GPU Comparison
RADEON
ATI Radeon HD 2350 PRO
CORE STATE
RV610
VRAM
256 MB
CLOCK SPEED
—
TDP
20 W
BUS WIDTH
64 bit
ARCHITECTURE
TeraScale
PROCESS
65 nm
LAUNCH DATE
—
VS
GEFORCE
GeForce RTX 5090
CORE STATE
GB202
VRAM
32 GB
CLOCK SPEED
2407 MHz
TDP
575 W
BUS WIDTH
512 bit
ARCHITECTURE
Blackwell 2.0
PROCESS
5 nm
LAUNCH DATE
2025
PERFORMANCE BENCHMARKS
3dmark_3dmark_steel_nomad_dx12
geekbench_opencl
geekbench_vulkan
passmark_directx_10
passmark_directx_11
passmark_directx_12
passmark_directx_9
passmark_g2d
passmark_g3d
passmark_gpu_compute
DETAILED SPECIFICATIONS
SPECIFICATION
ATI Radeon HD 2350 PRO
RTX 5090
Core Specs
Shading Units
40
21,760
+54300.0%
Shaders
40
21,760
+54300.0%
TMUs
4
680
+16900.0%
ROPs
4
176
+4300.0%
Compute Units
2
—
SM Count
—
170
Clocks
Base Clock
—
2017 MHz
Boost Clock
—
2407 MHz
GPU Clock
525 MHz
—
Memory Clock
400 MHz
800 Mbps effective
1750 MHz
28 Gbps effective
Memory
Memory Size
256 MB
32 GB
VRAM (MB)
256
32,768
+12700.0%
Memory Type
DDR2
GDDR7
Memory Bus
64 bit
512 bit
Bandwidth
6.400 GB/s
1.79 TB/s
Cache
L1 Cache
—
128 KB (per SM)
L2 Cache
32 KB
96 MB
Performance
Pixel Rate
2.100 GPixel/s
423.6 GPixel/s
Texture Rate
2.100 GTexel/s
1,636.8 GTexel/s
FP32 (TFLOPS)
42.00 GFLOPS
104.8 TFLOPS
FP64 (TFLOPS)
—
1.637 TFLOPS (1:64)
FP16 (TFLOPS)
—
104.8 TFLOPS (1:1)
AI/RT
RT Cores
—
170
Tensor Cores
—
680
Power
TDP
20 W
575 W
TDP (W)
20
575
+2775.0%
Suggested PSU
200 W
950 W
Power Connectors
None
1x 16-pin
Architecture
Architecture
TeraScale
Blackwell 2.0
GPU Name
RV610
GB202
Generation
Radeon R600
(HD 2400)
GeForce 50
Process Size
65 nm
5 nm
Transistors
180 million
92,200 million
Die Size
85 mm²
750 mm²
Foundry
TSMC
TSMC
Density
2.1M / mm²
122.9M / mm²
API Support
DirectX
10.0 (10_0)
12 Ultimate (12_2)
OpenGL
3.3
4.6
Vulkan
—
1.4
OpenCL
—
3.0
CUDA
—
12.0
Shader Model
4.0
6.8
Physical
Slot Width
Single-slot
Dual-slot
Length
—
304 mm
12 inches
Height
—
137 mm
5.4 inches
Outputs
1x DVI1x S-Video
1x HDMI 2.1b3x DisplayPort 2.1b
Bus Interface
PCIe 1.0 x16
PCIe 5.0 x16
Other
Launch Price
—
1,999 USD
Production
End-of-life
Active
Predecessor
Radeon R500 PCIe
GeForce 40
Successor
Radeon R700
—