PG506-242

Key Metrics

Save this GPU, then open another GPU page to compare them side by side.

Identity
Entry Type	Reference GPU
Official Name	NVIDIA PG506-242
GPU Codename	GA100
Architecture	Ampere
Launch Date	2021-04-12
Market Segment Notes	Desktop in NVIDIA A-Series
Core Specs
GPU Die	GA100
Chip Variant / Package	BGA-2743
Process Node	TSMC 7 nm
Transistor Count	54.2 billion
Die Size	826 mm²
CUDA Cores	3584
SM Count	56
TMUs	224
ROPs	96
AI Units / Tensor Cores	224
Base Clock	930 MHz
Boost Clock	1,440 MHz
Pixel Fillrate	138.2 GP/s
Texture Fillrate	322.6 GT/s
FP32 Throughput	10.32 TFLOPS
FP16 Throughput	10.32 TFLOPS
FP64 Throughput	5.16 TFLOPS
Memory
Memory Size	24 GB
Memory Type	HBM2
Memory Bus Width	3,072-bit
Memory Clock	1,215 MHz
Memory Bandwidth	933.1 GB/s
L2 Cache	24 MB
L1 Cache	192 KB
Board and Display
TDP / TBP	165 W
Recommended PSU	450 W
Power Connectors	8-pin EPS
Interface	PCIe 4.0 x16
Slot Width	Dual-slot, 267 mm length
Card Length	267 mm
Board Partner Model	Reference or OEM specification
Reference Design	NVIDIA reference design
Software
CUDA Compute Capability	8.0
OpenCL Support	OpenCL 3.0

Sources

TechPowerUp GPU SpecsModel-level specification reference for this GPU entryOpen source

RightNow GPU DatabaseOpen GPU database used to cross-check specifications A reference database: good for cross-checking specifications, but not proof of the original release details on its own.Open source