TechPowerUp Editor-In-Chief "W1zzard" received confirmation yesterday from AMD that the Navi 23 GPU will indeed have 64 ROPs; the same as it's previous Navi 22 GPU, VideoCardz reports.
Aside from AMD announcing that the Navi 23 GPU is currently in use as the Radeon RX 6600M and three other unreleased projects, Elon Musk has also stated that the new GPU is in Tesla's Model S information and entertainment system - something that is quoted to rival the Sony Playstation 5 console's processing power.
This new information now adds more speculation to other details of not only the Navi 23 units, but Radeon's RX 6600M, Radeon Pro W6600(M), and the Radeon RX 6600 XT GPUs.
TechPowerUp breaks down the specs for the AMD Navi 23 GPU:
AMD's Navi 23 GPU uses the RDNA 2.0 architecture and is made using a 7 nm production process at TSMC. With a die size of 237 mm² and a transistor count of 11,060 million it is a medium-sized chip. Navi 23 supports DirectX 12.0 (Feature Level 12_1). For GPU compute applications, OpenCL version 2.1 can be used. It features 2048 shading units, 128 texture mapping units and 64 ROPs. The GPU also contains 32 raytracing acceleration cores.
The Navi 23 GPU utilizes up to 32 CU (compute units). That is intriguing, considering that none of the products to be launched have been confirmed to only use 28 CU.
Last September, we posted a comparison of the Navi family of GPUs, including the new Navi 23:
Property | Navi 10 | Navi 14 | Navi 12 | Navi 21 | Navi 22 | Navi 23 | Navi 31 |
---|---|---|---|---|---|---|---|
num_se | 2 | 1 | 2 | 4 | 2 | 2 | 4 |
num_cu_per_sh | 10 | 12 | 10 | 10 | 10 | 8 | 10 |
num_sh_per_se | 2 | 2 | 2 | 2 | 2 | 2 | 2 |
num_rb_per_se | 8 | 8 | 8 | 4 | 4 | 4 | 4 |
num_tccs | 16 | 8 | 16 | 16 | 12 | 8 | 16 |
num_gprs | 1024 | 1024 | 1024 | 1024 | 1024 | 1024 | 1024 |
num_max_gs_thds | 32 | 32 | 32 | 32 | 32 | 32 | 32 |
gs_table_depth | 32 | 32 | 32 | 32 | 32 | 32 | 32 |
gsprim_buff_depth | 1792 | 1792 | 1792 | 1792 | 1792 | 1792 | 1792 |
parameter_cache_depth | 1024 | 1024 | 1024 | 1024 | 1024 | 1024 | 1024 |
double_offchip_lds_buffer | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
wave_size | 32 | 32 | 32 | 32 | 32 | 32 | 32 |
max_waves_per_simd | 20 | 20 | 20 | 16 | 16 | 16 | 16 |
max_scratch_slots_per_cu | 32 | 32 | 32 | 32 | 32 | 32 | 32 |
lds_size | 64 | 64 | 64 | 64 | 64 | 64 | 64 |
num_sc_per_sh | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
num_packer_per_sc | 2 | 2 | 2 | 4 | 4 | 4 | 4 |
num_gl2a | N/A | N/A | N/A | 4 | 2 | 2 | 4 |
unknown0 | N/A | N/A | N/A | 10 | 10 | 8 | 10 |
unknown1 | N/A | N/A | N/A | 16 | 12 | 8 | 16 |
unknown2 | N/A | N/A | N/A | 80 | 40 | 32 | 80 |
num_cus (computed) | 40 | 24 | 40 | 80 | 40 | 32 | 80 |
"WhyCry" at VideoCardz states:
Both the mobile Radeon RX 6600M as well as a desktop and mobile workstation Radeon PRO W6600M feature 1792 Stream Processors. With that in mind, 10 TFLOPs of FP32 compute power is already impressive enough because it means those GPUs peak at 2.9 GHz within 90-100W TDP.
AMD Radeon RX 6600 series specifications that we posted in more detail earlier this month.
AMD Radeon RX 6000 Series "RDNA 2" Graphics Card Lineup:
Graphics Card | AMD Radeon RX 6600 | AMD Radeon RX 6600 XT | AMD Radeon RX 6700 | AMD Radeon RX 6700 XT | AMD Radeon RX 6800 | AMD Radeon RX 6800 XT | AMD Radeon RX 6900 XT | AMD Radeon RX 6900 XT Liquid Cooled |
---|---|---|---|---|---|---|---|---|
GPU | Navi 23 (XL?) | Navi 23 (XT?) | Navi 22 (XL?) | Navi 22 (XT?) | Navi 21 XL | Navi 21 XT | Navi 21 XTX | Navi 21 XTXH |
Process Node | 7nm | 7nm | 7nm | 7nm | 7nm | 7nm | 7nm | 7nm |
Die Size | 237mm2 | 237mm2 | 336mm2 | 336mm2 | 520mm2 | 520mm2 | 520mm2 | 520mm2 |
Transistors | 11.06 Billion | 11.06 Billion | 17.2 Billion | 17.2 Billion | 26.8 Billion | 26.8 Billion | 26.8 Billion | 26.8 Billion |
Compute Units | 28 | 32 | 36 | 40 | 60 | 72 | 80 | 80 |
Stream Processors | 1792 | 2048 | 2304 | 2560 | 3840 | 4608 | 5120 | 5120 |
TMUs/ROPs | TBA | TBA | TBA | 160/64 | 240 / 96 | 288 / 128 | 320 / 128 | 320 / 128 |
Game Clock | TBA | TBA | TBA | 2424 MHz | 1815 MHz | 2015 MHz | 2015 MHz | 2250 MHz |
Boost Clock | TBA | TBA | TBA | 2581 MHz | 2105 MHz | 2250 MHz | 2250 MHz | 2345 MHz |
FP32 TFLOPs | TBA | TBA | TBA | 13.21 TFLOPs | 16.17 TFLOPs | 20.74 TFLOPs | 23.04 TFLOPs | 24.01 TFLOPs |
Memory Size | 8 GB GDDR6 + 32 MB Infinity Cache? | 8 GB GDDR6 + 32 MB Infinity Cache? | 12 GB GDDR6 + 96 MB Infinity Cache? | 12 GB GDDR6 + 96 MB Infinity Cache | 16 GB GDDR6 +128 MB Infinity Cache | 16 GB GDDR6 +128 MB Infinity Cache | 16 GB GDDR6 +128 MB Infinity Cache | 16 GB GDDR6 +128 MB Infinity Cache |
Memory Bus | 128-bit? | 192-bit | 192-bit | 192-bit | 256-bit | 256-bit | 256-bit | 256-bit |
Memory Clock | 16 Gbps? | 16 Gbps? | 16 Gbps? | 16 Gbps | 16 Gbps | 16 Gbps | 16 Gbps | 18 Gbps |
Bandwidth | 256 GB/s? | 256 GB/s? | 384 GB/s | 384 GB/s | 512 GB/s | 512 GB/s | 512 GB/s | 576 GB/s |
TDP | TBA | TBA | TBA | 230W | 250W | 300W | 300W | 330W |
Price | TBA | TBA | TBA | $479 US | $579 US | $649 US | $999 US | ~$1199 US |
With the public having no access to the Navi 23 GPU or any driver information for the new GPU, there is still a large amount of guesswork and speculation until AMD releases information on their new graphics cards, such as the Radeon RX 6600XT GPU. But, this new information about the Navi 23 GPU definitely helps give us most of the clues regarding the RDNA2 chips powering both Sony and Microsoft's home consoles.
AMD Confirms: Navi 23 GPU Has 64 ROPs and 32 Ray Tracing Cores - Wccftech
Read More
No comments:
Post a Comment