GPU Comparison
GEFORCE
NVIDIA CMP 70HX
CORE STATE
GA104
VRAM
8 GB
CLOCK SPEED
1395 MHz
TDP
—
BUS WIDTH
256 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
—
VS
GEFORCE
PG506-232
CORE STATE
GA100
VRAM
24 GB
CLOCK SPEED
1440 MHz
TDP
165 W
BUS WIDTH
3072 bit
ARCHITECTURE
Ampere
PROCESS
7 nm
LAUNCH DATE
2021
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
CMP 70HX
PG506-232
Core Specs
Shading Units
3,840
3,584
-6.7%
Shaders
3,840
3,584
-6.7%
TMUs
120
224
+86.7%
ROPs
64
96
+50.0%
SM Count
30
56
+86.7%
Clocks
Base Clock
1365 MHz
930 MHz
Boost Clock
1395 MHz
1440 MHz
Memory Clock
1188 MHz
19 Gbps effective
1215 MHz
2.4 Gbps effective
Memory
Memory Size
8 GB
24 GB
VRAM (MB)
8,192
24,576
+200.0%
Memory Type
GDDR6X
HBM2
Memory Bus
256 bit
3072 bit
Bandwidth
608.3 GB/s
933.1 GB/s
Cache
L1 Cache
128 KB (per SM)
192 KB (per SM)
L2 Cache
4 MB
24 MB
Performance
Pixel Rate
89.28 GPixel/s
138.2 GPixel/s
Texture Rate
167.4 GTexel/s
322.6 GTexel/s
FP32 (TFLOPS)
10.71 TFLOPS
10.32 TFLOPS
FP64 (TFLOPS)
167.4 GFLOPS (1:64)
5.161 TFLOPS (1:2)
FP16 (TFLOPS)
10.71 TFLOPS (1:1)
10.32 TFLOPS (1:1)
AI/RT
RT Cores
30
—
Tensor Cores
120
224
+86.7%
Power
TDP
—
165 W
TDP (W)
—
165
Suggested PSU
200 W
450 W
Power Connectors
1x 12-pin
8-pin EPS
Architecture
Architecture
Ampere
Ampere
GPU Name
GA104
GA100
Generation
Mining GPUs
Server Ampere
(Axx)
Process Size
8 nm
7 nm
Transistors
17,400 million
54,200 million
Die Size
392 mm²
826 mm²
Foundry
Samsung
TSMC
Density
44.4M / mm²
65.6M / mm²
API Support
DirectX
12 Ultimate (12_2)
—
OpenGL
4.6
—
Vulkan
1.4
—
OpenCL
3.0
3.0
CUDA
8.6
8.0
Shader Model
6.8
—
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm
10.5 inches
267 mm
10.5 inches
Height
112 mm
4.4 inches
112 mm
4.4 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 1.0 x4
PCIe 4.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
—
Tesla Turing
Successor
—
Server Ada