As NVIDIA’s Turing architecture turns six this year, the company has retired many remaining Turing products from its graphics card lineup. That spring cleaning spirit is making its way into the entry-level portion of NVIDIA’s professional visualization lineup today, as NVIDIA launches two new desktop cards based on its low-end Ampere hardware.
The new RTX A1000 and RTX A400 cards will replace the T1000/T600/T400 series released three years ago in 2021. The new cards fall into the same entry-level category and finally round out the RTX A-Series lineup of graphics cards, delivering NVIDIA Ampere-generation professional graphics technology in the lowest power, lowest performance, lowest cost configurations.
Notably, since the entry-level T-Series is based on NVIDIA’s feature-limited TU11x chip, it lacks ray tracing and Tensor Core support (the foundation of NVIDIA’s RTX technology and related brands), marking the first time these technologies have been available on NVIDIA’s entry-level desktop proiz Card. As a result, these cards are promoted as RTX-branded cards, ending the odd overlap with NVIDIA compute cards, which never carry RTX branding.
It goes without saying that as a low-end card, any part of the ray tracing performance is nothing to write home about, but it gives NVIDIA’s current proiz range a consistent set of graphics features from top to bottom.
| NVIDIA Professional Visualization Card Specs Comparison | ||||||
| A1000 | A400 | T1000 | T400 | |||
| CUDA color | 2304 | Chapter 768 | 896 | Chapter 384 | ||
| tensor core | 72 | twenty four | not applicable | not applicable | ||
| boost clock | 1460 MHz | 1755 MHz | 1395 MHz | 1425 MHz | ||
| memory clock | 12GbpsGDDR6 | 12GbpsGDDR6 | 10Gbps GDDR6 | 10Gbps GDDR6 |
||
| memory bus width | 128 bit | 64 bit | 128 bit | 64 bit | ||
| Video memory | 8GB | 4GB | 8GB | 4GB | ||
| single precision | 6.74 teraflops | 2.7 teraflops | 2.5 teraflops | 1.09 teraflops | ||
| tensor performance | 53.8 teraflops | 21.7 teraflops | not applicable | not applicable | ||
| TDP | 50W | 50W | 50W | 30W | ||
| cool down | Active, SS | Active, SS | Active, SS | Active, SS | ||
| output | 4x mDP 1.4a | 4x mDP 1.4a | 3x mDP 1.4a | |||
| graphics processor | 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 based on the same motherboard design, and NVIDIA has given up on any pretense of physical feature differences this time around (the T400 lacks its 4th Mini DisplayPort). This means both cards are based on the GA107 GPU, with different core and memory configurations.
The RTX A1000 is a less complete configuration of the GA107, with 2304 CUDA cores and 72 tensor cores. Paired with 8GB GDDR6, the operating speed is 12Gbps, for a total of 192GB/second memory bandwidth. The card has a TDP of 50 watts, in line with its predecessor.
The RTX A400, meanwhile, is much less streamlined, offering about a third of the active hardware on the GPU itself, and half the memory bandwidth. Theoretically, this provides about 40% of the performance of the T1000, and half the memory bandwidth, at 96GB/sec. It’s worth noting that despite the reduced hardware, the official TDP is still 50 watts, compared to its predecessor’s 30 watts. As a result, NVIDIA will soon stop offering sub-50 watt desktop proiz cards.
As mentioned, both cards have the same physical design, using a half-height, half-length (HHHL) board with active cooling. As you’d expect from such a low TDP card, these are single-slot cooler designs. Both cards feature four Mini DisplayPorts with the same DP 1.4a capabilities we’ve seen in all NVIDIA products over the past few years.
Finally, video-focused users should note that the video capabilities of the A1000/A400 are slightly different. While the A1000 has access to both of the GA107’s NVDEC video decoding blocks, the A400 can only access a single block – another cut made to differentiate the two cards. Otherwise, both graphics cards have access to the GPU’s unique NVENC block.
According to NVIDIA, the RTX A1000 will be available starting today through its distribution partners. Meanwhile, the RTX A400 will hit distribution channels in May, with OEMs expected to start offering the cards as part of their pre-built systems this summer.