Qualcomm Centriq

Brand of SoCs by Qualcomm

Samsung^[1]

Architecture and classificationInstructionsARMv8-APhysical specificationsCores

up to 48

Products, models, variantsCore name(s)

Falkor

Centriq (/sɛnˈtriːk/ sen-TREEK^[2]) is a brand of system on a chip (SoC) semiconductor products designed and marketed by Qualcomm for data centers. The Centriq central processing unit (CPU) uses the ARM RISC instruction set, with multiple CPU cores in a single chip.

History

Pre-release

In November 2014, Qualcomm announced it was developing an ARM ARMv8-A microarchitecture based CPU that was purpose-built for data centers.^[3] In December 2016, the company announced and demonstrated the first multi-core CPUs based on a custom ARM ARMv8-A microarchitecture.

Early products

The first Centriq 2400 series of products were made available to server manufacturers in November 2017.^[1] With these first products, Qualcomm introduced its "Falkor" ARMv8-A microarchitecture. The chip has up to 48 of Qualcomm's custom designed "Falkor" cores at up to 2.6GHz, with six-channel DDR4 memory and a 60 MB L3 cache.^[4]^[5]

Market environment

A number of reviews have noted at its release that the Centriq is expected to face significant competition from established x86-64 data-center CPU manufacturers Intel and AMD, and ARM microarchitecture server products such as Cavium's ThunderX2.^[6]^[7] In addition to competitive pressures, it has been noted that running established workloads on ARM microarchitectures requires re-optimizing and recompiling the software, or x86-64 emulation, presenting a barrier to entry for some potential customers.

References

^ ^a ^b Kennedy, Anthony (8 November 2017). "Qualcomm Centriq 2400 Officially Launched". Serve the Home. Retrieved 14 November 2017.
^ "Qualcomm ARM Server Centriq 2400 at Linaro Connect San Francisco 2017". Retrieved 15 December 2019.
^ Shilov, Anton (16 December 2016). "Qualcomm Demos 48-core Centriq Server SoC in Action, Begins Sampling". Anandtech. Retrieved 14 November 2017.
^ Kennedy, Patrick (23 August 2017). "Qualcomm Centriq 2400 ARM CPU from Hot Chips 29". Serve The Home. Retrieved 14 November 2017.
^ Kennedy, Patrick (6 October 2017). "New Qualcomm Centriq 2400 details 48 cores 60MB L3 cache over 2GHz". Serve the Home. Retrieved 14 November 2017.
^ Cutress, Ian (20 August 2017). "Analyzing Falkor's Microarchitecture". Anandtech. Retrieved 14 November 2017.
^ Kennedy, Patrick (8 November 2017). "Analyzing Key Qualcomm Centriq 2400 Market Headwinds". Serve the Home. Retrieved 14 November 2017.

External links

Official website

ARM-based chips

Application ARM-based chips

Application
processors
(32-bit)

ARMv7-A

Cortex-A5	Actions ATM702x Amlogic M805/S805, T82x Atmel SAMA5D3 InfoTM iMAPx820, iMAPx15 Qualcomm Snapdragon S4 Play, 200 RDA RDA8810PL Telechips TCC892x
Cortex-A7	Allwinner A2x, A3x, A83T, H3, H8 NXP i.MX7, QorIQ LS10xx, NXP i.MX6UL Broadcom VideoCore BCM2836, BCM23550 Leadcore LC1813, LC1860/C, LC1913, LC1960 Marvell Armada PXA1920, 1500 mini plus MediaTek MT65xx Qualcomm Snapdragon 200, 400
Cortex-A8	Allwinner A1x Apple A4 Freescale i.MX5 Rockchip RK291x Samsung Exynos 3110(S5PC110), S5PV210 Texas Instruments OMAP 3 Texas Instruments Sitara AM3xxx Texas Instruments DM38x ZiiLABS ZMS-08
Cortex-A9	Actions ATM702x, ATM703x Altera Cyclone V, Arria V/10 Amlogic AML8726, MX, M6x, M801, M802/S802, S812, T86x Apple A5, A5X Broadcom VideoCore BCM21xxx, BCM28xxx Freescale i.MX6 HiSilicon K3V2, 910's InfoTM iMAPx912 Leadcore LC1810, LC1811 Marvell Armada 1500 mini MediaTek MT65xx Nvidia Tegra, 2, 3, 4i Nufront NuSmart 2816M, NS115, NS115M Renesas EMMA EV2, R-Car H1, RZ/A Rockchip RK292x, RK30xx, RK31xx Samsung Exynos 4 421x, 441x ST-Ericsson NovaThor Telechips TCC8803 Texas Instruments OMAP 4 Texas Instruments Sitara AM4xxx VIA WonderMedia WM88x0, 89x0 Xilinx Zynq-7000 ZiiLABS ZMS-20, ZMS-40
Cortex-A15	Allwinner A80 HiSilicon K3V3 MediaTek MT8135/V Nvidia Tegra 4, K1 Renesas R-Car H2 Samsung Exynos 5 52xx, 54xx Texas Instruments OMAP 5, DRA7xx, AM57xx Texas Instruments Sitara AM5xxx
Cortex-A17	MediaTek MT6595, MT5595 MStar 6A928 Rockchip RK3288
Others	Cortex-A12
ARMv7-A compatible	Apple A6, A6X, S1, S1P, S2, S3 Broadcom Brahma-B15 Marvell P4J Qualcomm Snapdragon S1, S2, S3, S4 Plus, S4 Pro, 600, 800 (Scorpion, Krait)

ARMv8-A

Others	Cortex-A32

Application
processors
(64-bit)

ARMv8-A

Cortex-A35	NXP i.MX8X MediaTek MT6799, MT8516 Rockchip RK3308
Cortex-A53	Actions GT7, S900, V700 Allwinner A64, H5, H64, R18 Altera Stratix 10 Amlogic S9 Family, T96x Broadcom BCM2837 EZchip TILE-Mx100 HiSilicon Kirin 620, 650, 655, 658, 659, 930, 935 Marvell Armada PXA1928, Mobile PXA1908/PXA1936 MediaTek MT673x, MT675x, MT6761V, MT6762/V, MT6763T, MT6765/G/H, MT6795, MT8161, MT8163, MT8165, MT8732, MT8735, MT8752 NXP ARM S32, QorIQ LS1088, LS1043, i.MX8M Qualcomm Snapdragon 215, 410, 412, 415, 425, 427, 430, 435, 429, 439, 450, 610, 615, 616, 617, 625, 626, 630 Renesas RZ/V2M Rockchip RK3328, RK3368 Samsung Exynos 7570, 7578, 7580, 7870, 7880 Texas Instruments Sitara AM6xxx UNISOC SC9820E, SC9832E, SC9860/GV Xilinx ZynqMP
Cortex-A57	AMD Opteron A1100-series NXP QorIQ LS20xx Nvidia Tegra X1 and Tegra X2 Qualcomm Snapdragon 808 and 810 Samsung Exynos 7 5433, 7420 HiSilicon Kirin Hi1610 and Hi1612
Cortex-A72	AWS Graviton Broadcom BCM2711 HiSilicon Kirin 950, 955, Kunpeng 916 MediaTek MT6797/D/T/X, MT8173, MT8176, MT8693 MStar 6A938 Qualcomm Snapdragon 650, 652, 653 Rockchip RK3399 NXP QorIQ LS2088, QorIQ LS1046A, QorIQ LX2160A, QorIQ LS1028A, i.MX8
Cortex-A73	Qualcomm Snapdragon 460, 636, 660, 632, 662, 665, 680, 685, 835 Samsung Exynos 7872, 7884, 7885, 7904, 9609, 9610, 9611 HiSilicon Kirin 710, 960, 970 MediaTek MT6771/V, MT6799, MT8183, MT8788 Amlogic S922X
Others	Cortex-A34
ARMv8-A compatible	Ampere eMAG Apple A7, A8, A8X, A9, A9X, A10, A10X Applied Micro X-Gene Cavium ThunderX Nvidia Tegra K1 (Denver), Tegra X2 (Denver2) Qualcomm Kryo, Falkor Samsung Exynos M1 (Mongoose), M2 (Mongoose)

ARMv8.1-A

ARMv8.1-A compatible	Cavium ThunderX2

ARMv8.2-A

Cortex-A55	Samsung Exynos 850 UNISOC SC9863/A, T603
Cortex-A75	Qualcomm Snapdragon 670, 710, 712, 845, 850 Samsung Exynos 9820, 9825 MediaTek MT6769H/T/V/Z, MT6768, MT6779V UNISOC T310, T606, T610, T616, T618, T619, T700, T710, T740
Cortex-A76	Google Tensor HiSilicon Kirin 810, 820, 980, 985, 990 Qualcomm Snapdragon 480(+), 675, 678, 720G, 730(G), 732G, 765(G), 768G, 855(+) and 860, 7c, 7c Gen 2, 8c, 8cx and 8cx Gen 2 Microsoft SQ1 and SQ2 MediaTek MT6781, MT6785V, MT6789, MT6833V/P, MT6853V/T, MT6873, MT6875, Dimensity 6020, 6080, 6100+, 6300, MT8192 Samsung Exynos 990 UNISOC T750, T760, T770, T820
Cortex-A77	MediaTek Dimensity 1000(+) Qualcomm Snapdragon 690, 750G, 865(+) and 870 HiSilicon Kirin 9000 Samsung Exynos 880, 980
Cortex-A78	Google Tensor G2 MediaTek MT6877, MT6878, MT6879, MT6891, MT6893, Dimensity 7020, 7025, 7030, 7050, 8000, 8020, 8050, 8100, 8200, Kompanio 900T, 1200, 1380, 1300T Qualcomm Snapdragon 4 Gen 1, 4 Gen 2, 695, 6 Gen 1, 778G(+), 780G, 782G, 888(+) Samsung Exynos 1080, 1280, 1330, 1380, 2100
Cortex-X1	Google Tensor, Tensor G2 Qualcomm Snapdragon 888(+) Samsung Exynos 2100
Neoverse N1	Ampere Altra, Altra Max AWS Graviton2
Others	Cortex-A65, Cortex-A65AE, Cortex-A76AE, Cortex-A78C, Cortex-X1C, Neoverse E1
ARMv8.2-A compatible	Apple A11 Fujitsu A64FX HiSilicon TaiShan v110 Nvidia Tegra Xavier (Carmel) Samsung Exynos M3 (Meerkat), M4 (Cheetah), M5 (Lion)

ARMv8.3-A

ARMv8.3-A compatible	Apple A12, A12X/A12Z, S4, S5 Marvell ThunderX3

ARMv8.4-A

Neoverse V1	AWS Graviton3
ARMv8.4-A compatible	Apple A13, S6, S7, S8

ARMv8.5-A

ARMv8.5-A compatible	Apple A14, M1

ARMv8.6-A

ARMv8.6-A compatible	Apple A15, A16, A17, M2, M3

ARMv9.0-A

Cortex-A510	MediaTek Dimensity 7200 (Pro/Ultra), 8300 (Ultra), 9000/9000+, 9200 Qualcomm Snapdragon 7 Gen 1, 7s/7+ Gen 2, 7 Gen 3, 8(+) Gen 1, 8 Gen 2 Samsung Exynos 2200
Cortex-A710	MediaTek Dimensity 9000/9000+ Qualcomm Snapdragon 7 Gen 1, 7s/7+ Gen 2, 8(+) Gen 1, 8 Gen 2 Samsung Exynos 2200
Cortex-A715	MediaTek Dimensity 7200 (Pro/Ultra), 8300 (Ultra), 9200 Qualcomm Snapdragon 7 Gen 3, 8 Gen 2
Cortex-X2	MediaTek Dimensity 9000/9000+ Qualcomm Snapdragon 7s/7+ Gen 2, 8(+) Gen 1 Samsung Exynos 2200
Cortex-X3	Google Tensor G3 MediaTek Dimensity 9200/9200+ Qualcomm Snapdragon 8 Gen 2
Neoverse N2	Alibaba YiTian 710 Microsoft Azure Cobalt 100
Neoverse V2	AWS Graviton4 Nvidia Grace Google Axion

ARMv9.2-A

Cortex-A520	Qualcomm Snapdragon 7+ Gen 3, Snapdragon 8(s) Gen 3 Samsung Exynos 2400
Cortex-A720	MediaTek Dimensity 9300(+) Qualcomm Snapdragon 7+ Gen 3, Snapdragon 8(s) Gen 3 Samsung Exynos 2400
Cortex-X4	MediaTek Dimensity 9300(+) Qualcomm Snapdragon 7+ Gen 3, Snapdragon 8(s) Gen 3 Samsung Exynos 2400
Neoverse N3	-
Neoverse V3	-

Embedded ARM-based chips

Embedded
microcontrollers

Cortex-M0	Cypress PSoC 4000, 4100, 4100M, 4200, 4200DS, 4200L, 4200M Infineon XMC1000 Nordic nRF51 NXP LPC1100, LPC1200 nuvoTon NuMicro Sonix SN32F700 STMicroelectronics STM32 F0 Toshiba TX00 Vorago VA108x0
Cortex-M0+	Cypress PSoC 4000S, 4100S, 4100S+, 4100PS, 4700S, FM0+ Holtek HT32F52000 Microchip (Atmel) SAM C2, D0, D1, D2, DA, L2, R2, R3 NXP LPC800, LPC11E60, LPC11U60 NXP (Freescale) Kinetis E, EA, L, M, V1, W0 Raspberry Pi RP2040 Renesas Synergy S1 Silicon Labs (Energy Micro) EFM32 Zero, Happy STMicroelectronics STM32 L0
Cortex-M1	Altera FPGAs Cyclone-II, Cyclone-III, Stratix-II, Stratix-III Microsemi (Actel) FPGAs Fusion, IGLOO/e, ProASIC3L, ProASIC3/E Xilinx FPGAs Spartan-3, Virtex-2-3-4
Cortex-M3	Actel SmartFusion, SmartFusion 2 Analog Devices ADuCM300 Cypress PSoC 5000, 5000LP, FM3 Fujitsu FM3 Holtek HT32F Microchip (Atmel) SAM 3A, 3N, 3S, 3U, 3X NXP LPC1300, LPC1700, LPC1800 ON Semiconductor Q32M210 Silicon Labs Precision32 Silicon Labs (Energy Micro) EFM32 Tiny, Gecko, Leopard, Giant STMicroelectronics STM32 F1, F2, L1 Texas Instruments F28, LM3, TMS470, OMAP 4 Toshiba TX03
Cortex-M4	Microchip (Atmel) SAM 4L, 4N, 4S NXP (Freescale) Kinetis K, W2 Renesas RA4W1, RA6M1, RA6M2, RA6M3, RA6T1
Cortex-M4F	Cypress 6200, FM4 Infineon XMC4000 Microchip (Atmel) SAM 4C, 4E, D5, E5, G5 Microchip CEC1302 Nordic nRF52 NXP LPC4000, LPC4300 NXP (Freescale) Kinetis K, V3, V4 Renesas Synergy S3, S5, S7 Silicon Labs (Energy Micro) EFM32 Wonder STMicroelectronics STM32 F3, F4, L4, L4+, WB Texas Instruments LM4F/TM4C, MSP432 Toshiba TX04
Cortex-M7F	Microchip (Atmel) SAM E7, S7, V7 NXP (Freescale) Kinetis KV5x, i.MX RT 10xx, i.MX RT 11xx, S32K3xx STMicroelectronics STM32 F7, H7
Cortex-M23	GigaDevice CD32E2xx Microchip (Atmel) SAM L10, L11, and PIC 32CM-LE 32CM-LS Nuvoton M23xx family, M2xx family, NUC1262, M2L31 Renesas S1JA, RA2A1, RA2L1, RA2E1, RA2E2
Cortex-M33F	Analog Devices ADUCM4 Dialog DA1469x GigaDevice GD32E5, GD32W5 Nordic nRF91, nRF5340, nRF54 NXP LPC5500, i.MX RT600 ON RSL15 Renesas RA4, RA6 ST STM32 H5, L5, U5, WBA Silicon Labs Wireless Gecko Series 2
Cortex-M35P	STMicroelectronics ST33K
Cortex-M55F	Alif Semiconductor Ensemble Infineon PSoC Edge
Cortex-M85F	Renesas RA8

Real-time
microprocessors

Cortex-R4F	Texas Instruments RM4, TMS570 Renesas RZ/T1
Cortex-R5F	Scaleo OLEA Texas Instruments RM57, AM2 Xilinx Versal, ZynqMP, ZynqRF
Cortex-R7F	Renesas RZ/G2E, RZ/G2H, RZ/G2M, RZ/G2N
Cortex-R52F	NXP S32Z, S32E Renesas RZ/N2L, RZ/T2L, RZ/T2M
Cortex-R52+F	STMicroelectronics Stellar G, Stellar P

Classic ARM-based chips

Classic
processors

ARM7	Atmel SAM7L, SAM7S, SAM7SE, SAM7X, SAM7XC, AT91CAP7, AT91M, AT91R Cirrus Logic PS7xxx, EP7xxx Mediatek MT62xx NXP LPC2100, LPC2200, LPC2300, LPC2400, LH7 STMicroelectronics STR7
ARM9	Aspeed AST2400 Atmel SAM9G, SAM9M, SAM9N, SAM9R, SAM9X, SAM9XE, SAM926x, AT91CAP9 Cirrus Logic EP9xxx Freescale i.MX1x, i.MX2x Nuvoton NUC900 NXP LPC2900, LPC3000, LH7A Philips Nexperia PNX4008 Rockchip RK27xx, RK28xx Samsung S3C24xx STMicroelectronics Nomadik STn881x STMicroelectronics STR9 Texas Instruments OMAP 1, AM1x, DaVinci VIA WonderMedia WM8505/8650 ZiiLABS ZMS-05
ARM11	Broadcom BCM2835 Cavium CNS3xxx Freescale i.MX3x Infotmic IMAPX210/220 Mindspeed Comcerto 1000 Nvidia Tegra APX, 6xx Qualcomm MSM7000, Snapdragon S1 Samsung S3C64xx, S5P64xx ST-NXP Wireless Nomadik STn882x Telechips TCC8902 Texas Instruments OMAP 2 VIA WonderMedia WM87x0
ARMv2a compatible	Amber (open FPGA core)
ARMv4 compatible	Faraday FA526, FA626 DEC/Intel StrongARM
ARMv5TE compatible	Intel/Marvell XScale Marvell Sheeva, Feroceon, Jolteon, Mohawk Faraday FA606TE, FA616TE, FA626TE, FA726TE