GPU Comparison
RADEON
AMD Radeon RX Vega M GH
CORE STATE
Polaris 22
VRAM
4 GB
CLOCK SPEED
1190 MHz
TDP
100 W
BUS WIDTH
1024 bit
ARCHITECTURE
GCN 4.0
PROCESS
14 nm
LAUNCH DATE
2018
VS
GEFORCE
L4
CORE STATE
AD104
VRAM
24 GB
CLOCK SPEED
2040 MHz
TDP
72 W
BUS WIDTH
192 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2023
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
RX Vega M GH
L4
Core Specs
Shading Units
1,536
7,424
+383.3%
Shaders
1,536
7,424
+383.3%
TMUs
96
240
+150.0%
ROPs
64
80
+25.0%
Compute Units
24
—
SM Count
—
60
Clocks
Base Clock
1063 MHz
795 MHz
Boost Clock
1190 MHz
2040 MHz
Memory Clock
800 MHz
1600 Mbps effective
1563 MHz
12.5 Gbps effective
Memory
Memory Size
4 GB
24 GB
VRAM (MB)
4,096
24,576
+500.0%
Memory Type
HBM2
GDDR6
Memory Bus
1024 bit
192 bit
Bandwidth
204.8 GB/s
300.1 GB/s
Cache
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
1024 KB
48 MB
Performance
Pixel Rate
76.16 GPixel/s
163.2 GPixel/s
Texture Rate
114.2 GTexel/s
489.6 GTexel/s
FP32 (TFLOPS)
3.656 TFLOPS
30.29 TFLOPS
FP64 (TFLOPS)
228.5 GFLOPS (1:16)
473.3 GFLOPS (1:64)
FP16 (TFLOPS)
3.656 TFLOPS (1:1)
30.29 TFLOPS (1:1)
AI/RT
RT Cores
—
60
Tensor Cores
—
240
Power
TDP
100 W
72 W
TDP (W)
100
72
-28.0%
Suggested PSU
—
250 W
Power Connectors
—
None
Architecture
Architecture
GCN 4.0
Ada Lovelace
GPU Name
Polaris 22
AD104
Generation
Vega
(Vega M)
Server Ada
(Lxx)
Process Size
14 nm
5 nm
Transistors
5,000 million
35,800 million
Die Size
208 mm²
294 mm²
Foundry
GlobalFoundries
TSMC
Density
24.0M / 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
IGP
Single-slot
Length
—
169 mm
6.7 inches
Height
—
56 mm
2.2 inches
Outputs
Portable Device Dependent
No outputs
Bus Interface
IGP
PCIe 4.0 x16
Other
Production
End-of-life
Active
Predecessor
—
Server Ampere
Successor
—
Server Hopper