NVIDIA GeForce GTS 240 OEM vs ATI Radeon HD 4670 AGP
We compared two Desktop platform GPUs: 1024MB VRAM GeForce GTS 240 OEM and 1024MB VRAM Radeon HD 4670 AGP to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce GTS 240 OEM 's Advantages
Larger VRAM bandwidth (70.40GB/s vs 25.60GB/s)
ATI Radeon HD 4670 AGP 's Advantages
208 additional rendering cores
Lower TDP (59W vs 120W)
Score
Benchmark
FP32 (float)
GeForce GTS 240 OEM
0.363 TFLOPS
Radeon HD 4670 AGP
+32%
0.48 TFLOPS
Graphics Card
Jul 2009
Release Date
Jul 2009
GeForce 200
Generation
Radeon R700
Desktop
Type
Desktop
PCIe 2.0 x16
Bus Interface
AGP 8x
Clock Speeds
-
-
-
-
-
-
1100 MHz
Memory Clock
800 MHz
Memory
1024MB
Memory Size
1024MB
GDDR3
Memory Type
GDDR3
256bit
Memory Bus
128bit
70.40GB/s
Bandwidth
25.60GB/s
Render Config
-
Compute Units
4
14
SM Count
-
112
Shading Units
320
56
TMUs
32
16
ROPs
8
-
-
-
-
-
-
-
L1 Cache
16 KB (per CU)
64 KB
L2 Cache
128 KB
-
-
-
Theoretical Performance
10.80 GPixel/s
Pixel Rate
6.000 GPixel/s
37.80 GTexel/s
Texture Rate
24.00 GTexel/s
-
-
-
362.9 GFLOPS
FP32 (float)
480.0 GFLOPS
-
-
-
Board Design
120W
TDP
59W
300 W
Suggested PSU
250 W
2x DVI
1x S-Video
Outputs
1x DVI
1x HDMI 1.3a
1x VGA
1x 6-pin
Power Connectors
-
Graphics Processor
G92B
GPU Name
RV730
G92-240-B1
GPU Variant
RV730 XT
(215-0719047)
Tesla
Architecture
TeraScale
TSMC
Foundry
TSMC
55 nm
Process Size
55 nm
0.754 billion
Transistors
0.514 billion
260 mm²
Die Size
146 mm²
Graphics Features
11.1 (10_0)
DirectX
10.1 (10_1)
3.3
OpenGL
3.3
1.1
OpenCL
1.1
N/A
Vulkan
N/A
1.1
CUDA
-
4.0
Shader Model
4.1
