With NVIDIA’s Turing structure turning six years previous this yr, the corporate has been retiring lots of the remaining Turing merchandise from its video card lineup. And as we speak that spirit of spring cleansing is coming to the entry-level phase of NVIDIA’s skilled visualization lineup, the place NVIDIA is introducing a pair of latest desktop playing cards primarily based on their low-end Ampere {hardware}.
The new RTX A1000 and RTX A400 playing cards might be changing the T1000/T600/T400 lineup, which was launched three years in the past in 2021. The new playing cards slot into the identical entry-level class and at last end fleshing out the RTX A collection of proviz playing cards, providing NVIDIA’s Ampere-generation skilled graphics applied sciences within the lowest-power, lowest-performance, lowest-cost configuration attainable.
Notably, for the reason that entry-level T-series have been primarily based on NVIDIA’s feature-limited TU11x silicon, which lacked ray tracing and tensor core help – the idea of NVIDIA’s RTX applied sciences and related branding – this marks the primary time these applied sciences might be out there in NVIDIA’s entry-level desktop proviz playing cards. And accordingly, these are being promoted to RTX-branded video playing cards, ending the odd overlap with NVIDIA’s compute playing cards, which by no means carry RTX branding.
It goes with out saying that as low-end playing cards, the ray tracing efficiency of both half is nothing to put in writing residence about, but it surely offers NVIDIA’s present proviz lineup a constant set of graphics options from high to backside.
| NVIDIA Professional Visualization Card Specification Comparison | ||||||
| A1000 | A400 | T1000 | T400 | |||
| CUDA Cores | 2304 | 768 | 896 | 384 | ||
| Tensor Cores | 72 | 24 | N/A | N/A | ||
| Boost Clock | 1460MHz | 1755MHz | 1395MHz | 1425MHz | ||
| Memory Clock | 12Gbps GDDR6 | 12Gbps GDDR6 | 10Gbps GDDR6 | 10Gbps GDDR6 |
||
| Memory Bus Width | 128-bit | 64-bit | 128-bit | 64-bit | ||
| VRAM | 8GB | 4GB | 8GB | 4GB | ||
| Single Precision | 6.74 TFLOPS | 2.7 TFLOPS | 2.5 TFLOPS | 1.09 TFLOPS | ||
| Tensor Performance | 53.eight TFLOPS | 21.7 TFLOPS | N/A | N/A | ||
| TDP | 50W | 50W | 50W | 30W | ||
| Cooling | Active, SS | Active, SS | Active, SS | Active, SS | ||
| Outputs | 4x mDP 1.4a | 4x mDP 1.4a | 3x mDP 1.4a | |||
| GPU | GA107 | TU117 | ||||
| Architecture | Ampere | Turing | ||||
| Manufacturing Process | Samsung 8nm | TSMC 12nm | ||||
| Launch Date | 04/2024 | 05/2024 | 05/2021 | 05/2021 | ||
Both the A1000 and A400 are primarily based on the identical board design, with NVIDIA taking out any pretense of bodily characteristic differentiation this time round (T400 was lacking its 4th Mini DisplayPort). This means each playing cards are primarily based on the GA107 GPU, sporting completely different core and reminiscence configurations.
RTX A1000 is a not-quite-complete configuration of GA107, with 2304 CUDA cores and 72 tensor cores. This is paired with 8GB of GDDR6, which runs at 12Gbps, for a complete of 192GB/second of reminiscence bandwidth. The TDP of the cardboard is 50 Watts, matching its predecessor.
Meanwhile RTX A400 is much extra reduce down, providing a few third of the lively {hardware} on the GPU itself, and half the reminiscence bandwidth. On paper this provides it round 40% of T1000’s efficiency, and half the reminiscence bandwidth – or 96GB/second. Notably, regardless of the {hardware} cut-down, the official TDP remains to be 50 Watts, versus the 30 Watts of its predecessor. So at this level NVIDIA will quickly stop providing a desktop proviz card decrease than 50 Watts.
As famous earlier than, each playing cards in any other case characteristic the identical bodily design, with a half-height half-length (HHHL) board with lively cooling. As you’d count on from such low-TDP playing cards, these are single-slot cooler designs. Both playing cards characteristic a quartet of Mini DisplayPorts, with the identical DP 1.4a…
