AMD Confirms: Navi 23 GPU Has 64 ROPs and 32 Ray Tracing Cores-April 2024-www.yitit.com

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.

AMD Navi 23 GPU

AMD Navi 23 GPU. Source: TechPowerUp

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 6950 XT	AMD Radeon RX 6900 XT	AMD Radeon RX 6800 XT	AMD Radeon RX 6800	AMD Radeon RX 6750 XT	AMD Radeon RX 6700 XT	AMD Radeon RX 6700	AMD Radeon RX 6650 XT	AMD Radeon RX 6600 XT	AMD Radeon RX 6600	AMD Radeon RX 6500 XT	AMD Radeon RX 6400
GPU	Navi 21 KXTX	Navi 21 XTX	Navi 21 XT	Navi 21 XL	Navi 22 KXT	Navi 22 XT	Navi 22 XL	Navi 23 KXT	Navi 23 (XT)	Navi 23 (XL)	Navi 24 (XT)	Navi 24 (XL)
Process Node	7nm	7nm	7nm	7nm	7nm	7nm	7nm	7nm	7nm	7nm	6nm	6nm
Die Size	520mm2	520mm2	520mm2	520mm2	336mm2	336mm2	336mm2	237mm2	237mm2	237mm2	107mm2	107mm2
Transistors	26.8 Billion	26.8 Billion	26.8 Billion	26.8 Billion	17.2 Billion	17.2 Billion	17.2 Billion	11.06 Billion	11.06 Billion	11.06 Billion	5.4 Billion	5.4 Billion
Compute Units	80	80	72	60	40	40	36	32	32	28	16	12
Stream Processors	5120	5120	4608	3840	2560	2560	2304	2048	2048	1792	1024	768
TMUs/ROPs	320 / 128	320 / 128	288 / 128	240 / 96	160/64	160/64	144/64	128/64	128/64	112/64	64/32	48/32
Game Clock	2116 MHz	2015 MHz	2015 MHz	1815 MHz	2495 MHz	2424 MHz	2330 MHz	2410 MHz	2359 MHz	2044 MHz	2610 MHz	2039 MHz
Boost Clock	2324 MHz	2250 MHz	2250 MHz	2105 MHz	2600 MHz	2581 MHz	2495 MHz	2635 MHz	2589 MHz	2491 MHz	2815 MHz	2321 MHz
FP32 TFLOPs	23.80 TFLOPs	23.04 TFLOPs	20.74 TFLOPs	16.17 TFLOPs	13.31 TFLOPs	13.21 TFLOPs	11.50 TFLOPs	10.79 TFLOPs	10.6 TFLOPs	9.0 TFLOPs	5.7 TFLOPs	3.5 TFLOPs
Memory Size	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	12 GB GDDR6 + 96 MB Infinity Cache	12 GB GDDR6 + 96 MB Infinity Cache	10 GB GDDR5 + 80 MB Infinity Cache	8 GB GDDR6 + 32 MB Infinity Cache	8 GB GDDR6 + 32 MB Infinity Cache	8 GB GDDR6 + 32 MB Infinity Cache	4 GB / 8 GB GDDR6 + 16 MB Infinity Cache	4 GB GDDR6 + 16 MB Infinity Cache
Memory Bus	256-bit	256-bit	256-bit	256-bit	192-bit	192-bit	160-bit	128-bit	128-bit	128-bit	64-bit	64-bit
Memory Clock	18 Gbps	16 Gbps	16 Gbps	16 Gbps	18 Gbps	16 Gbps	16 Gbps	17.5 Gbps	16 Gbps	14 Gbps	18 Gbps	14 Gbps
Bandwidth	576 GB/s	512 GB/s	512 GB/s	512 GB/s	432 GB/s	384 GB/s	320 GB/s	280 GB/s	256 GB/s	224 GB/s	144 GB/s	112 GB/s
TDP	335W	300W	300W	250W	250W	230W	220W	176W	160W	132W	107W	53W
Price	$1099 US	$999 US	$649 US	$579 US	$549 US	$479 US	TBD	$399 US	$379 US	$329 US	$199 US	$159 US?