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
Tesla K40m
CORE STATE
GK110B
VRAM
12 GB
CLOCK SPEED
876 MHz
TDP
245 W
BUS WIDTH
384 bit
ARCHITECTURE
Kepler
PROCESS
28 nm
LAUNCH DATE
2013
PERFORMANCE BENCHMARKS
geekbench_opencl
DETAILED SPECIFICATIONS
SPECIFICATION
RX 640 OEM
Tesla K40m
Core Specs
Shading Units
640
2,880
+350.0%
Shaders
640
2,880
+350.0%
TMUs
40
240
+500.0%
ROPs
16
48
+200.0%
Compute Units
10
—
Clocks
Base Clock
—
745 MHz
Boost Clock
—
876 MHz
GPU Clock
1295 MHz
—
Memory Clock
1500 MHz
6 Gbps effective
1502 MHz
6 Gbps effective
Memory
Memory Size
4 GB
12 GB
VRAM (MB)
4,096
12,288
+200.0%
Memory Type
GDDR5
GDDR5
Memory Bus
128 bit
384 bit
Bandwidth
96.00 GB/s
288.4 GB/s
Cache
L1 Cache
16 KB (per CU)
16 KB (per SMX)
L2 Cache
512 KB
1536 KB
Performance
Pixel Rate
20.72 GPixel/s
52.56 GPixel/s
Texture Rate
51.80 GTexel/s
210.2 GTexel/s
FP32 (TFLOPS)
1.658 TFLOPS
5.046 TFLOPS
FP64 (TFLOPS)
103.6 GFLOPS (1:16)
1.682 TFLOPS (1:3)
FP16 (TFLOPS)
1.658 TFLOPS (1:1)
—
Power
TDP
50 W
245 W
TDP (W)
50
245
+390.0%
Suggested PSU
250 W
550 W
Power Connectors
None
—
Architecture
Architecture
GCN 4.0
Kepler
GPU Name
Polaris 23
GK110B
Generation
Polaris
(RX 600)
Tesla Kepler
(Kxx)
Process Size
14 nm
28 nm
Transistors
2,200 million
7,080 million
Die Size
103 mm²
561 mm²
Foundry
GlobalFoundries
TSMC
Density
21.4M / mm²
12.6M / mm²
API Support
DirectX
12 (12_0)
12 (11_1)
OpenGL
4.6
4.6
Vulkan
1.3
1.2.175
OpenCL
2.1
3.0
CUDA
—
3.5
Shader Model
6.7
6.5 (5.1)
Physical
Slot Width
Single-slot
Dual-slot
Length
—
267 mm
10.5 inches
Outputs
1x DisplayPort 1.4a2x mini-DisplayPort 1.4a
No outputs
Bus Interface
PCIe 3.0 x8
PCIe 3.0 x16
Other
Launch Price
—
7,699 USD
Production
End-of-life
End-of-life
Predecessor
Polaris
Tesla Fermi
Successor
Vega
Tesla Maxwell