Puma (microarchitecture)

The Puma Family 16h is a low-power microarchitecture by AMD for its APUs. It succeeds the Jaguar as a second-generation version, _targets the same market, and belongs to the same AMD architecture Family 16h. The Beema line of processors are aimed at low-power notebooks, and Mullins are _targeting the tablet sector.

Puma - Family 16h (2nd-gen)

General information
Launched	mid-2014
Discontinued	mid-2015
Common manufacturer	AMD
Performance
Max. CPU clock rate	1.35 GHz to 2.5 GHz
Cache
L1 cache	64 KB per core
L2 cache	1 MB to 2 MB shared
Architecture and classification
Technology node	28 nm
Instruction set	AMD64 (x86-64)
Physical specifications
Cores	2–4
GPUs	Radeon RX: 128 cores, 300–800 Mhz
Sockets	Socket AM1 Socket FT3b (BGA-769)
Products, models, variants
Core names	Beema Mullins
Brand name	AMD APU
History
Predecessor	Jaguar - Family 16h

This article is about the microarchitecture. For the 2008 mobile platform, see AMD mobile platform § Puma platform (2008).

Design

The Puma cores use the same microarchitecture as Jaguar, and inherits the design:

• Out-of-order execution and Speculative execution, up to 4 CPU cores
• Two-way integer execution
• Two-way 128-bit wide floating-point and packed integer execution
• Integer hardware divider
• Puma does not feature clustered multi-thread (CMT), meaning that there are no "modules"
• Puma does not feature Heterogeneous System Architecture or zero-copy
• 32 KiB instruction + 32 KiB data L1 cache per core
• 1–2 MiB unified L2 cache shared by two or four cores
• Integrated single channel memory controller supporting 64bit DDR3L
• 3.1 mm² area per core

Instruction set support

Like Jaguar, the Puma core has support for the following instruction sets and instructions: MMX, SSE, SSE2, SSE3, SSSE3, SSE4a, SSE4.1, SSE4.2, AVX, F16C, CLMUL, AES, BMI1, MOVBE (Move Big-Endian instruction), XSAVE/XSAVEOPT, ABM (POPCNT/LZCNT), and AMD-V.

Improvements over Jaguar

• 19% CPU core leakage reduction at 1.2V
• 38% GPU leakage reduction
• 500 mW reduction in memory controller power
• 200 mW reduction in display interface power
• Chassis temperature aware turbo boost
• Selective boosting according to application needs (intelligent boost)
• Support for ARM TrustZone via integrated Cortex-A5 processor
• Support for DDR3L-1866 memory

Puma+

AMD released a revision of the Puma microarchitecture, Puma+, which is integrated into the Carrizo-L APU platform.

Features

APU features table

Processors

See also: List of AMD processors with 3D graphics and List of AMD mobile processors

Desktop/Mobile (Beema)

Family	Model	Socket	CPU				GPU			TDP (W)	DDR3L Memory Speed
			Cores	Freq. (GHz)	Max. Turbo (GHz)	L2 Cache (MB)	Model	Config.	Max. Freq. (MHz)
A8	6410	Socket FT3b	4	2.0	2.4	2	Radeon R5	128:?:?	800	15	1866
A6	6310			1.8			Radeon R4
A4	6250J			2.0	—		Radeon R3		600	25	1600
A4	6210			1.8			Radeon R3			15
E2	6110			1.5			Radeon R2		500
E1	6010		2	1.35		1			350	10	1333

Tablet (Mullins)

Family	Model	CPU				GPU			Power		DDR3L Memory Speed
		Cores	Freq. (GHz)	Max. Turbo (GHz)	L2 Cache (MB)	Model	Config.	Max. Freq. (MHz)	TDP (W)	SDP (W)
A10 Micro	6700T	4	1.2	2.2	2	Radeon R6	128:?:?	500	4.5	2.8	1333
A6 Micro	6500T			1.8		Radeon R4		401
A4 Micro	6400T		1.0	1.6		Radeon R3		350
E1 Micro	6200T	2		1.4	1	Radeon R2		300	3.95		1066

External links

• Software Optimization Guide for Family 16h Processors
• 2014 AMD Low-Power Mobile APUs
• Jaguar presentation (video) at ISSCC 2013
• Discussion initiated on RWT forums by Jeff Rupley, Chief Architect of the Jaguar core
• BKDG for Family 16h Models 00h-0Fh Processors
• Revision Guide for Family 16h Models 00h-0Fh Processors (Jaguar)
• Revision Guide for Family 16h Models 30h-3Fh Processors (Puma)