RDNA 3

RDNA 3
Launched	December 13, 2022
Designed by	AMD
Manufactured by	TSMC;
Fabrication process	TSMC N4; TSMC N5; TSMC N6;
Codename(s)	Plum Bonito; Wheat Nas; Hotpink Bonefish;
Product Series
Desktop	Radeon RX 7000 series;
Professional/workstation	Radeon Pro W7000 series;
Specifications
Compute	122.8 TFLOPS (FP16); 61.42 TFLOPS (FP32); 1.919 TFLOPS (FP64);
Clock rate	1500 MHz to 2500 MHz
Shader clock rate	2269 MHz
L0 cache	64 KB (per WGP): ; 32 KB instructions cache; 16 KB K data cache;
L1 cache	256 KB (per array)
L2 cache	6 MB
L3 cache	up to 96 MB
Memory support	GDDR6
Memory clock rate	20 Gbps
PCIe support	PCIe 4.0
Supported Graphics APIs
Direct3D	Direct3D 12.0 Ultimate (feature level 12_2)
Shader Model	Shader Model 6.7
OpenCL	OpenCL 2.1
OpenGL	OpenGL 4.6
Vulkan	Vulkan 1.3
Media Engine
Encode codecs	H.264; H.265; AV1;
Decode codecs	H.264; H.265; AV1;
Color bit-depth	8-bit; 10-bit; 12-bit;
Encoder(s) supported	AMF; VCE;
Display outputs	DisplayPort 2.1; HDMI 2.1a; USB-C;
History
Predecessor	RDNA 2
Variant	CDNA 3 (datacenter)
Successor	RDNA 4

RDNA 3 is a GPU microarchitecture designed by AMD, released with the Radeon RX 7000 series on December 13, 2022. Alongside powering the RX 7000 series, RDNA 3 is also featured in the SoCs designed by AMD for the Asus ROG Ally and Legion Go consoles.

Background

On June 9, 2022, AMD held their Financial Analyst Day where they presented a client GPU roadmap which contained mention of RDNA 3 coming in 2022 and RDNA 4 coming in 2024.[1] AMD announced to investors their intention to achieve a performance-per-watt uplift of over 50% with RDNA 3 and that the upcoming architecture would be built using chiplet packaging on a 5 nm process.[2]

A sneak preview for RDNA 3 was included towards the end of AMD's Ryzen 7000 unveiling event on August 29, 2022. The preview included RDNA 3 running gameplay of Lies of P, AMD CEO Lisa Su confirming that a chiplet design would be used, and a partial look at AMD's reference design for an RDNA 3 GPU.[3]

Full details for the RDNA 3 architecture were unveiled on November 3, 2022 at an event in Las Vegas.[4]

Architectural details

Chiplet packaging

For the first time ever in a consumer GPU, RDNA 3 utilizes modular chiplets. AMD previously had great success with its use of chiplets in its Ryzen desktop and Epyc server processors.[5]

The decision to move to a chiplet-based GPU microarchitecture was led by AMD Senior Vice President Sam Naffziger who had also lead the chiplet initiative with Ryzen and Epyc.[6] The development of RDNA 3's chiplet architecture began towards the end of 2017 with Naffziger leading the AMD graphics team in the effort.[7]

Memory Cache Dies (MCDs)

With a respective 2.05 billion transistors, each Memory Cache Die (MCD) contains large blocks of L3 cache and two physical 32-bit GDDR6 memory interfaces for a combined 64-bit interface per MCD.[8] The Radeon RX 7900 XTX has a 384-bit memory bus through the use of six MCDs while the RX 7900 XT has a 320-bit bus due to its five MCDs.

Chiplet interconnects

The chiplet interconnects have a bandwidth of 5.3 TB/s.[9]

Process node

According to Naffziger, cache and SRAM do not scale as linearly as logic does on advanced nodes like N5 in terms of density and power consumption so they can instead be fabricated on the cheaper, more mature N6 node. The use of smaller chiplet dies rather than one large monolithic die is beneficial for maximizing wafer yields as more dies can be fitted onto a single wafer.[7]

Compute Units

RDNA 3 includes improved dual-issue shader ALUs with the ability to execute two instructions per cycle. It can contain up to 96 graphics Compute Units that can provide up to 61 TFLOPS of compute.[10]

RDNA 3 has dedicated AI acceleration with Wave MMA (matrix multiply-accumulate) instructions,[11] which can improve AI-based performance by 2.7x and also benefits ray tracing instructions, similar to Nvidia's Tensor cores.[10]

Ray tracing

Each RDNA 3 Compute Unit contains one ray tracing accelerator. The overall number of ray tracing accelerators is increased due to the higher number of Compute Units, though the number of ray tracing accelerators per Compute Unit has not increased over RDNA 2.

Clock speeds

RDNA 3 was designed to support high clock speeds. On RDNA 3, clock speeds have been decoupled with the front end operating at a 2.5 GHz frequency while the shaders operate at 2.3 GHz. The shaders operating at a lower clock speed gives up to 25% power savings according to AMD and RDNA 3's shader clock speed is still 15% faster than RDNA 2.[12]

Cache and memory subsystem

RDNA 3 GPUs use GDDR6 memory rather than faster GDDR6X due to the latter's increased power consumption.

16 MB Infinity Cache is included on each MCD. Theoretically, additional L3 cache could be added to the MCDs via AMD's 3D V-Cache die stacking technology as the MCDs contain unused TSV connection points.[13][14]

Power efficiency

AMD claims that RDNA 3 achieves a 54% increase in performance-per-watt which is in line with their previous claims of 50% performance-per-watt increases for both RDNA and RDNA 2.

Media engine

RDNA 3 is the first RDNA architecture to have a dedicated media engine. It is built into the GCD and is based on VCN 4.0 encoding and decoding core.[15] AMD's AMF AV1 encoder is comparable in quality to Nvidia's NVENC AV1 encoder but can handle a higher number of simultaneous encoding streams compared to the limit of 3 on the GeForce RTX 40 series.[16]

Supported encoding frame rates (FPS) per resolution and video coding format[17]
Resolution	H.264	H.265	AV1
1080p
1440p
4K	180	180	240
8K	48	48	60

Display engine

RDNA 3 GPUs feature a new display engine called the "Radiance Display Engine". AMD touted its support for DisplayPort 2.1 UHBR 13.5, delivering up to 54 Gbit/s bandwidth for high refresh rates at 4K and 8K resolutions.[18] DisplayPort 2.1 can support 4K at 480 Hz and 8K at 165 Hz with Display Stream Compression (DSC). The previous DisplayPort 1.4 standard with DSC was limited to 4K at 240 Hz and 8K at 60 Hz.

Navi 3x dies

			Graphics Compute Die (GCD)			Memory Cache Die (MCD)
			Navi 31	Navi 32	Navi 33	Memory Cache Die (MCD)
Ref.			[8]
Launch			Dec 2022	Aug 2023	Jan 2023	Dec 2022
Codename			Plum Bonito	Wheat Nas	Hotpink Bonefish	—
Compute units (Stream processors) [FP32 cores]			96 (6144) [12288]	60 (3840) [7680]	32 (2048) [4096]	—
Process			TSMC N5		TSMC N6
Transistors			45.4B	Unknown	13.3B	2.05B
Transistor density			150.2 MTr/mm²	Unknown	65.2 MTr/mm²	54.64 MTr/mm²
Die size			304.35 mm²	200 mm²	204 mm²	37.52 mm²
Max TDP			405 W	263 W	200 W	—
Products	Consumer	Desktop	RX 7900 GRE RX 7900 XT RX 7900 XTX	RX 7700 XT RX 7800 XT	RX 7600	RX 7700 XT (3×) RX 7800 XT (4×) RX 7900 GRE (4×) RX 7900 XT (5×) RX 7900 XTX (6×)
	Consumer	Mobile	RX 7900M	—	RX 7600S RX 7600M RX 7600M XT RX 7700S	RX 7900M (4×)
	Workstation	Desktop	W7800 W7900	—	W7500 W7600	W7800 (4×) W7900 (6×)
	Workstation	Mobile	—	—	—	—

Products

Desktop

Model (Code name)	Release date & price	Architecture & fab	Chiplets (active)	Transistors & die size[lower-alpha 1]	Core		Fillrate[lower-alpha 2][lower-alpha 3][lower-alpha 4]		Processing power[lower-alpha 2][lower-alpha 5] (TFLOPS)			Infinity Cache		Memory				TBP	Bus interface
Model (Code name)	Release date & price	Architecture & fab	Chiplets (active)	Transistors & die size[lower-alpha 1]	Config[lower-alpha 6][lower-alpha 7]	Clock[lower-alpha 2] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Size (MB)	Bandwidth (GB/s)	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)	TBP	Bus interface
Radeon RX 7600 (Navi 33)[20]	May 25, 2023 $269 USD	RDNA 3 TSMC N6	—	13.3×10⁹ 204 mm²	2048:128:64 32:64:32 CU	1720 2655	220.2 339.8	110.1 169.9	28.18 43.50	14.09 21.75	0.440 0.680	32	476.9	8	288	GDDR6 128-bit	18000	165 W	PCIe 4.0 ×8
Radeon RX 7700 XT (Navi 32)[21]	Sep 6, 2023 $449 USD	RDNA 3 TSMC N5 (GCD) TSMC N6 (MCD)	1 × GCD 3 × MCD	28.1×10⁹ 346 mm²	3456:216:96 54:108:54 CU	1900 2544	410.4 549.5	182.4 244.2	52.53 70.34	26.27 35.17	0.821 1.099	48	1995	12	432	GDDR6 192-bit	18000	245 W	PCIe 4.0 ×16
Radeon RX 7800 XT (Navi 32)[22]	Sep 6, 2023 $499 USD		1 × GCD 4 × MCD	28.1×10⁹ 346 mm²	3840:240:96 60:120:60 CU	1800 2430	432 583.2	172.8 233.2	55.30 74.65	27.64 37.32	0.864 1.166	64	2708	16	624	GDDR6 256-bit	19500	263 W
Radeon RX 7900 GRE (Navi 31)	Jul 27, 2023 $649 USD		1 × GCD 4 × MCD	57.7×10⁹ 529 mm²	5120:320:192 80:160:80 CU	1270 2245	406.4 718.4	243.8 431.0	52.02 91.96	26.01 45.98	0.813 1.437	64	2250	16	576	GDDR6 256-bit	18000	260 W
Radeon RX 7900 XT (Navi 31)[23]	Dec 13, 2022 $899 USD		1 × GCD 5 × MCD		5376:336:192 84:168:84 CU	1500 2400	504.0 806.4	288.0 460.8	64.51 103.2	32.26 51.61	1.008 1.613	80	2900	20	800	GDDR6 320-bit	20000	315 W
Radeon RX 7900 XTX (Navi 31)[24]	Dec 13, 2022 $999 USD		1 × GCD 6 × MCD		6144:384:192 96:192:96 CU	1900 2500	729.6 960.0	364.8 480.0	93.39 122.9	46.69 61.44	1.459 1.920	96	3500	24	960	GDDR6 384-bit	20000	355 W

Approximate die size of entire MCM package that consists of single GCD (Graphics Compute Die) and six MCDs (Memory Cache Die).
Radeon RX 7900 XT has only five active MCDs, inactive one is for structural support and heat dissipation. Die size of GCD is 306 mm², size of each MCD is 37.5 mm².[19]
Boost values (if available) are stated below the base value in italic.
Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
Unified shaders : Texture mapping units : Render output units : Ray accelerators : AI accelerators and Compute units (CU)
GPUs based on RDNA 3 have dual-issue stream processors so that up to two shader instructions can be executed per clock cycle under certain parallelism conditions.

Mobile

Model (Code name)	Release date	Architecture & fab	Chiplets (active)	Transistors & die size	Core		Fillrate[lower-alpha 1][lower-alpha 2][lower-alpha 3]		Processing power[lower-alpha 1][lower-alpha 4] (TFLOPS)			Infinity Cache	Memory				TDP	Bus interface
Model (Code name)	Release date	Architecture & fab	Chiplets (active)	Transistors & die size	Config[lower-alpha 5]	Clock[lower-alpha 1] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Infinity Cache	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)	TDP	Bus interface
Radeon RX 7600S (Navi 33)[25]	Jan 4, 2023	RDNA 3 TSMC N6	—	13.3×10⁹ 204 mm²	1792:112:64 28:56:28 CU	1500 2200	168.0 246.4	96.00 140.8	21.50 31.54	10.75 15.77	0.336 0.493	32 MB	8	256	GDDR6 128-bit	16000	75 W	PCIe 4.0 ×8
Radeon RX 7600M (Navi 33)[26]					1792:112:64 28:56:28 CU	1500 2410	168.0 269.9	96.00 154.2	21.50 34.55	10.75 17.28	0.336 0.540			256		16000	90 W
Radeon RX 7600M XT (Navi 33)[27]					2048:128:64 32:64:32 CU	1500 2615	192.0 334.1	96.00 167.0	24.58 42.84	12.29 21.42	0.384 0.669			288		18000	120 W
Radeon RX 7700S (Navi 33)[28]					2048:128:64 32:64:32 CU	1500 2500	192.0 320.0	96.00 160.0	24.58 40.96	12.29 20.48	0.384 0.640			288			100 W
Radeon RX 7900M (Navi 31)	Oct 19, 2023	RDNA 3 TSMC N5 (GCD) TSMC N6 (MCD)	1 × GCD 4 × MCD	57.7×10⁹ 529 mm²	4608:288:192 72:144:72 CU	2090	601.9	401.3	77,05	38.52	1.204	64 MB	16	576	GDDR6 256-bit		180 W	PCIe 4.0 ×16

Boost values (if available) are stated below the base value in italic.
Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
Unified shaders : Texture mapping units : Render output units : Ray accelerators : AI accelerators and Compute units (CU), GPUs based on RDNA 3 have dual-issue stream processors so that up to two shader instructions can be executed per clock cycle under certain parallelism conditions.

Workstation

Desktop Workstation

Model (Code name)	Release date & price	Architecture & fab	Chiplets (active)	Transistors & die size[lower-alpha 1]	Core		Fillrate[lower-alpha 2][lower-alpha 3][lower-alpha 4]		Processing power[lower-alpha 2][lower-alpha 5] (TFLOPS)			Infinity Cache	Memory				TDP	Bus interface
Model (Code name)	Release date & price	Architecture & fab	Chiplets (active)	Transistors & die size[lower-alpha 1]	Config[lower-alpha 6][lower-alpha 7]	Clock[lower-alpha 2] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	Infinity Cache	Size (GB)	Bandwidth (GB/s)	Bus type & width	Clock (MT/s)	TDP	Bus interface
Radeon Pro W7500 (Navi 33)[29][30][31]	Aug 3, 2023 $429 USD	RDNA 3 TSMC N6	—	13.3×10⁹ 204 mm²	1792:112:64 28:56:28 CU	1700	190.4	108.8	24.37	12.19	0.381	32 MB	8	172	GDDR6 128-bit	18000	70 W	PCIe 4.0 ×8
Radeon Pro W7600 (Navi 33)[32][30][33]	Aug 3, 2023 $599 USD	RDNA 3 TSMC N6	—	13.3×10⁹ 204 mm²	2048:128:64 32:64:32 CU	2440	312.3	156.2	39.98	19.99	0.625	32 MB	8	288	GDDR6 128-bit		130 W	PCIe 4.0 ×8
Radeon Pro W7800 (Navi 31)[34][35][36]	2023 $2499 USD	RDNA 3 TSMC N5 (GCD) TSMC N6 (MCD)	1 × GCD 4 × MCD	57.7×10⁹ ~531 mm²	4480:280:128 70:128:70 CU	2525	707	323.2	90.50	45.25	1.414	64 MB	32	576	GDDR6 256-bit		260 W	PCIe 4.0 ×16
Radeon Pro W7900 (Navi 31)[37][35][38]	2023 $3999 USD	RDNA 3 TSMC N5 (GCD) TSMC N6 (MCD)	1 × GCD 6 × MCD	57.7×10⁹ ~531 mm²	6144:384:192 96:192:96 CU	2495	958.1	479	122.6	61.32	1.916	96 MB	48	864	GDDR6 384-bit		295 W	PCIe 4.0 ×16

Approximate die size of entire MCM package that consists of single GCD (Graphics Compute Die) and six MCDs (Memory Cache Die).
Radeon Pro W7800 has only four active MCDs, inactive one is for structural support and heat dissipation.
Boost values (if available) are stated below the base value in italic.
Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
Unified shaders : Texture mapping units : Render output units : Ray accelerators : AI accelerators and Compute units (CU)
GPUs based on RDNA 3 have dual-issue stream processors so that up to two shader instructions can be executed per clock cycle under certain parallelism conditions.

Integrated graphics processors (iGPs)

Model	Launch	Codename	Architecture & fab	Die size	Core		Fillrate[lower-alpha 1][lower-alpha 2][lower-alpha 3]		Processing power[lower-alpha 1][lower-alpha 4] (GFLOPS)			Cache			TDP	Bus interface
Model	Launch	Codename	Architecture & fab	Die size	Config[lower-alpha 5][lower-alpha 6]	Clock[lower-alpha 1] (MHz)	Texture (GT/s)	Pixel (GP/s)	Half	Single	Double	L0	L1	L2	TDP	Bus interface
Radeon 740M	Apr 2023	Phoenix	RDNA 3 TSMC N4	178 mm²	4 CU 256:16:8:4	2,500	40	26.7	5,120	2,560	80	64 KB	512 KB	2 MB	15–30 W	PCIe 4.0 ×8
Ryzen Z1					4 CU 256:16:8:4	2,735	40	26.7	5,600	2,800	87.5	64 KB	512 KB		9–30 W
Radeon 760M					8 CU 512:32:16:8	1,000 2,600	32 83.2	21.3 55.5	8,192 10,649	4,096 5,324	64 332.8	128 KB	1 MB		15–54 W
Radeon 780M					12 CU 768:48:24:12	2,700	129.6	86.4	16,588	8,294	259.2	192 KB	1.5 MB		15–54 W
Ryzen Z1 Extreme					12 CU 768:48:24:12	2,800	129.6	86.4	17,203	8,600	268.75	192 KB	1.5 MB		9–30 W

Boost values (if available) are stated below the base value in italic.
Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.
Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.
Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.
Unified shaders : Texture mapping units : Render output units : Ray accelerators and Compute units (CU)
GPUs based on RDNA 3 have dual-issue stream processors so that up to two shader instructions can be executed per clock cycle under certain parallelism conditions.

References

Smith, Ryan (June 9, 2022). "AMD's 2022-2024 Client GPU Roadmap: RDNA 3 This Year, RDNA 4 Lands in 2024". AnandTech. Retrieved April 8, 2023.
Walton, Jarred (June 9, 2022). "AMD GPU Roadmap: RDNA 3 With 5nm GPU Chiplets Coming This Year". Tom's Hardware. Retrieved April 8, 2023.
Wickens, Katie (August 31, 2022). "AMD's Lisa Su confirms chiplet-based RDNA 3 GPU architecture". PC Gamer. Retrieved April 8, 2023.
"AMD Unveils World's Most Advanced Gaming Graphics Cards, Built on Groundbreaking AMD RDNA 3 Architecture with Chiplet Design". AMD (Press release). Las Vegas, NV. November 3, 2022. Retrieved April 8, 2023.
James, Dave (June 24, 2022). "AMD suggests a Ryzen-like design for RDNA 3 chiplets would be 'a reasonable inference'". PC Gamer. Retrieved April 8, 2023.
Alcorn, Paul; Walton, Jarred (June 23, 2022). "Into the GPU Chiplet Era: An Interview With AMD's Sam Naffziger". Tom's Hardware. Retrieved April 8, 2023.
Brosdahl, Peter (November 22, 2022). "AMD Lead Engineer Sam Naffziger Explains Advantages of RDNA3 Chiplet Design". The FPS Review. Retrieved April 8, 2023.
Walton, Jarred (November 14, 2022). "AMD RDNA 3 GPU Architecture Deep Dive: The Ryzen Moment for GPUs". Tom's Hardware. Retrieved April 8, 2023.
"AMD Explains the Economics Behind Chiplets for GPUs". TechPowerUp. November 14, 2022. Retrieved April 8, 2023.
Gula, Damien (November 3, 2022). "AMD's RDNA 3 GPUs are Way Cheaper Than the RTX 4090". Gizmodo. Retrieved April 8, 2023.
Vasishta, Aaryaman (January 10, 2023). "How to accelerate AI applications on RDNA 3 using WMMA". GPUOpen.com. Archived from the original on January 10, 2023. Retrieved August 14, 2023.
Olšan, Jan (November 7, 2022). "AMD RDNA 3 details: architecture changes, AI acceleration, DP 2.1". HWCooling. Retrieved April 8, 2023.
Klotz, Aaron (January 29, 2023). "AMD GPU Appears to Leave Room for Future 3D V-Cache". Tom's Hardware. Retrieved April 8, 2023.
Ridley, Jacob (January 30, 2023). "Tiny spots on AMD's RDNA 3 GPU hint at massive cache potential". PC Gamer. Retrieved April 8, 2023.
Shilov, Anton (May 4, 2022). "First Details About AMD's Next Generation Video Engine Revealed". Tom's Hardware. Retrieved April 10, 2023.
Klotz, Aaron (December 12, 2022). "AMD's Radeon RX 7900 AV1 encoder is almost on par with Intel Arc and Nvidia's RTX 40 series". TechSpot. Retrieved April 8, 2023.
Taylor, Adam (December 14, 2022). "Tested: With RDNA 3, AMD Radeon is finally useful for content creators". PCWorld. Retrieved April 8, 2023.
Sag, Anshel (November 14, 2022). "AMD's New Radeon RX 7900XTX And 7900XT Put The Pressure On NVIDIA". Forbes. Retrieved April 8, 2023.
"AMD Unveils World's Most Advanced Gaming Graphics Cards, Built on Groundbreaking AMD RDNA 3 Architecture with Chiplet Design". AMD (Press release). April 21, 2023.
"AMD Radeon RX 7600 Specs". TechPowerUp. Retrieved May 24, 2023.
"AMD Radeon RX 7700 XT Specs". TechPowerUp. August 25, 2023. Retrieved August 25, 2023.
"AMD Radeon RX 7800 XT Specs". TechPowerUp. August 25, 2023. Retrieved August 25, 2023.
"AMD Radeon RX 7900 XT Specs". TechPowerUp. Retrieved November 4, 2022.
"AMD Radeon RX 7900 XTX Specs". TechPowerUp. Retrieved November 4, 2022.
"AMD Radeon RX 7600S Specs". TechPowerUp. Retrieved January 16, 2023.
"AMD Radeon RX 7600M Specs". TechPowerUp. Retrieved January 16, 2023.
"AMD Radeon RX 7600M XT Specs". TechPowerUp. Retrieved April 20, 2023.
"AMD Radeon RX 7700S Specs". TechPowerUp. Retrieved January 16, 2023.
"AMD Radeon PRO W7500 Professional Graphics". AMD. Retrieved August 4, 2023.
"New AMD Radeon PRO W7000 Series Workstation Graphics Cards Deliver Advanced Technologies and Exceptional Performance for Mainstream Professional Workflows" (Press release). AMD. August 3, 2023. Retrieved August 4, 2023.
"AMD Radeon PRO W7500 Specs". TechPowerUp. Retrieved August 4, 2023.
"AMD Radeon PRO W7600 Professional Graphics". AMD. Retrieved August 4, 2023.
"AMD Radeon PRO W7600 Specs". TechPowerUp. Retrieved August 4, 2023.
"AMD Radeon PRO W7800 Professional Graphics". AMD. Retrieved April 13, 2023.
"AMD Unveils the Most Powerful AMD Radeon PRO Graphics Cards, Offering Unique Features and Leadership Performance to Tackle Heavy to Extreme Professional Workloads" (Press release). AMD. April 13, 2023. Retrieved April 13, 2023.
"AMD Radeon PRO W7800 Specs". TechPowerUp. Retrieved April 13, 2023.
"AMD Radeon PRO W7900 Professional Graphics". AMD. Retrieved April 13, 2023.
"AMD Radeon PRO W7900 Specs". TechPowerUp. Retrieved April 13, 2023.

This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.

[MCM-20] Approximate die size of entire MCM package that consists of single GCD (Graphics Compute Die) and six MCDs (Memory Cache Die).
Radeon RX 7900 XT has only five active MCDs, inactive one is for structural support and heat dissipation. Die size of GCD is 306 mm², size of each MCD is 37.5 mm².[19]

[Boost-21] Boost values (if available) are stated below the base value in italic.

[Texture_fill-22] Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.

[Pixel_fill-23] Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.

[FLOPS-24] Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

[Core_config-25] Unified shaders : Texture mapping units : Render output units : Ray accelerators : AI accelerators and Compute units (CU)

[Stream_processors-26] GPUs based on RDNA 3 have dual-issue stream processors so that up to two shader instructions can be executed per clock cycle under certain parallelism conditions.

[boost-32] Boost values (if available) are stated below the base value in italic.

[texture_fill-33] Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.

[pixel_fill-34] Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.

[FLOPS-35] Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

[cconfig-36] Unified shaders : Texture mapping units : Render output units : Ray accelerators : AI accelerators and Compute units (CU), GPUs based on RDNA 3 have dual-issue stream processors so that up to two shader instructions can be executed per clock cycle under certain parallelism conditions.

[MCM_die_size-41] Approximate die size of entire MCM package that consists of single GCD (Graphics Compute Die) and six MCDs (Memory Cache Die).
Radeon Pro W7800 has only four active MCDs, inactive one is for structural support and heat dissipation.

[Boost-42] Boost values (if available) are stated below the base value in italic.

[Texture_fill-43] Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.

[Pixel_fill-44] Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.

[FLOPS-45] Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

[Core_config-46] Unified shaders : Texture mapping units : Render output units : Ray accelerators : AI accelerators and Compute units (CU)

[Stream_processors-47] GPUs based on RDNA 3 have dual-issue stream processors so that up to two shader instructions can be executed per clock cycle under certain parallelism conditions.

[Boost-58] Boost values (if available) are stated below the base value in italic.

[Texture_fill-59] Texture fillrate is calculated as the number of Texture Mapping Units multiplied by the base (or boost) core clock speed.

[Pixel_fill-60] Pixel fillrate is calculated as the number of Render Output Units multiplied by the base (or boost) core clock speed.

[FLOPS-61] Precision performance is calculated from the base (or boost) core clock speed based on a FMA operation.

[Core_config-62] Unified shaders : Texture mapping units : Render output units : Ray accelerators and Compute units (CU)

[Stream_processors-63] GPUs based on RDNA 3 have dual-issue stream processors so that up to two shader instructions can be executed per clock cycle under certain parallelism conditions.

[1] Smith, Ryan (June 9, 2022). "AMD's 2022-2024 Client GPU Roadmap: RDNA 3 This Year, RDNA 4 Lands in 2024". AnandTech. Retrieved April 8, 2023.

[2] Walton, Jarred (June 9, 2022). "AMD GPU Roadmap: RDNA 3 With 5nm GPU Chiplets Coming This Year". Tom's Hardware. Retrieved April 8, 2023.

[3] Wickens, Katie (August 31, 2022). "AMD's Lisa Su confirms chiplet-based RDNA 3 GPU architecture". PC Gamer. Retrieved April 8, 2023.

[4] "AMD Unveils World's Most Advanced Gaming Graphics Cards, Built on Groundbreaking AMD RDNA 3 Architecture with Chiplet Design". AMD (Press release). Las Vegas, NV. November 3, 2022. Retrieved April 8, 2023.

[5] James, Dave (June 24, 2022). "AMD suggests a Ryzen-like design for RDNA 3 chiplets would be 'a reasonable inference'". PC Gamer. Retrieved April 8, 2023.

[6] Alcorn, Paul; Walton, Jarred (June 23, 2022). "Into the GPU Chiplet Era: An Interview With AMD's Sam Naffziger". Tom's Hardware. Retrieved April 8, 2023.

[Brosdahl-7] Brosdahl, Peter (November 22, 2022). "AMD Lead Engineer Sam Naffziger Explains Advantages of RDNA3 Chiplet Design". The FPS Review. Retrieved April 8, 2023.

[Walton-8] Walton, Jarred (November 14, 2022). "AMD RDNA 3 GPU Architecture Deep Dive: The Ryzen Moment for GPUs". Tom's Hardware. Retrieved April 8, 2023.

[9] "AMD Explains the Economics Behind Chiplets for GPUs". TechPowerUp. November 14, 2022. Retrieved April 8, 2023.

[Gula-10] Gula, Damien (November 3, 2022). "AMD's RDNA 3 GPUs are Way Cheaper Than the RTX 4090". Gizmodo. Retrieved April 8, 2023.

[wmma-gpuopen-11] Vasishta, Aaryaman (January 10, 2023). "How to accelerate AI applications on RDNA 3 using WMMA". GPUOpen.com. Archived from the original on January 10, 2023. Retrieved August 14, 2023.

[12] Olšan, Jan (November 7, 2022). "AMD RDNA 3 details: architecture changes, AI acceleration, DP 2.1". HWCooling. Retrieved April 8, 2023.

[13] Klotz, Aaron (January 29, 2023). "AMD GPU Appears to Leave Room for Future 3D V-Cache". Tom's Hardware. Retrieved April 8, 2023.

[14] Ridley, Jacob (January 30, 2023). "Tiny spots on AMD's RDNA 3 GPU hint at massive cache potential". PC Gamer. Retrieved April 8, 2023.

[15] Shilov, Anton (May 4, 2022). "First Details About AMD's Next Generation Video Engine Revealed". Tom's Hardware. Retrieved April 10, 2023.

[16] Klotz, Aaron (December 12, 2022). "AMD's Radeon RX 7900 AV1 encoder is almost on par with Intel Arc and Nvidia's RTX 40 series". TechSpot. Retrieved April 8, 2023.

[17] Taylor, Adam (December 14, 2022). "Tested: With RDNA 3, AMD Radeon is finally useful for content creators". PCWorld. Retrieved April 8, 2023.

[18] Sag, Anshel (November 14, 2022). "AMD's New Radeon RX 7900XTX And 7900XT Put The Pressure On NVIDIA". Forbes. Retrieved April 8, 2023.

[19] "AMD Unveils World's Most Advanced Gaming Graphics Cards, Built on Groundbreaking AMD RDNA 3 Architecture with Chiplet Design". AMD (Press release). April 21, 2023.

[27] "AMD Radeon RX 7600 Specs". TechPowerUp. Retrieved May 24, 2023.

[28] "AMD Radeon RX 7700 XT Specs". TechPowerUp. August 25, 2023. Retrieved August 25, 2023.

[29] "AMD Radeon RX 7800 XT Specs". TechPowerUp. August 25, 2023. Retrieved August 25, 2023.

[30] "AMD Radeon RX 7900 XT Specs". TechPowerUp. Retrieved November 4, 2022.

[31] "AMD Radeon RX 7900 XTX Specs". TechPowerUp. Retrieved November 4, 2022.

[37] "AMD Radeon RX 7600S Specs". TechPowerUp. Retrieved January 16, 2023.

[38] "AMD Radeon RX 7600M Specs". TechPowerUp. Retrieved January 16, 2023.

[39] "AMD Radeon RX 7600M XT Specs". TechPowerUp. Retrieved April 20, 2023.

[40] "AMD Radeon RX 7700S Specs". TechPowerUp. Retrieved January 16, 2023.

[48] "AMD Radeon PRO W7500 Professional Graphics". AMD. Retrieved August 4, 2023.

[PRO_W7600_release-49] "New AMD Radeon PRO W7000 Series Workstation Graphics Cards Deliver Advanced Technologies and Exceptional Performance for Mainstream Professional Workflows" (Press release). AMD. August 3, 2023. Retrieved August 4, 2023.

[50] "AMD Radeon PRO W7500 Specs". TechPowerUp. Retrieved August 4, 2023.

[51] "AMD Radeon PRO W7600 Professional Graphics". AMD. Retrieved August 4, 2023.

[52] "AMD Radeon PRO W7600 Specs". TechPowerUp. Retrieved August 4, 2023.

[53] "AMD Radeon PRO W7800 Professional Graphics". AMD. Retrieved April 13, 2023.

[PRO_W7000_release-54] "AMD Unveils the Most Powerful AMD Radeon PRO Graphics Cards, Offering Unique Features and Leadership Performance to Tackle Heavy to Extreme Professional Workloads" (Press release). AMD. April 13, 2023. Retrieved April 13, 2023.

[55] "AMD Radeon PRO W7800 Specs". TechPowerUp. Retrieved April 13, 2023.

[56] "AMD Radeon PRO W7900 Professional Graphics". AMD. Retrieved April 13, 2023.

[57] "AMD Radeon PRO W7900 Specs". TechPowerUp. Retrieved April 13, 2023.