GPU Comparison
RADEON
AMD Radeon RX 640 OEM
CORE STATE
Polaris 23
VRAM
4 GB
CLOCK SPEED
—
TDP
50 W
BUS WIDTH
128 bit
ARCHITECTURE
GCN 4.0
PROCESS
14 nm
LAUNCH DATE
2020
VS
GEFORCE
RTX A5000-8Q
CORE STATE
GA102
VRAM
8 GB
CLOCK SPEED
1695 MHz
TDP
230 W
BUS WIDTH
384 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2021
DETAILED SPECIFICATIONS
SPECIFICATION
RX 640 OEM
RTX A5000-8Q
Core Specs
Shading Units
640
8,192
+1180.0%
Shaders
640
8,192
+1180.0%
TMUs
40
256
+540.0%
ROPs
16
96
+500.0%
Compute Units
10
—
SM Count
—
64
Clocks
Base Clock
—
1170 MHz
Boost Clock
—
1695 MHz
GPU Clock
1295 MHz
—
Memory Clock
1500 MHz
6 Gbps effective
2000 MHz
16 Gbps effective
Memory
Memory Size
4 GB
8 GB
VRAM (MB)
4,096
8,192
+100.0%
Memory Type
GDDR5
GDDR6
Memory Bus
128 bit
384 bit
Bandwidth
96.00 GB/s
768.0 GB/s
Cache
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
512 KB
6 MB
Performance
Pixel Rate
20.72 GPixel/s
162.7 GPixel/s
Texture Rate
51.80 GTexel/s
433.9 GTexel/s
FP32 (TFLOPS)
1.658 TFLOPS
27.77 TFLOPS
FP64 (TFLOPS)
103.6 GFLOPS (1:16)
433.9 GFLOPS (1:64)
FP16 (TFLOPS)
1.658 TFLOPS (1:1)
27.77 TFLOPS (1:1)
AI/RT
RT Cores
—
64
Tensor Cores
—
256
Power
TDP
50 W
230 W
TDP (W)
50
230
+360.0%
Suggested PSU
250 W
550 W
Power Connectors
None
1x 8-pin
Architecture
Architecture
GCN 4.0
Ampere
GPU Name
Polaris 23
GA102
Generation
Polaris
(RX 600)
Workstation Ampere
(Ax000)
Process Size
14 nm
8 nm
Transistors
2,200 million
28,300 million
Die Size
103 mm²
628 mm²
Foundry
GlobalFoundries
Samsung
Density
21.4M / mm²
45.1M / mm²
API Support
DirectX
12 (12_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.3
1.4
OpenCL
2.1
3.0
CUDA
—
8.6
Shader Model
6.7
6.8
Physical
Slot Width
Single-slot
Dual-slot
Length
—
267 mm
10.5 inches
Height
—
112 mm
4.4 inches
Outputs
1x DisplayPort 1.4a2x mini-DisplayPort 1.4a
4x DisplayPort 1.4a
Bus Interface
PCIe 3.0 x8
PCIe 4.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
Polaris
Quadro Turing
Successor
Vega
Workstation Ada