Tech outlet Angstronomics has a very detailed roundup published regarding the specifications of AMD’s RDNA 3 GPUs such as the Navi 31, Navi 32, and Navi 33 chips that will go on to power their next-gen Radeon RX 7000 series graphics cards.
AMD Navi 31, Navi 32, Navi 33 “RDNA 3” GPUs For Radeon RX 7000 Series Graphics Cards Detailed
Previously leaked information within the Linux patches has revealed that there are going to be at least four RDNA 3 IPs that will be launched for the consumer segment. These include Navi 31, Navi 32, Navi 33, and an APU design.
GC IP VER | GFX ID | AMDGPU_FAMILY (via Coelacanth-Dream) | TYPE |
---|---|---|---|
11.0.0 | gfx1100 (Navi31)1 | AMDGPU_FAMILY_GC_11_0_0 (FAMILY_GFX1100) | dGPU |
11.0.1 | gfx1103 | AMDGPU_FAMILY_GC_11_0_2 (FAMILY_GFX1103) | APU |
11.0.2 | gfx1102 (Navi32) | AMDGPU_FAMILY_GC_11_0_0 (FAMILY_GFX1100) | dGPU |
11.0.3? | gfx1101 (Navi33)? | AMDGPU_FAMILY_GC_11_0_0 (FAMILY_GFX1100)? | dGPU? |
Now Angstronomics has reported information such as die sizes, GPU configurations, and features that may end up in the final retail products. An interesting statement by the tech outlet has been made which reveals that configurations for Navi 3X GPUs were first formulated in 2019 and then finalized sometime in 2020. These specifications have not been changed since however, various rumors have pointed out two different specifications for the GPUs which means that either AMD has in fact made changes since their final designs or those rumors were simply not aligned with the truth. With that said, let’s see what sort of configurations we can expect with the Navi 3x “RDNA 3” GPU lineup.
AMD confirmed that its RDNA 3 GPUs will be coming later this year with a huge performance uplift. The company’s Senior Vice President of Engineering, Radeon Technologies Group, David Wang, said that the next-gen GPUs for Radeon RX 7000 series will offer over 50% performance per watt uplift vs the existing RDNA 2 GPUs. Some of the key features of the RDNA 3 GPUs highlighted by AMD will include:
- 5nm Process Node
- Advanced Chiplet Packaging
- Rearchitected Compute Unit
- Optimized Graphics Pipeline
- Next-Gen AMD Infinity Cache
- >50% Perf/Watt vs RDNA 2
Gamers should expect fluid 4K gaming to be buttery smooth on these graphics cards and with the FidelityFX suite offering next-gen FSR, SAS, and SAM support, we might even see playable 60 FPS at 8K resolution.
AMD Navi 31 “Plum Bonito” GPU Configuration
The AMD Navi 31 GPU, the flagship RDNA 3 chip, would power the next-gen enthusiast cards such as the Radeon RX 7900 XT graphics card. We have heard that AMD will drop CU (Compute Units) in favor of WGP (Work Group Processors) on its next-gen RDNA 3 GPUs. Each WGP will house dual CU (Compute Units) but with twice the SIMD32 clusters as opposed to just 2 on each CU within RDNA 2. Rumors are that AMD has the option to select between Samsung and TSMC for the 6nm die.
- AMD Navi 31: 12288 Cores, 384-bit Bus, 192 MB Infinity Cache, 308mm2 GPU Die @5nm
- AMD Navi 21: 5120 Cores, 384-bit Bus, 128 MB Infinity Cache, 520mm2 GPU Die @7nm
According to the latest information, the AMD Navi 31 GPU with RDNA 3 architecture is expected to offer a single GCD with 48 WGPs, 12 SAs, and 6 SEs. This will give out a total of 12,288 SPs or stream processors. This is an increase of 2.4x in cores compared to the 5120 SPs featured on the Navi 21 GPU. The GPU or the Navi 31 GCD is said to measure 308mm2 and will come packaged on TSMC’s 5nm process node.
The Navi 31 GPU will also carry 6 MCD’s which will feature 16 MB Infinity Cache per die and are also likely to carry the 64-bit (32-bit x 2) memory controllers that will provide the chip with a 384-bit bus interface. While this equals 96 MB of Infinity Cache which is lower than the 128 MB featured on the current Navi 21 GPUs, there’s also a 3D-Stacked solution in the works which was pointed out recently and that would double the Infinity Cache with 32 MB (16 MB 0-hi + 16 MB 1-hi) capacities for a total of 192 MB of cache. This is a 50% increase versus the current Navi 21 design and it also makes Navi 31 the first GPU with both, chiplet and 3D stacked designs. These chiplets or MCD’s will be fabricated on TSMC’s 6nm process node and measure 37.5mm2 each.
The outlet reports that there was an even higher 288 MB (16 MB 0-Hi + 16 MB 1-Hi + 16 MB 2-Hi) MCD package planned but that was scrapped due to cost-benefit reasons. There are also talks of a cut-down variant of the Navi 31 GPU which will feature 42 WGPs or 10,752 cores and 5 MCDs for 80MB Infinity Cache across a 320-bit bus interface.
Now, this is going to result in higher power draw and AMD seems to have confirmed this much that their next-generation graphics card lineup will feature higher power consumption but they will still be a more efficient option than what NVIDIA has to offer. The AMD Radeon RX 6950 XT already has a TBP of 335W so for a >2x performance gain. The cards are expected to retain their dual 8-pin plug input for power and feature an updated triple-fan cooling design which is slightly taller than the one currently in use.
AMD Navi 32 “Wheat Nas” GPU Configuration
The AMD Navi 32 GPU codenamed “Wheat Nas” is also one of the two MCM GPUs featured in the RDNA 3 lineup. The GPU will feature a single GCD (Graphics Compute Dies) and four MCDs (Multi-Cache Die). The GPU or GCD is said to measure 200mm2 while each MCD will retain the same size at 37.5mm2.
- AMD Navi 32: 7680 Cores, 256-bit Bus, 64 MB Infinity Cache, 200mm2 GPU Die @5nm
- AMD Navi 22: 2560 Cores, 192-bit Bus, 96 MB Infinity Cache, 335mm2 GPU Die @7nm
The GCD will be equipped with 3 Shader Engines and each Shader Engine has 6 Shader Arrays (18 in total). The GPU will feature a total of 30 WGP or 60 Compute Units for a total of 7680 cores. This rounds up to >50% more cores than the Navi 31 flagship.
Each MCD should also feature 2 memory connect links (32-bit). That’s a total of 8 32-bit memory controllers for a 256-bit bus interface. Each MCD will retain the 16 MB 0-Hi capacity but there does not seem to be any 1-Hi variant which means that the chip will have just 64 MB maximum configs. That Navi 32 GPU is said to launch in 2023 and will be the highest chip for mobile and mid-tier chip for desktops. The GPU would be first rolled out to the mobile segment and might be announced at CES 2023 which makes ideal sense since we will have Phoenix Range and Dragon Range laptops with Zen 4 cores ready by then.
AMD Navi 32 “Hotpink Bonefish” GPU Configuration
The AMD Navi 33 GPU codenamed “Hotpink Bonefish” will start the monolithic segment within the RDNA 3 family. The GPU will feature a single die. The die is very similar to the flagship Navi 21 GPU and is expected to utilize a 6nm process node for fabrication with a die size of 203mm2.
- AMD Navi 33: 4096 Cores, 128-bit Bus, 32 MB Infinity Cache, 335mm2 GPU Die @6nm
- AMD Navi 23: 2048 Cores, 128-bit Bus, 32 MB Infinity Cache, 237mm2 GPU Die @7nm
The Navi 33 GCD is expected to feature 2 Shader Engines and each Shader Engine has 2 Shader Arrays (2 per SE / 4 in total). This rounds up to 16 WGP’s or 32 Compute Units for a total of 4096 cores which is higher than the Radeon RX 6800 “Navi 21 XL” GPU. The GPU will come packaged with 32 MB of Infinity Cache, the same amount as the Navi 23 GPU, and across a 128-bit wide bus. Just like the Navi 32 GPUs, the Navi 33 chips will be focused first on the mobile lineup with early graphics performance putting them ahead of the Intel Arc Alchemist lineup at less than half the cost & while pulling less power.
The outlet also talks about two new features coming to AMD RDNA 3 Navi 3x GPUs for Radeon RX 7000 series graphics cards such as:
OREO
One of the features in the RDNA 3 graphics pipeline is OREO: Opaque Random Export Order, which is just one of the many area saving techniques. With gfx10, the pixel shaders run out-of-order, where the outputs go into a Re-Order Buffer before moving to the rest of the pipeline in-order. With OREO, the next step (blend) can now receive and execute operations in any order and export to the next stage in-order. Thus, the ROB can be replaced with a much smaller skid buffer, saving area.
Infinity Cache Updates
The Memory Attached Last Level (MALL) Cache blocks are each halved in size, doubling the number of banks for the same cache amount. There are also changes and additions that increase graphics to MALL bandwidth and reduce the penalty of going out to VRAM.
The AMD Radeon RX 7000 “RDNA 3” GPU lineup based on the Nav 3x GPUs is expected to launch later this year with reports pitting the flagship Navi 31 launch first followed by Navi 32 and Navi 33 GPUs.
AMD RDNA 3 Navi 3X GPU Configurations (Preliminary)
GPU Name | Navi 21 | Navi 33 | Navi 32 | Navi 31 | Navi 3X |
---|---|---|---|---|---|
Codename | Sienna Cichlid | Hotpink Bonefish | Wheat Nas | Plum Bonito | TBD |
GPU Process | 7nm | 6nm | 5nm/6nm | 5nm/6nm | 5nm/6nm |
GPU Package | Monolithic | Monolithic | MCM (1 GCD + 4 MCD) | MCM (1 GCD + 6 MCD) | MCM (TBD) |
GPU Die Size | 520mm2 | 203mm2 (Only GCD) | 200mm2 (Only GCD) 425mm2 (with MCDs) |
308mm2 (Only GCD) 533mm2 (with MCDs) |
TBD |
Shader Engines | 4 | 2 | 4 | 6 | 8 |
GPU WGPs | 40 | 16 | 30 | 48 | 64 |
SPs Per WGP | 128 | 256 | 256 | 256 | 256 |
Compute Units (Per Die) | 80 | 32 | 60 | 96 | 128 (per GPU) 256 (Total) |
Cores (Per Die) | 5120 | 4096 | 7680 | 12288 | 8192 |
Cores (Total) | 5120 | 4096 | 7680 | 12288 | 16,384 |
Memory Bus | 256-bit | 128-bit | 256-bit | 384-bit | 384-bit x2? |
Memory Type | GDDR6 | GDDR6 | GDDR6 | GDDR6 | GDDR6 |
Memory Capacity | Up To 16 GB | Up To 8 GB | Up To 16 GB | Up To 24 GB | Up To 32 GB |
Memory Speed | 16-18 Gbps | TBD | TBD | 20 Gbps | TBD |
Memory Bandwidth | 512-576 GB/s | TBD | TBD | 960 GB/s | TBD |
Infinity Cache | 128 MB | 32 MB | 64 MB | 96/192 MB | TBD |
Flagship SKU | Radeon RX 6900 XTX | Radeon RX 7600 XT? | Radeon RX 7800 XT? Radeon RX 7700 XT? |
Radeon RX 7900 XT? | Radeon Pro |
TBP | 330W | ~150W | ~250W | ~350W | TBD |
Launch | Q4 2020 | Q4 2022? | Q4 2022? | Q4 2022? | 2023? |
The post AMD RDNA 3 GPUs For Radeon RX 7000 Graphics Cards Detailed – Navi 31 “Plum Bonito”, Navi 32 “Wheat Nas”, Navi 33 “Hotpink Bonefish” by Hassan Mujtaba appeared first on Wccftech.
Powered by WPeMatico