Performance Rating
NVIDIA A100 PCIe 80 GB outperforms GALAX GTX 980 Ti HOF by 366.85% in the overall GPU ARK performance rating
NVIDIA A100 PCIe 80 GB
Expert Comparison
GALAX GTX 980 Ti HOF более подходящий для игр и базовых вычислений, благодаря своему более низкому энергопотреблению (250 Вт) и более доступной памяти (6 ГБ). NVIDIA A100 PCIe 80 GB же значительно превосходит по производительности (1.94 TB/s против 336.6 GB/s), особенно в вычислительных задачах и AI, благодаря большей памяти (80 ГБ) и более новой архитектуре Ampere.
Contents:
Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering AdditionalMemory
Memory Size
+1,233%
80
ГБ
Memory Type
Memory Bandwidth
1.94 TB/s
Memory Bus Width
ML Performance
FP16 (Half Precision)
77.97
TFLOPS
BF16 (Brain Float)
311.84
TFLOPS
TF32 (TensorFloat)
155.92
Compute Power
FP32 (Single Precision)
+168%
19.49
TFLOPS
FP64 (Double Precision)
+4,190%
9.746
TFLOPS
CUDA Cores
+145%
6,912
RT Cores
Architecture & Compatibility
GPU Architecture
SM (Streaming Multiprocessor)
108
PCIe Version
ML Software Support
CUDA Version
8.0
CUDA Toolkit (first supported)
CUDA Toolkit (deprecated)
CUDA Toolkit (support removed)
CUDA Toolkit status
Clocks & Performance
Base Clock
1,065
Boost Clock
+9%
1,410
Memory Clock
1,512
Power Consumption
Recommended PSU
-14%
600 W
Power Connector
TDP/TGP
-17%
250 W
Rendering
Texture Units (TMU)
+145%
432
ROP
L2 Cache
+2,567%
80 MB
Additional
Slots
Release Date
Display Outputs
Rent on Intelion Cloud
Available for rent on Intelion Cloud
