GPUSPECINDEX

NVIDIA · Ampere · 2021

A30 GPU accelerator (PCIe card)

A30 GPU accelerator (PCIe card): 24 GB HBM2, 165 W, 3,584 CUDA cores. Launched April 12, 2021.

Memory
24 GB
Power
165 W
Bus width
3,072 bit
Memory24 GB9 of 32 in Data Center
Power165 W36 of 40 by higher draw in Data Center
CUDA cores3,58416 of 47 in Data Center

Affiliate links — we may earn a commission.

Memory

Capacity
24 GB
Memory type
HBM2
Bus width
3,072 bit
Bandwidth
933.1 GB/s

Compute

CUDA cores
3,584
SM count
56
TMUs
224
ROPs
96
FP32
10,320 GFLOPS
FP64
5,161 GFLOPS

Clocks

Base clock
930 MHz
Boost clock
1,440 MHz

Board

TDP
165 W
Form factor
datacenter

Physical

Architecture
Ampere
Series
Data Center
Launch date
April 12, 2021

Not recorded by the source: generation, codename, process and transistors, or 7 further fields.

Silicon, made visible

Die area is drawn against the largest recorded die in the catalog. Shader dots use a labeled, card-specific ratio so both early and modern GPUs remain legible.

Die size not recorded · 3,584 shadersDie size not recorded; shader grid shown without scale. Each dot = 32 shaders.3,584 shadersEach dot = 32 shadersDie size not recorded; shader grid shown without scale

Within its series, the A30 GPU accelerator (PCIe card) ranks 15th of 36 for FP32 throughput and 9th of 32 for memory capacity. Its 165 W TDP is above the 75 W PCIe slot-power ceiling.

Source: Wikipedia, revision 1369488585 · catalog loaded 2026-08-16