Tesla P4 vs Radeon R9 390X
Aggregate performance score
We've compared Radeon R9 390X with Tesla P4, including specs and performance data.
R9 390X outperforms P4 by a minimal 3% based on our aggregate benchmark results.
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 287 | 293 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 8.56 | no data |
| Power efficiency | 6.19 | 22.02 |
| Architecture | GCN 2.0 (2013−2017) | Pascal (2016−2021) |
| GPU code name | Grenada | GP104 |
| Market segment | Desktop | Workstation |
| Design | reference | no data |
| Release date | 18 June 2015 (10 years ago) | 13 September 2016 (9 years ago) |
| Launch price (MSRP) | $429 | 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 | 2816 | 2560 |
| Core clock speed | no data | 886 MHz |
| Boost clock speed | 1050 MHz | 1114 MHz |
| Number of transistors | 6,200 million | 7,200 million |
| Manufacturing process technology | 28 nm | 16 nm |
| Power consumption (TDP) | 275 Watt | 75 Watt |
| Texture fill rate | 184.8 | 178.2 |
| Floating-point processing power | 5.914 TFLOPS | 5.704 TFLOPS |
| ROPs | 64 | 64 |
| TMUs | 176 | 160 |
| L1 Cache | 704 KB | 960 KB |
| L2 Cache | 1024 KB | 2 MB |
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).
| Bus support | PCIe 3.0 | no data |
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Length | 275 mm | 168 mm |
| Width | 2-slot | 1-slot |
| Supplementary power connectors | 1 x 6-pin, 1 x 8-pin | None |
| Bridgeless CrossFire | + | - |
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 | GDDR5 |
| High bandwidth memory (HBM) | - | no data |
| Maximum RAM amount | 0 MB | 8 GB |
| Memory bus width | 512 Bit | 256 Bit |
| Memory clock speed | 1050 MHz | 1502 MHz |
| Memory bandwidth | 384 GB/s | 192.3 GB/s |
| 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 | 2x DVI, 1x HDMI, 1x DisplayPort | No outputs |
| Eyefinity | + | - |
| Number of Eyefinity displays | 6 | no data |
| HDMI | + | - |
| DisplayPort support | + | - |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| CrossFire | + | - |
| FreeSync | + | - |
| PowerTune | + | - |
| TrueAudio | + | - |
| VCE | + | - |
| DDMA audio | + | no data |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | DirectX® 12 | 12 (12_1) |
| Shader Model | 6.3 | 6.4 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 1.2 |
| Vulkan | + | 1.2.131 |
| Mantle | + | - |
| CUDA | - | 6.1 |
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.
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.
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 | 91
+7.1%
| 85−90
−7.1%
|
| 4K | 48
+6.7%
| 45−50
−6.7%
|
Cost per frame, $
| 1080p | 4.71 | no data |
| 4K | 8.94 | no data |
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 120−130
+6.7%
|
120−130
−6.7%
|
| Cyberpunk 2077 | 45−50
+8.9%
|
45−50
−8.9%
|
Full HD
Medium
| Battlefield 5 | 90−95
+7.1%
|
85−90
−7.1%
|
| Counter-Strike 2 | 120−130
+6.7%
|
120−130
−6.7%
|
| Cyberpunk 2077 | 45−50
+8.9%
|
45−50
−8.9%
|
| Escape from Tarkov | 85−90
+3.5%
|
85−90
−3.5%
|
| Far Cry 5 | 70−75
+5.7%
|
70−75
−5.7%
|
| Fortnite | 110−120
+3.6%
|
110−120
−3.6%
|
| Forza Horizon 4 | 90−95
+5.9%
|
85−90
−5.9%
|
| Forza Horizon 5 | 70−75
+9.2%
|
65−70
−9.2%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 85−90
+3.5%
|
85−90
−3.5%
|
| Valorant | 160−170
+6.7%
|
150−160
−6.7%
|
Full HD
High
| Battlefield 5 | 90−95
+7.1%
|
85−90
−7.1%
|
| Counter-Strike 2 | 120−130
+6.7%
|
120−130
−6.7%
|
| Counter-Strike: Global Offensive | 250−260
+4.6%
|
240−250
−4.6%
|
| Cyberpunk 2077 | 45−50
+8.9%
|
45−50
−8.9%
|
| Dota 2 | 110−120
+8.2%
|
110−120
−8.2%
|
| Escape from Tarkov | 85−90
+3.5%
|
85−90
−3.5%
|
| Far Cry 5 | 70−75
+5.7%
|
70−75
−5.7%
|
| Fortnite | 110−120
+3.6%
|
110−120
−3.6%
|
| Forza Horizon 4 | 90−95
+5.9%
|
85−90
−5.9%
|
| Forza Horizon 5 | 70−75
+9.2%
|
65−70
−9.2%
|
| Grand Theft Auto V | 80−85
+3.8%
|
80−85
−3.8%
|
| Metro Exodus | 45−50
+8.9%
|
45−50
−8.9%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 85−90
+3.5%
|
85−90
−3.5%
|
| The Witcher 3: Wild Hunt | 76
+8.6%
|
70−75
−8.6%
|
| Valorant | 160−170
+6.7%
|
150−160
−6.7%
|
Full HD
Ultra
| Battlefield 5 | 90−95
+7.1%
|
85−90
−7.1%
|
| Cyberpunk 2077 | 45−50
+8.9%
|
45−50
−8.9%
|
| Dota 2 | 110−120
+8.2%
|
110−120
−8.2%
|
| Escape from Tarkov | 85−90
+3.5%
|
85−90
−3.5%
|
| Far Cry 5 | 70−75
+5.7%
|
70−75
−5.7%
|
| Forza Horizon 4 | 90−95
+5.9%
|
85−90
−5.9%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 85−90
+3.5%
|
85−90
−3.5%
|
| The Witcher 3: Wild Hunt | 41
+17.1%
|
35−40
−17.1%
|
| Valorant | 160−170
+6.7%
|
150−160
−6.7%
|
Full HD
Epic
| Fortnite | 110−120
+3.6%
|
110−120
−3.6%
|
1440p
High
| Counter-Strike 2 | 45−50
+6.7%
|
45−50
−6.7%
|
| Counter-Strike: Global Offensive | 160−170
+7.3%
|
150−160
−7.3%
|
| Grand Theft Auto V | 40−45
+17.1%
|
35−40
−17.1%
|
| Metro Exodus | 30−33
+11.1%
|
27−30
−11.1%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+8.8%
|
160−170
−8.8%
|
| Valorant | 190−200
+3.7%
|
190−200
−3.7%
|
1440p
Ultra
| Battlefield 5 | 60−65
+6.7%
|
60−65
−6.7%
|
| Cyberpunk 2077 | 21−24
+4.8%
|
21−24
−4.8%
|
| Escape from Tarkov | 50−55
+11.1%
|
45−50
−11.1%
|
| Far Cry 5 | 50−55
+13.3%
|
45−50
−13.3%
|
| Forza Horizon 4 | 55−60
+3.6%
|
55−60
−3.6%
|
| The Witcher 3: Wild Hunt | 35−40
+16.7%
|
30−33
−16.7%
|
1440p
Epic
| Fortnite | 50−55
+8%
|
50−55
−8%
|
4K
High
| Counter-Strike 2 | 21−24
+4.8%
|
21−24
−4.8%
|
| Grand Theft Auto V | 40−45
+5%
|
40−45
−5%
|
| Metro Exodus | 18−20
+5.6%
|
18−20
−5.6%
|
| The Witcher 3: Wild Hunt | 29
+7.4%
|
27−30
−7.4%
|
| Valorant | 130−140
+10%
|
120−130
−10%
|
4K
Ultra
| Battlefield 5 | 35−40
+16.7%
|
30−33
−16.7%
|
| Counter-Strike 2 | 21−24
+4.8%
|
21−24
−4.8%
|
| Cyberpunk 2077 | 9−10
+12.5%
|
8−9
−12.5%
|
| Dota 2 | 75−80
+7.1%
|
70−75
−7.1%
|
| Escape from Tarkov | 21−24
+9.5%
|
21−24
−9.5%
|
| Far Cry 5 | 24−27
+8.3%
|
24−27
−8.3%
|
| Forza Horizon 4 | 35−40
+11.4%
|
35−40
−11.4%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 24−27
+14.3%
|
21−24
−14.3%
|
4K
Epic
| Fortnite | 24−27
+14.3%
|
21−24
−14.3%
|
This is how R9 390X and Tesla P4 compete in popular games:
- R9 390X is 7% faster in 1080p
- R9 390X is 7% faster in 4K
Pros & cons summary
| Performance score | 22.08 | 21.43 |
| Recency | 18 June 2015 | 13 September 2016 |
| Chip lithography | 28 nm | 16 nm |
| Power consumption (TDP) | 275 Watt | 75 Watt |
R9 390X has a 3% higher aggregate performance score.
Tesla P4, on the other hand, has an age advantage of 1 year, a 75% more advanced lithography process, and 266.7% lower power consumption.
Given the minimal performance differences, no clear winner can be declared between Radeon R9 390X and Tesla P4.
Be aware that Radeon R9 390X is a desktop graphics card while Tesla P4 is a workstation one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
