GPU Comparison
RADEON
AMD Radeon RX Vega M GL
CORE STATE
Polaris 22
VRAM
4 GB
CLOCK SPEED
1011 MHz
TDP
65 W
BUS WIDTH
1024 bit
ARCHITECTURE
GCN 4.0
PROCESS
14 nm
LAUNCH DATE
2018
VS
GEFORCE
Quadro GV100
CORE STATE
GV100
VRAM
32 GB
CLOCK SPEED
1627 MHz
TDP
250 W
BUS WIDTH
4096 bit
ARCHITECTURE
Volta
PROCESS
12 nm
LAUNCH DATE
2018
PERFORMANCE BENCHMARKS
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
RX Vega M GL
Quadro GV100
Core Specs
Shading Units
1,280
5,120
+300.0%
Shaders
1,280
5,120
+300.0%
TMUs
80
320
+300.0%
ROPs
32
128
+300.0%
Compute Units
20
—
SM Count
—
80
Clocks
Base Clock
931 MHz
1132 MHz
Boost Clock
1011 MHz
1627 MHz
Memory Clock
700 MHz
1400 Mbps effective
848 MHz
1696 Mbps effective
Memory
Memory Size
4 GB
32 GB
VRAM (MB)
4,096
32,768
+700.0%
Memory Type
HBM2
HBM2
Memory Bus
1024 bit
4096 bit
Bandwidth
179.2 GB/s
868.4 GB/s
Cache
L1 Cache
16 KB (per CU)
128 KB (per SM)
L2 Cache
1024 KB
6 MB
Performance
Pixel Rate
32.35 GPixel/s
208.3 GPixel/s
Texture Rate
80.88 GTexel/s
520.6 GTexel/s
FP32 (TFLOPS)
2.588 TFLOPS
16.66 TFLOPS
FP64 (TFLOPS)
161.8 GFLOPS (1:16)
8.330 TFLOPS (1:2)
FP16 (TFLOPS)
2.588 TFLOPS (1:1)
33.32 TFLOPS (2:1)
AI/RT
Tensor Cores
—
640
Power
TDP
65 W
250 W
TDP (W)
65
250
+284.6%
Suggested PSU
—
600 W
Power Connectors
—
1x 8-pin
Architecture
Architecture
GCN 4.0
Volta
GPU Name
Polaris 22
GV100
Generation
Vega
(Vega M)
Quadro Volta
(Vx000)
Process Size
14 nm
12 nm
Transistors
5,000 million
21,100 million
Die Size
208 mm²
815 mm²
Foundry
GlobalFoundries
TSMC
Density
24.0M / mm²
25.9M / mm²
API Support
DirectX
12 (12_0)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.3
1.4
OpenCL
2.1
3.0
CUDA
—
7.0
Shader Model
6.7
6.8
Physical
Slot Width
IGP
Dual-slot
Length
—
267 mm
10.5 inches
Height
—
111 mm
4.4 inches
Outputs
Portable Device Dependent
4x DisplayPort 1.4a
Bus Interface
IGP
PCIe 3.0 x16
Other
Launch Price
—
8,999 USD
Production
End-of-life
End-of-life
Predecessor
—
Quadro Pascal
Successor
—
Quadro Turing