NVIDIA GeForce GT 740 vs ATI Radeon HD 3850
We compared two Desktop platform GPUs: 1024MB VRAM GeForce GT 740 and 512MB VRAM Radeon HD 3850 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce GT 740 's Advantages
Released 6 years and 6 months late
More VRAM (1024GB vs 512GB)
Larger VRAM bandwidth (80.19GB/s vs 53.12GB/s)
64 additional rendering cores
Lower TDP (64W vs 75W)
Score
Benchmark
FP32 (float)
GeForce GT 740
+78%
0.763 TFLOPS
Radeon HD 3850
0.428 TFLOPS
Graphics Card
May 2014
Release Date
Nov 2007
GeForce 700
Generation
Radeon R600
Desktop
Type
Desktop
PCIe 3.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
-
-
-
-
-
-
1253 MHz
Memory Clock
830 MHz
Memory
1024MB
Memory Size
512MB
GDDR5
Memory Type
GDDR3
128bit
Memory Bus
256bit
80.19GB/s
Bandwidth
53.12GB/s
Render Config
-
Compute Units
4
-
-
-
384
Shading Units
320
32
TMUs
16
16
ROPs
16
-
-
-
-
-
-
16 KB (per SMX)
L1 Cache
-
256 KB
L2 Cache
256 KB
-
-
-
Theoretical Performance
7.944 GPixel/s
Pixel Rate
10.69 GPixel/s
31.78 GTexel/s
Texture Rate
10.69 GTexel/s
-
-
-
762.6 GFLOPS
FP32 (float)
427.5 GFLOPS
31.78 GFLOPS
FP64 (double)
85.50 GFLOPS
Board Design
64W
TDP
75W
250 W
Suggested PSU
250 W
2x DVI
1x mini-HDMI 1.4a
Outputs
2x DVI
1x S-Video
1x 6-pin
Power Connectors
1x 6-pin
Graphics Processor
GK107
GPU Name
RV670
GK107-425-A2
GPU Variant
RV670 PRO
(215-0708003)
Kepler
Architecture
TeraScale
TSMC
Foundry
TSMC
28 nm
Process Size
55 nm
1.27 billion
Transistors
0.666 billion
118 mm²
Die Size
192 mm²
Graphics Features
12 (11_0)
DirectX
10.1 (10_1)
4.6
OpenGL
3.3 (full)
4.0 (partial)
3.0
OpenCL
N/A
1.1
Vulkan
N/A
3.0
CUDA
-
5.1
Shader Model
4.1
