Goldmont

Goldmont

General information
Product code	80668 (Apollo Lake) 80765 (Denverton)
Architecture and classification
Technology node	14 nm
Instructions	x86-64, Intel 64
Extensions	MMX, SSE, SSE2, SSE3, SSSE3, SSE4, SSE4.1, SSE4.2 AES-NI, RDRAND, CLMUL, SHA VT-x, VT-d
Physical specifications
Cores	2–4
Products, models, variants
Brand names	Atom Celeron Pentium
History
Predecessor	Airmont (die shrink)
Successor	Goldmont Plus (optimization)

Goldmont is a microarchitecture for low-power Atom, Celeron and Pentium branded processors used in systems on a chip (SoCs) made by Intel. They allow only one thread per core.

The Apollo Lake platform with 14 nm Goldmont core was unveiled at the Intel Developer Forum (IDF) in Shenzhen, China, April 2016.^[1] The Goldmont architecture borrows heavily from the Skylake Core processors, so it offers a more than 30 percent performance boost compared to the previous Braswell platform, and it can be used to implement power-efficient low-end devices including Cloudbooks, 2-in-1 netbooks, small PCs, IP cameras, and in-car entertainment systems.^[2][3]

Goldmont is the 2nd generation out-of-order low-power Atom microarchitecture designed for the entry level desktop and notebook computers.^[4] Goldmont is built on the 14 nm manufacturing process and supports up to four cores for the consumer devices. It includes the Intel Gen9 graphics architecture introduced with the Skylake.

The Goldmont microarchitecture builds on the success of the Silvermont microarchitecture, and provides the following enhancements:

• An out-of-order execution engine with a 3-wide superscalar pipeline.^[5] Specifically:
  • The decoder can decode 3 instructions per cycle.
  • The microcode sequencer can send 3 μops per cycle for allocation into the reservation stations.
  • Retirement supports a peak rate of 3 per cycle.
• Enhancement in branch prediction which de-couples the fetch pipeline from the instruction decoder.
• Larger out-of-order execution window and buffers that enable deeper out-of-order execution across integer, FP/SIMD, and memory instruction types.
• Fully out-of-order memory execution and disambiguation. The Goldmont microarchitecture can execute one load and one store per cycle (compared to one load or one store per cycle in the Silvermont microarchitecture). The memory execution pipeline also includes a second level TLB enhancement with 512 entries for 4KB pages.
• Integer execution cluster in the Goldmont microarchitecture provides three pipelines and can execute up to three simple integer ALU operations per cycle.
• SIMD integer and floating-point instructions execute in a 128-bit wide engine. Throughput and latency of many instructions have improved, including PSHUFB with 1-cycle throughput (versus 5 cycles for Silvermont microarchitecture) and many other SIMD instructions with doubled throughput.
• Throughput and latency of instructions for accelerating encryption/decryption (AES) and carry-less multiplication (PCLMULQDQ) have been improved significantly in the Goldmont microarchitecture.
• The Goldmont microarchitecture provides new instructions with hardware accelerated secure hashing algorithm, SHA1 and SHA256.
• The Goldmont microarchitecture also adds support for the RDSEED instruction for random number generation meeting the NIST SP800-90C standard.
• PAUSE instruction latency is optimized to enable better power efficiency.

• A 14 nm manufacturing process
• System on chip architecture
• 3D tri-gate transistors
• Consumer chips up to quad-cores
• Supports SSE4.2 instruction set
• Supports Intel AESNI and PCLMUL instructions
• Supports Intel RDRAND and RDSEED instructions
• Supports Intel SHA extensions
• Supports Intel MPX (Memory Protection Extensions)
• Gen 9 Intel HD Graphics with DirectX 12, OpenGL 4.6 with latest Windows 10 driver update^[6] (OpenGL 4.5 on Linux^[7]), OpenGL ES 3.2 and OpenCL 2.0 support.
• HEVC Main10 & VP9 Profile0 hardware decoding support
• 10 W thermal design power (TDP) Desktop or Server processors
• 4.0 to 6.0 W TDP mobile processors
• eMMC 5.0 technology to connect to NAND flash storage
• USB 3.1 & USB-C specification
• Support for DDR3L, LPDDR3, and LPDDR4 memory
• Integrated Sensor Hub (ISH) which can sample and combine data from individual sensors and operate independently when the host platform is in a low power state
• Image Signal Processor (ISP) supporting four concurrent camera streams
• Audio controller supporting HD Audio and LPE Audio
• Trusted Execution Engine 3.0 security subsystem

Similar to the previous Silvermont generation, design flaws were found in processor circuitry, resulting in cease of operation when processors are actively used for several years. An Erratum named APL46 "System May Experience Inability to Boot or May Cease Operation"^[8] was added to documentation in June 2017, stating that low pin count (LPC), real time clock (RTC), SD card and GPIO interfaces may stop functioning.

Mitigations^[9] were found to limit impact on systems. A firmware update for the LPC bus called LPC_CLKRUN# reduces the utilization of the LPC interface, which in turn decreases (but does not eliminate) LPC bus degradation – some systems are however not compatible with this new firmware. It is recommended not to use SD cards as boot devices, and to remove the card from the system when not in use; other possible solutions being using only UHS-I cards and operating them at 1.8 V.

Congatec also states the issues impact USB buses and eMMC, although those are not mentioned in Intel's public documentation. USB should have a maximum of 12% active time and there is a 60TB transmit traffic life expectancy over the lifetime of the port. eMMC should have a maximum of 33% active time and should be set to D3 device low power state by the operating system when not in use. Newer designs such as Atom C3000 Denverton do not seem to be affected.^[10]

List of desktop processors as follows:^[3][11]

Target segment	Cores (threads = cores)	Processor branding & model		GPU model		TDP (W)	CPU freq. (GHz)		GPU freq. (MHz)		L2 cache	Release date	Price (USD)
				Brand name & model number	EU		Base	Turbo	Base	Turbo
Desktop	4 (4)	Pentium	J4205	HD Graphics 505	18	10	1.5	2.6	250	800	2 MB	Q3 2016	$161
		Celeron	J3455	HD Graphics 500	12			2.3		750			$107
	2 (2)		J3355				2.0	2.5		700

Target segment	Cores (threads)	Processor branding & model		TDP (W)	CPU freq. (GHz)		L2 cache	DDR4 speed	Release date	Price (USD)
					Base	Turbo
Server	16 (16)	Atom	C3958[12][13]	31	2.0		16 MB	2400	Q3 2017	$449
	16 (16)		C3955[12]	32	2.1	2.4				$434
	12 (12)		C3858[12]	25	2.0		12 MB			$332
	12 (12)		C3850[12]		2.1	2.4				$323
	12 (12)		C3830[12]	21	1.9	2.3		2133		$289
	12 (12)		C3808[12]	25	2.0					$369
	8 (8)		C3758[12]		2.2		16 MB	2400		$193
	8 (8)		C3750[12]	21	2.2	2.4				$171
	8 (8)		C3708[12]	17	1.7			2133		$209
	4 (4)		C3558[12]	16	2.2		8 MB			$86
	4 (4)		C3538[12]	15	2.1					$75
	4 (4)		C3508[12]	11.25	1.6			1866		$86
	2 (2)		C3338[12]	9	1.5	2.2	4 MB		Q1 2017	$27
	2 (2)		C3308[12]	9.5	1.6	2.1			Q3 2017	$32

List of mobile processors as follows:^[3][11]

Target segment	Cores (Threads)	Processor branding & model		GPU model		TDP (W)	CPU freq. (GHz)		GPU freq. (MHz)		L2 cache	Release date	Price (USD)
				Brand name & model number	EU		Base	Turbo	Base	Turbo
Mobile	4 (4)	Pentium	N4200	HD Graphics 505	18	6	1.1	2.5	200	750	2 MB	Q3 2016	$161
		Celeron	N3450	HD Graphics 500	12			2.2		700			$107
	2 (2)		N3350					2.4		650

List of embedded processors as follows:

Target segment	Cores (threads)	Processor branding & model		GPU model		TDP (W)	CPU freq. (GHz)		GPU freq. (MHz)		L2 cache	Release date	Price (USD)
				Brand name & model number	EU		Base	Turbo	Base	Turbo
Embedded	4 (4)	Atom x7	E3950	HD Graphics 505	18	12	1.6	2.0	500	650	2 MB	Q3 2016	?
		Atom x5	E3940	HD Graphics 500	12	9.5		1.8	400	600
	2 (2)		E3930			6.5	1.3			550

There is also an Atom A3900 series exclusively for automotive customers with AEC-Q100 qualification:^[14]

Target segment	Cores (threads)	Processor branding & model		GPU model		TDP (W)	CPU freq. (GHz)		GPU freq. (MHz)		L2 cache	Release date	Price (USD)
				Brand name & model number	EU		Base	Turbo	Normal	Turbo
Automotive	4 (4)	Atom x7	A3960	HD Graphics 505	18	12.5	1.9	2.4	600	750	2 MB	?
			A3950			9.5	1.6	2.0	500	650
		Atom x5	A3940	HD Graphics 500	12	8		1.8	400	600
	2 (2)		A3930			6	1.3			550

Willow Trail platform was canceled. Apollo Lake will be offered instead.^[15]

• List of Intel CPU microarchitectures
• List of Intel Pentium microprocessors
• List of Intel Celeron microprocessors
• List of Intel Atom microprocessors
• Atom (system on chip)