The popular diagnostic tool, AIDA64, has now added support for the faster, next-gen NVIDIA graphics card for 2022, Next GeForce RTX 4090.
AIDA64 adds support for NVIDIA’s flagship 2022, GeForce RTX 4090 . graphics card
The NVIDIA GeForce RTX 4090 will be the green team’s flagship offering this year, replacing the RTX 3090 that was launched nearly two years ago. Because the graphics card contains most of the files Device ID and information already leakedAIDA64 decided to support it at its last date The trial version (6.70.6033) is available for ite.
The tool states that it has added “GPU Information for NVIDIA GeForce RTX 4090 (AD102)” but does not say what the specific information is. It is very likely that raw parameters have been added to the device. The software is the first to add such support, even before GPU-z. The GeForce RTX 4090 specifically has a PCI ID ‘NVIDIA_DEV.2684’. Here are the release notes for the latest version of AIDA64:
- SMTP / TLS v1.2 Support
- GPU Information for AMD Radeon Pro W6600 (Navi 23)
- GPU Information for nVIDIA GeForce GTX 1630 (TU117)
- GPU Information for nVIDIA GeForce RTX 4090 (AD102)
- GPU Information for nVIDIA H100 96GB (GH100)
- Improved support for Intel Alder Lake-M/P . CPU
- Sensor information for Asus Pro B550M-C Series motherboard
- Sensor information for MSI B650, X670, X670E series motherboard
- Sensor information for MSI MS-7D66 motherboard
- Fixed: System stability test/average throttling computation
- Fixed: AMD GPU enumeration with multiple GPUs
- Fixed: Select Intel Core i5-9300HF (aka Coffee Lake-H)
- Fixed: Select Intel Core i7-9750HF (aka Coffee Lake-H)
- Removed: Intel PCH Diode Temperature Measurement on Jginyue X99M-Plus V2
NVIDIA GeForce RTX 4090 “Rumored” Specifications
The NVIDIA GeForce RTX RTX 4090 graphics card is expected to be powered by the top-of-the-line AD102-300 GPU, but only the “Ti” variant will feature the full chip. The Geforce RTX 4090 will use a slightly reduced configuration.
The NVIDIA GeForce RTX 4090 will use 128 SMs from the 144 SMs for a total of 16,384 CUDA cores. The GPU will be equipped with 96MB of L2 cache and a total of 384 ROPs which is simply insane. Clock speeds haven’t been confirmed yet, but given that the TSMC 4N process is in use, we’d expect clocks in the 2.0-3.0GHz range.
As for the memory specs, the GeForce RTX 4090 is expected to have 24GB GDDR6X capacities which will be clocked at 21Gbps via the 384-bit bus interface. This will save up to 1 TB/sec of bandwidth. This is the same bandwidth as the current RTX 3090 Ti graphics card and as far as power consumption is concerned, the TBP is said to be rated at 450W which means the TGP could end up being lower than that. The card will be powered by a single 16-pin connector that delivers up to 600 watts of power. Chances are we might get custom 500W+ builds as we saw with the RTX 3090 Ti.
The graphics card is expected to be released in October 2022 and the rest of the Ada Lovelace GPU-powered family of graphics cards will follow.
NVIDIA GeForce RTX 4090 Ti & RTX 4090 “Raw” Specifications:
Graphics card name | NVIDIA GeForce RTX 4090 Ti | NVIDIA GeForce RTX 4090 | NVIDIA GeForce RTX 3090 Ti | NVIDIA GeForce RTX 3090 |
---|---|---|---|---|
GPU name | Ada Lovelace AD102-350? | Ada Lovelace AD102-300? | GA102-350 . ampere | GA102-300 . ampere |
Operation knot | TSMC 4N | TSMC 4N | Samsung 8nm | Samsung 8nm |
die size | ~ 600 mm 2 | ~ 600 mm 2 | 628.4 mm 2 | 628.4 mm 2 |
transistors | to be announced later on | to be announced later on | 28 billion | 28 billion |
CUDA cores | 18432 | 16128 | 10752 | 10496 |
TMUs / ROPs | TBD / 384 | TBD / 384 | 336/112 | 328/112 |
tensor/RT cores | TBD / TBD | TBD / TBD | 336/84 | 328/82 |
base clock | to be announced later on | to be announced later on | 1560 MHz | 1400 MHz |
increase the clock | ~2800MHz | ~2600MHz | 1860 MHz | 1700 MHz |
FP32 account | ~103 TFLOPs | ~90 TFLOPs | 40 TFLOPs | 36 TFLOPs |
RT TFLOPs | to be announced later on | to be announced later on | 74 TFLOPs | 69 TFLOPs |
Tensor-TOPs | to be announced later on | to be announced later on | 320 higher | 285 peak |
Memory capacity | 24 GB GDDR6X | 24 GB GDDR6X | 24 GB GDDR6X | 24 GB GDDR6X |
Memory bus | 384 bit | 384 bit | 384 bit | 384 bit |
Memory speed | 24.0 Gbps | 21.0 Gbps | 21.0 Gbps | 19.5 Gbps |
Bandwidth | 1152 GB/sec | 1008 GB/sec | 1008 GB/sec | 936 Gbps |
TGP | 600 watts | 450 watts | 450 watts | 350 watts |
Price (MSRP/FE) | 1999 US dollars? | 1499 US dollars? | 1999 US dollars | 1499 USD |
launch (availability) | 2023? | October 2022? | March 29, 2022 | September 24, 2020 |
Products mentioned in this post
“Unapologetic communicator. Wannabe web lover. Friendly travel scholar. Problem solver. Amateur social mediaholic.”