Snapdragon 6 Gen 1 semble pas mal
4x CA78
@ 2.2GHz
4x CA55
@ 1.8GHz
pour le Snapdragon 4 Gen 1 (moins de gap (snap 480)
2x CA78
@ 2.0GHz
6x CA55
@ 1.8GHz
Cons
software compatibility of Windows on ARM
poor performance even in everyday use
eMMC storage
cramped keyboard
display with PWM
Qualcomm Snapdragon 7c Gen 2 8 x 2.6 GHz, Cortex-A76 / A55 (Kryo 468)
"the laptop will sometimes pause for a moment to think."
à fuir sous Windows ...
W5100 SoC
CPU – Quad-core Cortex-A53 processor @ up to 1.7 GHz
GPU – Qualcomm Adreno A702 @ up to 1 GHz with OpenGL ES 3.1 API support
DSP – Qualcomm Hexagon DSP V66K
System Memory – 16-bit LPDDR4 up to 2,133 MHz
Storage – eMMC 4.5 flash
Process – 4nm
Snapdragon W5+ and W5 Gen 1 platforms with up to 50% longer battery, twice the performance, and 30 percent smaller size.
Immortalis-G715, Mali-G715, G615: Hardware ray tracing and VRS move into new arm GPUs - ComputerBase
Arm provides 15 percent more performance
and 15 percent less consumption compared
to the previous generation with the same number of shader cores
+25% de perf CPU pour le Cortex-X3 (+20% en efficacité énergétique)
(dont +10% en IPC)
"Faster than an Intel Core i7-1260P in a notebook
The Cortex-X3 is said to offer a full plus of 34 percent single-core performance compared to today's processors in notebooks, whereby ARM uses a clock rate of 3.6 GHz in this scenario"
pour le CPU Cortex basse conso, le A715 :
the Cortex-A715 is to deliver the same performance as a Cortex-A710 using the same manufacturing process ("ISO Process"),
the power consumption of the core is a whopping 20 percent lower
Touting modest performance gains over the original M1 SoC of around 18% for multithreaded CPU workloads and 35% in peak GPU workloads,
1x Cortex-X2
@ 3.2GHz
3x Cortex-A710
@ 2.8GHz
4x Cortex-A510
@ 2.0GHz
+10% de perf
(dont +200mhz par coeur)
M1 MAX + M1 Max = M1 Ultra
Apple a connecté 2 M1 Max entre eux
RAM LPDDR5 soudée au Soc
performance CPU en nette hausse (24 coeurs CPU)
https://www.tomshardware.com/news/apple-m1-ultra-nearly-matches-amd-threadripper-3990x
(proche d'un 3990X de 64coeurs (zen2) !!! en multithread)
"Geekbench 5 results don't always line up with real-world performance, so we still need to take these results with a few doses of salt."
niveau GPU perf donc doublée
et surtout ils annoncent des perfs équivalentes avec une RTX3090 !!!! avec 200w de moins
mais "that Apple’s performance claims should be taken with a grain of salt, at least for now"
et surtout le process de gravure est différent (5nm vs 8nm)
https://www.cnx-software.com/2021/12/16/rockchip-rk3588-datasheet-sbc-coming-soon/
peut être bientôt dans les futurs autoradio, ça devrait avoiner.
CNX-Software remonte quelques tests qui montrent que le RK3588 est 2.7 fois plus performant en single-core sous Geekbench 4 que le précédent RK3399. Cette évolution monte à 3.4 fois en multi-core.
La partie graphique est, quant à elle, 6 fois plus rapide…
Antutu 9 score is about 540,000 points.
CPU – 4x Cortex-A76 @ up to 2.4/2.6 GHz and 4x Cortex-A55 cores @ 1.8 GHz in dynamIQ configuration
GPU
Arm Mali-G610 MP4 “Odin” GPU with support for OpenGLES 1.1, 2.0, and 3.2, OpenCL up to 2.2 and Vulkan1.2
2D graphics engine up to 8192×8192 source, 4096×4096 destination
Video decoding
8Kp60 H.265, VP9, AVS2, 8Kp30 H.264 AVC/MVC
4Kp60 AV1
1080p60 MPEG-2/-1, VC-1, VP8
Real-time 8Kp30 encoding with H.265/H.264; multi-channel encoding supported at lower resolutions
Memory I/F – LPDDR4/LPDDR4x/LPDDR5 up to 32GB
Storage – eMMC 5.1, SD/MMC, SATA 3.0 (multiplexed with PCIe 2.0), FSPI (Flexible SPI)
Video Output
Dual HDMI 2.1 / eDP 1.3 up to 8Kp60
Dual DisplayPort 1.4a up to 8Kp30 (multiplexed with USB 3.0)
Dual MIPI DSI output up to 4Kp60
Bt.1120 video output up to 1080p60
Optional dual LVDS up to 1080p60 via RK628 chip.
Up to four independent displays (up to 1x 8Kp60, 2x 4Kp60, 1x 1080p60)
Video Input/Camera
48MP (2x 24MP) ISP with HDR and 3D NR support; multi-camera input
2x MIPI DC (4-lane DPHY v2.0 or 3-lane CPHY V1.1),4x 2-lane MIPI CSI, DVP camera interface
HDMI Rx 2.0 interface up to 4Kp60 with HDCP 2.3 support
Audio
2x 8-channel I2S, 2x 2-channel I2S, 2x SPDIF, 2x 8-channel PDM (for mic arrays), 2-channel digital audio codec (16-bit DAC)
VAD engine
Networking – Dual Gigabit Ethernet
USB – 2x USB 3.1 Gen 1 up to 5 Gbps (multiplexed with DisplayPort), 1x USB 3.1 Gen 1 (multiplexed with Combo “PIPE PHY2”), 2x USB 2.0 OTG
PCIe – PCIe 3.0 up to 8 Gbps (1x 4-lane, or 2x 2-lane, or 4x 1-lane, or 1x 2-lane + 2x 1-lane
3x Combo PIPE PHY interfaces
Combo PIPE PHY0/1 – SATA III or PCIe2.1 up to 5 Gbps
Combo PIPE PHY2 – SATA III, PCIe 2.1, or USB 3.0
Low-speed I/O – 5x SPI, 9x I2C, 10x UART, GPIOs, 12-bit ADC (SARADC)
Package – FCBGA1088L; 21.45 x 21.45mm
Manufacturing process – 8nm LP
c'est quand même impressionnant sur certains points
https://www.anandtech.com/show/17016/the-apple-2021-fall-mac-event-live-blog-10am-pt-1700-utc
https://www.lesnumeriques.com/ordinateur-portable/nouveaux-macbook-pro-14-et-16-design-repense-ecran-miniled-a-encoche-et-performances-en-hausse-n170075.html
passage de 8 à 10coeurs
64Go LPDDR5 en 512bits
niveau GPU :
"In terms of performance, Apple is battling it out with the very best available in the market,
comparing the performance of the M1 Max to that of a mobile GeForce RTX 3080, at 100W less power (60W vs 160W).
Apple also includes a 100W TDP variant of the RTX 3080 for comparison, here, outperforming the NVIDIA discrete GPU, while still using 40% less power."
"La Xbox Series X aura une puissance de 12 TFlops alors que la PS5 se limitera à 10,28 téraflops"
et le M1Max aurait 10TFlops
je demande à voir
il s’agit d’un Cortex-M0 32 bits
La solution embarquera 128 bytes de RAM
et 456 bytes de ROM
Il vient en effet de faire la démonstration d'une GeForce RTX 3060 utilisée avec une puce MediaTek Kompanio 1200
capables de faire fonctionner une démo (The Bistro) et Wolfenstein : Youngblood sous Arch Linux,
sans la moindre trace de puce x86, de Windows ou de DirectX. Ce, bien que plusieurs technologies maison étaient utilisées.
avec Chromium !
4 modèles sont actuellement marketés, allant de 8 cœurs à 25 W maximum jusqu’à la bagatelle de 36 cœurs pour seulement 60 W (et 72 Mio de L3)
2.5ghz
The CPU performance of Armv9 SoC is expected to increase by more than 30% over the next two generations of mobile and infrastructure CPUs,