Grand Theft Auto V, with 1440p resolution and the High Preset, the Pro Vega 56 is 5700% faster.
All in all, in popular games:
- Without exception, Pro Vega 56 surpassed R7 384 Cores (Kaveri Desktop) in all 56 of our tests.
Pros & cons summary
Performance score | 27.94 | 2.40 |
Recency | 14 August 2017 | 14 January 2014 |
Chip lithography | 14 nm | 28 nm |
Pro Vega 56 has a 1064.2% higher aggregate performance score, an age advantage of 3 years, and a 100% more advanced lithography process.
The Radeon Pro Vega 56 is our recommended choice as it beats the Radeon R7 384 Cores (Kaveri Desktop) in performance tests.
Be aware that Radeon Pro Vega 56 is a mobile workstation graphics card while Radeon R7 384 Cores (Kaveri Desktop) is a desktop one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.