I am currently looking for a laptop to use for university next year. I will be studying Computer Sciences and I am still debating which laptop I should get.
These where the laptops I had in mind:
Dell XPS 15 9570 (€ 1.829,00)
i7-8750H processor (4,1 GHz; 6-cores)
16 GB DDR4, 2.666 MHz
512 GB M.2 2280 PCIe
NVIDIA® GeForce® GTX 1050Ti 4 GB GDDR5
1920 x 1080 15'' display.
Up to 11h of battery life (97-Wh)
Asus ZenBook Pro UX550VD (€1.599)
i7-7700HQ processor (3,8 GHz; 4-cores)
16 GB SO-DIMM DDR4
512 GB M.2 PCIe
NVIDIA® GeForce® GTX 1050 4 GB GDDR5
1920 x 1080 15'' display.
Up to 8h of battery life
The XPS has better battery life and has a better screen.
The ZenBook is cheaper, has more ports but has an older processor and CPU.
Maby their is another PC that is better. I would love to see different suggestions. Please note that since I am living in Belgium not every laptop is available here.
I hope I can post this type of question on this website. I don't really know where else to post. If you are not allowed to post this on here, I am terribly sorry in advance!
Thank you for helping!
If you want to use for studies only then you could go for Asus. It is good anyway. If you want to have laptop for your job then go with Dell
I am developing a monitoring agent for GPU cards that is capable of providing real-time telemetry using CUDA and NVML libraries.
I want to understand a little more about GPU core operation vs how Intel/AMD CPU cores work.
One formula that can be used for CPUs is (cpumhz or Workload average peak CPU utilization (MHz)) as follows:
((CPUSPEED * CORES) /100) * CPULOAD = Workload average peak CPU utilization
More details are here
https://vikernel.wordpress.com/tag/vmware-formulas/
So would it be correct that the same formula can be applied to GPUs. The exception would be CUDA cores/shaders in place of "CORES" or could I just multiple the current clock speed by the actual gpu clock usage being that a GPU has a core clock for its 1000s of cores/shaders.
For example:
((GRAPHICS_MHZ * CUDA_CORES) /100) * GPU_LOAD = GPU MHZ utilization
Check out gpustat, it is a wrapper of nvidia-smi.
And GPUtil, it can fetch Maximum current relative load for a GPU
I think I found my answer based on how a GPU card works. Being that each core runs in parallel they are working a lot more effectively than a CPU core from what I have read.
With a CPU core, you can use the above formula, but if you want to see the mhz used on a gpu card, you can simple just use:
(GRAPHICS_MHZ * /100) * GPU_LOAD = GPU MHZ utilization
The good thing is that the GPU_LOAD you get back is a different calculation provided from a GPU card than what you get from a CPU card. If anyone has a different opinion, I would love to hear it.
I have a dell laptop, i7 5th gen processor(1000MHz) with 4 logical cores and 2 physical cores with 16 GB RAM. I have taken a course on High performance computing, for which I have to draw graphs of speed-up.
Compared to a Desktop machine(800 MHz) (i5 5th gen and 8GB RAM), having 4 physical and logical cores, for same program, my laptop takes ~3 seconds while on the desktop machine it takes around 12 seconds. Ideally, since the laptop is 1.25 times faster, the time on my laptop should have been around 9 to 10 seconds
This might not have been the problem if I had got almost similar speedup. But in my laptop, using 4 threads, the speedup is nearly equal to 1.3 and for the same number of cores, on my desktop the speedup is nearly equal to 3.5. If my laptop was fast, then it would have also reflected that property for parallel program, but the parallel program was only ~1.3 times faster. What could have been the reason?
Closed. This question is off-topic. It is not currently accepting answers.
Want to improve this question? Update the question so it's on-topic for Stack Overflow.
Closed 9 years ago.
Improve this question
I want build custom Linux kernel with shell. I am very poor in hardware module. Is there any Chinese board who offer custom development? I don't find any low cost Linux board or android boards. If I get a cheap tablet, can I use it for my experiment? I mean can I access nand of nor flash to burn codes or setup bootloader? I need some very low cost boards where I want to discover kernel components. Can any one suggest me what to do ?
Compared to the expensive (US$300-500) evaluation boards from SoC manufacturers a few years ago, there are now several choices for a "reasonable price", if not downright cheap, ARM boards capable of running Linux.
The lowest-cost board that has an ARM SoC with an MMU that runs Linux is probably the Raspberry PI, which retails for about US$25 (or $35 for the "B" version) and should be available worldwide. This board is intended to be an educational device for software development, so its I/O capabilities are home or consumer oriented. Other boards like the Beagle line are targeted more towards HW hackers and industrial users, and have better I/O expansion capabilities.
Instead of a bare board, there are units in an enclosure with a remote control such as the Mele A1000 or the A2000 with a SATA disk port. These are sold as hackable media players, and do come with consumer-ready firmware (Android).
ADDENDUM
A comparison list of over 40 development boards and modules that are available for running Linux is here
ADDENDUM 2
Another comparison list of development boards and modules (although not all of them can support Linux) is here
ADDENDUM 3
An updated list for 01/2015 of forty SBCs, in which nine cost less than US$50.
There are few ARM board available in market in reasonable price. Like BeagleBoard(8-9k in India) is full fledged ARM board and stripped down version of same is BeagleBone(around 4k in India). For x86 Intel board, there is one assembled by pheonix which comes in nearly 12k.
All these hardware can be customized. You can flash NAND chips/BIOS. Put your bootloader, kernel, filesystems from scratch.
and there is cubieboard for 49$, ATM.
The features of the cubieboard:
1G ARM cortex-A8 processor, NEON, VFPv3, 512KB L2 cache
Mali400, OpenGL ES GPU
1GB DDR3 #400MHz
HDMI 1080p Output
100M Ethernet
2 USB Host, 2 MMC slot, 1 ir
96 extend pin including i2c, spi, lcd, sata, sensors, ..
Running Android, Ubuntu and other Linux distributions
Odroid U2. With wifi capabilities will and 2GB ram will sell for $120-$150.
The cheapest development target is of course a virtual machine (if you want to stay with the same architecture as your development machine) or emulator such as QEMU (if you want a different architecture).
While emulating a full graphic system such as a high-resolution android tablet and actually emulating the processor can load even a modern machine, supporting a console mode or moderate resolution system should have tolerable performance. And if the architecture is the same such that virtualization can be used, performance should be fine for everyday use (VM solutions are routinely employed for end use, not just for development testing...)
Thanks to Ravi Pujar
Document source link
I wanted to move from the microcontroller world to the world of Embedded linux, So was searching for cheap ARM Linux development boards to start with. While wandering in the web i chose some ARM based boards which are available easily for buying in India,
AT91RM9200 board:
Atmel ARM9 based development board running # 180MHz comes packed with,
16MB NOR flash,
32MB NAND flash,
32MB SDRAM,
Ethernet, USB,
UART,
CAN,
LCD,
SDCARD,
LED's,
Switches.
This board is available for order at RhydolabZ website at the price of Rs 8,999/-
Beagle Bone board:
This board comes with a 720 MHz Super-scaler ARM Cortex A8 processor manufatured by Texas instruments. Beagle bone comes packed with a
256MB RAM,
USB,
Ethernet support,
SD CARD.
This board is a made specifically for hardware hacking, so the manufacturer has left out most of the processor pins accessible by connectors.
Beagle bone is available for order # element14 website at the price of Rs 6,669/-
Beagle board:
This board is built to give a laptop like performance and comes with a 1 GHz Super-scaler ARM Cortex A8 processor manufatured by Texas instruments. Beagle board comes packed with a
512MB RAM,
USB,
Ethernet,
S-Video,
Camera port,
Stereo IN/OUT,
micro SD CARD slot,
LCD expansion.
Beagle board is available for buying # NSK electronics website at the price of Rs 9,500/-
Mini2440 | S3C2440 AMR9 Board by Friendly ARM:
400 MHz Samsung S3C2440A ARM920T (max freq. 533 MHz)
64 MB SDRAM, 32 bit Bus
64 MB / 128 MB / 256 MB / 1GB NAND Flash and 2 MB NOR Flash with BIOS
256 Byte EEPROM (I2C)
SD-Card socket
DB9 connector (RS232), total: 3 serial port connectors
USB
3.5 mm stereo jack
Condenser microphone with connector
Ethernet
CR1220 Real Time Clock with battery
PWM buzzer
20 pin (2.0 mm) Camera interface
41 pin (1.0 mm) connector for FriendlyARM Displays and VGA Board
4 wire resistive touchscreen interface
6 push buttons and 1 A/D pot
4 LEDs
This board is avaialble for buying at NSK Electronics website at the price of Rs 7800/-
RASPBERRY PI:
The RASPBERRY PI is the cheapest ARM11 powered linux capable single board computer board you will ever find. This board runs an ARM11 processor #700MHz and comes with a 512 Mega Bytes of RAM memory. Here are the features of the board,
512MB SDRAM,
Ethernet, USB,
HDMI,
LINUX FEDORA OS,
ARM 11 processor #700MHz
BCM2835 SoC based chipset
RASPBERRY PI model B is available for purchase at element14.com website at the price of Rs.2750/-
RASPBERRY PI kit is also available for purchase from Tenet technotronics at the price of Rs.4000/-
A13-OLINUXINO:
Its a development board by Olimex powered by the A13 processor from Allwinner technology from China. Here are the features of the board,
A13 Cortex A8 processor at 1GHz, 3D Mali400 GPU
512 MB RAM
6-16VDC input power supply, noise immune design
3 + 1 USB hosts, 3 available for users, 1 leads to onboard pinout
1 USB OTG which can power the board
SD-card connector for booting the Linux image
VGA video output
LCD signals available on connector so you still can use LCD if you diasble VGA/HDMI
Audio output
Microphone input
RTC PCF8536 on board for real time clock and alarms
5 Keys on board for android navigation
UEXT connector for connecting addtional UEXT modules like Zigbee, Bluetooth, Relays, etc
GPIO connector with 68/74 pins and these signals
Optional low-cost 7" LCD with touchscreen
17 for adding NAND flash;
22 for connecting LCDs;
20+4 including 8 GPIOs which can be input, output, interrupt sources;
3x I2C;
2x UARTs;
SDIO2 for connectinf SDcards and modules;
5 system pins: +5V, +3.3V, GND, RESET, NMI
This board is available for purchase from Tenet technetronics India at the price of Rs. 4652 /-
IMX233-OLINUXINO-MICRO:
This mini development board is based on the Freescales i.mx233 processor from freescale semiconductors.
Here are the features of the board,
iMX233 ARM926J processor at 454Mhz
64 MB RAM
SD-card connector for booting the Linux image
TV PAL/NTSC video output
1 USB High Speed Host
three Buttons
2x30 pin GPIO for connection of other hardware
PCB dimensions: 3.00'' x 1.70'' (76.2mm x 43.2mm)
Nominal dimensions: 3.40'' x 1.70'' (86.4mm x 43.2mm)
This board is available for purchase from Tenet tech website India at the price of Rs. 2481 /-
IMX233-OLINUXINO-MINI:
The board is the mini version of the Olinuxino board mentioned above. Here are the features of this mini linux board
iMX233 ARM926J processor at 454Mhz
64 MB RAM
SD-card connector for booting the Linux image
TV PAL/NTSC video output
3 USB High Speed Host
optional WIFI RTL8188CU module
Stereo Audio Input
Stereo Headphones Audio Output
two Buttons
UEXT connector for connection of different peripherial modules
40 pin GPIO for connection of other hardware
Board is in shape for fit inside Pactec JM42 plastic box
Power supply input 6-16VDC
PCB dimensions: 3.70'' x 2.15'' (94.0mm x 54.6mm)
Nominal dimensions: 3.70'' x 2.65'' (94.0mm x 67.3mm)
This board is available for buying #Tenet tech website at the price of Rs. 3435 /-