GPU Comparison
RADEON
AMD Radeon 540
CORE STATE
Lexa
VRAM
1024 MB
CLOCK SPEED
—
TDP
50 W
BUS WIDTH
32 bit
ARCHITECTURE
GCN 4.0
PROCESS
14 nm
LAUNCH DATE
2017
VS
GEFORCE
RTX 4000 Ada Generation
CORE STATE
AD104
VRAM
20 GB
CLOCK SPEED
2175 MHz
TDP
130 W
BUS WIDTH
160 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2023
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
540
RTX 4000 Ada Generation
Core Specs
Shading Units
384
6,144
+1500.0%
Shaders
384
6,144
+1500.0%
TMUs
24
192
+700.0%
ROPs
16
64
+300.0%
Compute Units
6
—
SM Count
—
48
Clocks
Base Clock
—
1500 MHz
Boost Clock
—
2175 MHz
GPU Clock
1183 MHz
—
Memory Clock
1500 MHz
6 Gbps effective
2250 MHz
18 Gbps effective
Memory
Memory Size
1024 MB
20 GB
VRAM (MB)
1,024
20,480
+1900.0%
Memory Type
GDDR5
GDDR6
Memory Bus
32 bit
160 bit
Bandwidth
24.00 GB/s
360.0 GB/s
Cache
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
512 KB
48 MB
Performance
Pixel Rate
18.93 GPixel/s
139.2 GPixel/s
Texture Rate
28.39 GTexel/s
417.6 GTexel/s
FP32 (TFLOPS)
908.5 GFLOPS
26.73 TFLOPS
FP64 (TFLOPS)
56.78 GFLOPS (1:16)
417.6 GFLOPS (1:64)
FP16 (TFLOPS)
908.5 GFLOPS (1:1)
26.73 TFLOPS (1:1)
AI/RT
RT Cores
—
48
Tensor Cores
—
192
Power
TDP
50 W
130 W
TDP (W)
50
130
+160.0%
Suggested PSU
250 W
300 W
Power Connectors
None
1x 16-pin
Architecture
Architecture
GCN 4.0
Ada Lovelace
GPU Name
Lexa
AD104
Generation
Polaris
(RX 500)
Workstation Ada
(x000A)
Process Size
14 nm
5 nm
Transistors
2,200 million
35,800 million
Die Size
103 mm²
294 mm²
Foundry
GlobalFoundries
TSMC
Density
21.4M / mm²
121.8M / 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
—
8.9
Shader Model
6.7
6.8
Physical
Slot Width
Single-slot
Single-slot
Length
—
245 mm
9.6 inches
Height
—
112 mm
4.4 inches
Outputs
2x DisplayPort 1.4a
4x DisplayPort 1.4a
Bus Interface
PCIe 3.0 x8
PCIe 4.0 x16
Other
Production
End-of-life
Active
Predecessor
Arctic Islands
Workstation Ampere
Successor
Vega
Blackwell PRO W