Tesla M40 vs ATI Radeon HD 4850
Aggregate performance score
We've compared Radeon HD 4850 with Tesla M40, including specs and performance data.
M40 outperforms HD 4850 by a whopping 898% 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 | 884 | 258 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 0.23 | no data |
| Power efficiency | 1.72 | 7.53 |
| Architecture | TeraScale (2005−2013) | Maxwell 2.0 (2014−2019) |
| GPU code name | RV770 | GM200 |
| Market segment | Desktop | Workstation |
| Release date | 25 June 2008 (17 years ago) | 10 November 2015 (10 years ago) |
| Launch price (MSRP) | $199 | 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 | 800 | 3072 |
| Core clock speed | 625 MHz | 948 MHz |
| Boost clock speed | no data | 1112 MHz |
| Number of transistors | 956 million | 8,000 million |
| Manufacturing process technology | 55 nm | 28 nm |
| Power consumption (TDP) | 110 Watt | 250 Watt |
| Texture fill rate | 25.00 | 213.5 |
| Floating-point processing power | 1 TFLOPS | 6.832 TFLOPS |
| ROPs | 16 | 96 |
| TMUs | 40 | 192 |
| L1 Cache | 160 KB | 1.1 MB |
| L2 Cache | 256 KB | 3 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).
| Interface | PCIe 2.0 x16 | PCIe 3.0 x16 |
| Length | 246 mm | 267 mm |
| Width | 1-slot | 2-slot |
| Supplementary power connectors | 1x 6-pin | 8-pin EPS |
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 | GDDR3 | GDDR5 |
| Maximum RAM amount | 512 MB | 12 GB |
| Memory bus width | 256 Bit | 384 Bit |
| Memory clock speed | 993 MHz | 1502 MHz |
| Memory bandwidth | 63.55 GB/s | 288.4 GB/s |
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 S-Video | No outputs |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 10.1 (10_1) | 12 (12_1) |
| Shader Model | 4.1 | 6.7 |
| OpenGL | 3.3 | 4.6 |
| OpenCL | 1.1 | 3.0 |
| Vulkan | N/A | 1.3 |
| CUDA | - | 5.2 |
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:
| 900p | 28
−864%
| 270−280
+864%
|
| Full HD | 40
−775%
| 350−400
+775%
|
| 1200p | 19
−847%
| 180−190
+847%
|
Cost per frame, $
| 1080p | 4.98 | no data |
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 6−7
−817%
|
55−60
+817%
|
| Cyberpunk 2077 | 5−6
−800%
|
45−50
+800%
|
| Resident Evil 4 Remake | 3−4
−800%
|
27−30
+800%
|
Full HD
Medium
| Battlefield 5 | 8−9
−838%
|
75−80
+838%
|
| Counter-Strike 2 | 6−7
−817%
|
55−60
+817%
|
| Cyberpunk 2077 | 5−6
−800%
|
45−50
+800%
|
| Far Cry 5 | 7−8
−829%
|
65−70
+829%
|
| Fortnite | 12−14
−817%
|
110−120
+817%
|
| Forza Horizon 4 | 12−14
−823%
|
120−130
+823%
|
| Forza Horizon 5 | 6−7
−817%
|
55−60
+817%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 12−14
−817%
|
110−120
+817%
|
| Valorant | 40−45
−830%
|
400−450
+830%
|
Full HD
High
| Battlefield 5 | 8−9
−838%
|
75−80
+838%
|
| Counter-Strike 2 | 6−7
−817%
|
55−60
+817%
|
| Counter-Strike: Global Offensive | 45−50
−838%
|
450−500
+838%
|
| Cyberpunk 2077 | 5−6
−800%
|
45−50
+800%
|
| Dota 2 | 24−27
−860%
|
240−250
+860%
|
| Far Cry 5 | 7−8
−829%
|
65−70
+829%
|
| Fortnite | 12−14
−817%
|
110−120
+817%
|
| Forza Horizon 4 | 12−14
−823%
|
120−130
+823%
|
| Forza Horizon 5 | 6−7
−817%
|
55−60
+817%
|
| Grand Theft Auto V | 5−6
−800%
|
45−50
+800%
|
| Metro Exodus | 4−5
−775%
|
35−40
+775%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 12−14
−817%
|
110−120
+817%
|
| The Witcher 3: Wild Hunt | 9−10
−844%
|
85−90
+844%
|
| Valorant | 40−45
−830%
|
400−450
+830%
|
Full HD
Ultra
| Battlefield 5 | 8−9
−838%
|
75−80
+838%
|
| Cyberpunk 2077 | 5−6
−800%
|
45−50
+800%
|
| Dota 2 | 24−27
−860%
|
240−250
+860%
|
| Far Cry 5 | 7−8
−829%
|
65−70
+829%
|
| Forza Horizon 4 | 12−14
−823%
|
120−130
+823%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 12−14
−817%
|
110−120
+817%
|
| The Witcher 3: Wild Hunt | 9−10
−844%
|
85−90
+844%
|
| Valorant | 40−45
−830%
|
400−450
+830%
|
Full HD
Epic
| Fortnite | 12−14
−817%
|
110−120
+817%
|
1440p
High
| Counter-Strike 2 | 6−7
−817%
|
55−60
+817%
|
| Counter-Strike: Global Offensive | 18−20
−844%
|
170−180
+844%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 21−24
−857%
|
220−230
+857%
|
| Valorant | 21−24
−852%
|
200−210
+852%
|
1440p
Ultra
| Cyberpunk 2077 | 1−2
−800%
|
9−10
+800%
|
| Far Cry 5 | 4−5
−775%
|
35−40
+775%
|
| Forza Horizon 4 | 6−7
−817%
|
55−60
+817%
|
| The Witcher 3: Wild Hunt | 4−5
−775%
|
35−40
+775%
|
1440p
Epic
| Fortnite | 4−5
−775%
|
35−40
+775%
|
4K
High
| Grand Theft Auto V | 14−16
−833%
|
140−150
+833%
|
| Valorant | 12−14
−817%
|
110−120
+817%
|
4K
Ultra
| Cyberpunk 2077 | 0−1 | 0−1 |
| Dota 2 | 6−7
−817%
|
55−60
+817%
|
| Far Cry 5 | 1−2
−800%
|
9−10
+800%
|
| Forza Horizon 4 | 2−3
−800%
|
18−20
+800%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 3−4
−800%
|
27−30
+800%
|
4K
Epic
| Fortnite | 3−4
−800%
|
27−30
+800%
|
This is how ATI HD 4850 and Tesla M40 compete in popular games:
- Tesla M40 is 864% faster in 900p
- Tesla M40 is 775% faster in 1080p
- Tesla M40 is 847% faster in 1200p
Pros & cons summary
| Performance score | 2.45 | 24.44 |
| Recency | 25 June 2008 | 10 November 2015 |
| Maximum RAM amount | 512 MB | 12 GB |
| Chip lithography | 55 nm | 28 nm |
| Power consumption (TDP) | 110 Watt | 250 Watt |
ATI HD 4850 has 127% lower power consumption.
Tesla M40, on the other hand, has a 898% higher aggregate performance score, an age advantage of 7 years, a 2300% higher maximum VRAM amount, and a 96% more advanced lithography process.
The Tesla M40 is our recommended choice as it beats the Radeon HD 4850 in performance tests.
Be aware that Radeon HD 4850 is a desktop graphics card while Tesla M40 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.
