Skip to content
linux-nerds.org

linux-nerds.org
  1. Übersicht
  2. Pine64
  3. ROCKPro64
  4. Images
  5. Mainline Kernel 4.20.x

Mainline Kernel 4.20.x

Verschoben Images
26 2 4.3k
  • FrankMF

    4.19.0-rc4-1065-ayufan released ✌

    • ayufan: defconfig: support tehuti 10gbps adapter

    Ok, 10gbps Netzwerkadapter läuft beim Kamil. 👏

    Im Fediverse -> @FrankM@nrw.social

    1. NanoPi R5S
    2. Quartz64 Model B, 4GB RAM
    3. Quartz64 Model A, 4GB RAM
    4. RockPro64 v2.1
    0
  • FrankMF

    4.19.0-rc4-1067-ayufan released

    • ayufan: dts: rockpro64: disable tx checksumming for gmac

    Im Fediverse -> @FrankM@nrw.social

    1. NanoPi R5S
    2. Quartz64 Model B, 4GB RAM
    3. Quartz64 Model A, 4GB RAM
    4. RockPro64 v2.1
    0
  • FrankMF

    4.19.0-rc4-1069-ayufan released

    • ayufan: rockpro64: fix emmc boot: Revert "mmc: sdhci-of-arasan: Add CQHCI…

    Im Fediverse -> @FrankM@nrw.social

    1. NanoPi R5S
    2. Quartz64 Model B, 4GB RAM
    3. Quartz64 Model A, 4GB RAM
    4. RockPro64 v2.1
    0
  • FrankMF

    4.19.0-rc4-1071-ayufan released

    • rockchip: pcie: limit bus number to 31 inclusive

    Im Fediverse -> @FrankM@nrw.social

    1. NanoPi R5S
    2. Quartz64 Model B, 4GB RAM
    3. Quartz64 Model A, 4GB RAM
    4. RockPro64 v2.1
    0
  • FrankMF

    4.19.0-1073-ayufan released

    Liste der Änderungen nicht gefunden. Es sind ein paar Dinge wohl geändert worden. Kann man hier nachlesen.

    Im Fediverse -> @FrankM@nrw.social

    1. NanoPi R5S
    2. Quartz64 Model B, 4GB RAM
    3. Quartz64 Model A, 4GB RAM
    4. RockPro64 v2.1
    0
  • FrankMF

    4.20.0-rc6-1075-ayufan released

    Jede Menge Änderungen im dts File, die aber von Kamil noch nicht angepasst sind. Mein Testimage hier läuft mit PCIe NVMe SSD nicht. Also, noch abwarten!!

    (19:26:49) FrankM: ayufan5: 4.20 without pcie ? nvm card don't recognized. with 4.4 no problem.
    (19:31:02) ayufan5: FrankM: I did not yet fix dts 🙂

    Im Fediverse -> @FrankM@nrw.social

    1. NanoPi R5S
    2. Quartz64 Model B, 4GB RAM
    3. Quartz64 Model A, 4GB RAM
    4. RockPro64 v2.1
    0
  • FrankMF

    4.20.0-1077-ayufan released

    Änderungen sind mir zur Zeit noch nicht bekannt. Test steht noch aus.

    PCIe NVMe Karte geht wieder.

    Kernel

    rock64@rockpro64:/mnt$ uname -a
Linux rockpro64 4.20.0-1077-ayufan-gdeb16128b458 #ayufan SMP PREEMPT Sun Dec 30 12:00:17 UTC 2018 aarch64 aarch64 aarch64 GNU/Linux

    iozone

    rock64@rockpro64:/mnt$ sudo iozone -e -I -a -s 100M -r 4k -r 16k -r 512k -r 1024k -r 16384k -i 0 -i 1 -i 2 
	Iozone: Performance Test of File I/O
	        Version $Revision: 3.429 $
		Compiled for 64 bit mode.
		Build: linux 

	Contributors:William Norcott, Don Capps, Isom Crawford, Kirby Collins
	             Al Slater, Scott Rhine, Mike Wisner, Ken Goss
	             Steve Landherr, Brad Smith, Mark Kelly, Dr. Alain CYR,
	             Randy Dunlap, Mark Montague, Dan Million, Gavin Brebner,
	             Jean-Marc Zucconi, Jeff Blomberg, Benny Halevy, Dave Boone,
	             Erik Habbinga, Kris Strecker, Walter Wong, Joshua Root,
	             Fabrice Bacchella, Zhenghua Xue, Qin Li, Darren Sawyer,
	             Vangel Bojaxhi, Ben England, Vikentsi Lapa.

	Run began: Sun Dec 30 13:50:15 2018

	Include fsync in write timing
	O_DIRECT feature enabled
	Auto Mode
	File size set to 102400 kB
	Record Size 4 kB
	Record Size 16 kB
	Record Size 512 kB
	Record Size 1024 kB
	Record Size 16384 kB
	Command line used: iozone -e -I -a -s 100M -r 4k -r 16k -r 512k -r 1024k -r 16384k -i 0 -i 1 -i 2
	Output is in kBytes/sec
	Time Resolution = 0.000001 seconds.
	Processor cache size set to 1024 kBytes.
	Processor cache line size set to 32 bytes.
	File stride size set to 17 * record size.
                                                              random    random     bkwd    record    stride                                    
              kB  reclen    write  rewrite    read    reread    read     write     read   rewrite      read   fwrite frewrite    fread  freread
          102400       4   105475   150901   165040   168152    55921   146649                                                          
          102400      16   323077   419261   446377   452714   199703   418553                                                          
          102400     512  1035241  1048622   962876   983026   776039  1044747                                                          
          102400    1024  1066733  1024204   922389   946779   863405  1042164                                                          
          102400   16384   942288  1384367  1395018  1457672  1446158  1372405                                                          

iozone test complete.

    Im Fediverse -> @FrankM@nrw.social

    1. NanoPi R5S
    2. Quartz64 Model B, 4GB RAM
    3. Quartz64 Model A, 4GB RAM
    4. RockPro64 v2.1
    0
  • FrankMF

    4.20.0-1081-ayufan & 4.20.0-1083-ayufan released

    1081 & 1083

    mmc: core: Add MMC Command Queue Support kernel parameter

    This parameter offers a workaround for cards that report command queue
    (CMDQ) support but don't work correctly when CMDQ is enabled. At least
    some ROCKPro64 + Foresee (32GB) eMMC card combinations have trouble
    working correctly. Setting mmc_cmdqueue=off in kernel command line
    disables CMDQ support and may help with troublesome hardware.

    Im Fediverse -> @FrankM@nrw.social

    1. NanoPi R5S
    2. Quartz64 Model B, 4GB RAM
    3. Quartz64 Model A, 4GB RAM
    4. RockPro64 v2.1
    0
  • FrankMF

    4.20.0-1088-ayufan released ✌

    ayufan: defconfig: add rockchip_linux_defconfig

    Im Fediverse -> @FrankM@nrw.social

    1. NanoPi R5S
    2. Quartz64 Model B, 4GB RAM
    3. Quartz64 Model A, 4GB RAM
    4. RockPro64 v2.1
    0
  • F

    Läuft damit auch der delock Sata Controller?
    Ich befürchte du testest auf einem separatem RP64, oder?

    0
  • F flockeee

    Läuft damit auch der delock Sata Controller?
    Ich befürchte du testest auf einem separatem RP64, oder?

    FrankMF

    @flockeee Aktuell teste ich auf einem anderen. Ich kann aber mal die SD-Karten tauschen 😉

    Im Fediverse -> @FrankM@nrw.social

    1. NanoPi R5S
    2. Quartz64 Model B, 4GB RAM
    3. Quartz64 Model A, 4GB RAM
    4. RockPro64 v2.1
    0
  • F

    @FrankM Vielen Dank, brauchst Du nicht. Habe es gerade getestet und es funktioniert alles.

    1
  • F flockeee

    @FrankM Vielen Dank, brauchst Du nicht. Habe es gerade getestet und es funktioniert alles.

    FrankMF

    @flockeee Ok, dann kann ich ja updaten 😉

    Kleine Ergänzung. Heute nach dem Einschalten.

    Welcome to Ubuntu 18.04.1 LTS (GNU/Linux 4.20.0-1088-ayufan-gaac9b4fce0ab aarch64)

    Alles aktualisiert

    Welcome to Ubuntu 18.04.2 LTS (GNU/Linux 4.20.0-1088-ayufan-gaac9b4fce0ab aarch64)

    Im Fediverse -> @FrankM@nrw.social

    1. NanoPi R5S
    2. Quartz64 Model B, 4GB RAM
    3. Quartz64 Model A, 4GB RAM
    4. RockPro64 v2.1
    0
  • FrankMF

    4.20.0-1090-ayufan released

    Änderungen -> https://gitlab.com/ayufan-repos/rock64/linux-mainline-kernel/commits/master

    Im Fediverse -> @FrankM@nrw.social

    1. NanoPi R5S
    2. Quartz64 Model B, 4GB RAM
    3. Quartz64 Model A, 4GB RAM
    4. RockPro64 v2.1
    0
Anmelden zum Antworten

  • N

    ROCKPro64: NAS mit PCI-e SATA-III Aufrüsten

    ROCKPro64 rockpro64
    13
    0 Stimmen
    13 Beiträge
    1k Aufrufe
    N
    @frankm Alles Klar! Wie schon erwähnt, für meine Zwecke rechts! Die Jahre über hat gute Dienste geleistet (PCI-e und HDD) und wird hoffentlich auch noch ein paar Jahre bis zum nächsten Umbau tun! Vielen Dank!
  • FrankMF

    ROCKPro64 - Armbian - NAS umgezogen

    Armbian armbian rockpro64
    2
    0 Stimmen
    2 Beiträge
    677 Aufrufe
    FrankMF
    Das NAS mit den drei 2,5 Zoll HDD Platten läuft an einem 3A Netzteil - ohne Probleme. Hat heute Nacht die Jobs einwandfrei erledigt https://www.pine64.org/?product=rockpro64-12v-3a-eu-power-supply
  • FrankMF

    ROCKPro64 - Armbian nand-sata-install

    Verschoben Armbian armbian rockpro64
    14
    6
    0 Stimmen
    14 Beiträge
    2k Aufrufe
    FrankMF
    Ich habe heute, nachdem es einige Updates von Armbian gab, mal nachgeschaut ob ein spezieller Fehler verschwunden ist. Und zwar geht es um das Resizen der Partion nachdem wir Armbian auf eine USB-HDD (USB3) installiert haben. Ich setze dafür folgendes System ein. Hardware ROCKPro64v2.0 4GB RAM SanDisk 240GB 2,5 Zoll HDD (nix tolles) Software Welcome to ARMBIAN 5.67.181217 nightly Debian GNU/Linux 9 (stretch) 4.4.167-rockchip64 Was sehe ich nach dem Reboot? root@rockpro64:~# df -h Filesystem Size Used Avail Use% Mounted on udev 1.9G 0 1.9G 0% /dev tmpfs 388M 5.3M 383M 2% /run /dev/sda1 220G 1.3G 207G 1% / tmpfs 1.9G 0 1.9G 0% /dev/shm tmpfs 5.0M 4.0K 5.0M 1% /run/lock tmpfs 1.9G 0 1.9G 0% /sys/fs/cgroup tmpfs 1.9G 4.0K 1.9G 1% /tmp /dev/mmcblk0p1 58G 1.3G 57G 3% /media/mmcboot /dev/zram0 49M 3.0M 43M 7% /var/log tmpfs 388M 0 388M 0% /run/user/0 Korrekt die Größe angepasst! Schnell mal den USB3 testen root@rockpro64:~# sudo dd if=/dev/zero of=sd.img bs=1M count=4096 conv=fdatasync 4096+0 records in 4096+0 records out 4294967296 bytes (4.3 GB, 4.0 GiB) copied, 38.0723 s, 113 MB/s Der Adapter root@rockpro64:~# lsusb -vvv Bus 004 Device 002: ID 2109:0715 VIA Labs, Inc. Device Descriptor: bLength 18 bDescriptorType 1 bcdUSB 3.10 bDeviceClass 0 (Defined at Interface level) bDeviceSubClass 0 bDeviceProtocol 0 bMaxPacketSize0 9 idVendor 0x2109 VIA Labs, Inc. idProduct 0x0715 bcdDevice 1.31 iManufacturer 1 VLI Manufacture String iProduct 2 VLI Product String iSerial 3 000000123ADA bNumConfigurations 1 Configuration Descriptor: bLength 9 bDescriptorType 2 wTotalLength 121 bNumInterfaces 1 bConfigurationValue 1 iConfiguration 0 bmAttributes 0x80 (Bus Powered) MaxPower 224mA Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 0 bAlternateSetting 0 bNumEndpoints 2 bInterfaceClass 8 Mass Storage bInterfaceSubClass 6 SCSI bInterfaceProtocol 80 Bulk-Only iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x81 EP 1 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 15 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x02 EP 2 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 15 Interface Descriptor: bLength 9 bDescriptorType 4 bInterfaceNumber 0 bAlternateSetting 1 bNumEndpoints 4 bInterfaceClass 8 Mass Storage bInterfaceSubClass 6 SCSI bInterfaceProtocol 98 iInterface 0 Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x04 EP 4 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 Command pipe (0x01) Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x85 EP 5 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 15 MaxStreams 32 Data-in pipe (0x03) Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x06 EP 6 OUT bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 15 MaxStreams 32 Data-out pipe (0x04) Endpoint Descriptor: bLength 7 bDescriptorType 5 bEndpointAddress 0x87 EP 7 IN bmAttributes 2 Transfer Type Bulk Synch Type None Usage Type Data wMaxPacketSize 0x0400 1x 1024 bytes bInterval 0 bMaxBurst 0 MaxStreams 32 Status pipe (0x02) Binary Object Store Descriptor: bLength 5 bDescriptorType 15 wTotalLength 70 bNumDeviceCaps 4 FIXME: alloc bigger buffer for device capability descriptors Device Status: 0x0000 (Bus Powered) Ein lästiger Fehler weniger.
  • FrankMF

    Booten von der NVMe Platte

    ROCKPro64 howto rockpro64
    16
    0 Stimmen
    16 Beiträge
    8k Aufrufe
    S
    Für dies Kernal: Linux rockpro64 4.4.167-1213-rockchip-ayufan-g34ae07687fce #1 SMP Tue Jun 18 20:44:49 UTC 2019 aarch64 GNU/Linux Booten von der NVMe Platte nicht möglich. Ich folgte die folgende Schritte. Leider funktioniert es nicht. Es gibt einen Fehler in Boot. Ohne RAID oder LVM config. Specs: Rockpro64 Marvel PCIe 88se9230 karte SANDISK SSD 120 GB
  • FrankMF

    ROCKPro64 - Der Bootvorgang

    Verschoben Hardware hardware rockpro64
    3
    0 Stimmen
    3 Beiträge
    2k Aufrufe
    FrankMF
    Um einen neuen Kernel booten zu können, brauche ich diese 4 Dateien unter /boot config-4.19.0-rc4-1065-ayufan-g72e04c7b3e06 initrd.img-4.19.0-rc4-1065-ayufan-g72e04c7b3e06 System.map-4.19.0-rc4-1065-ayufan-g72e04c7b3e06 vmlinuz-4.19.0-rc4-1065-ayufan-g72e04c7b3e06 Und den Ordner /boot/dtbs/4.19.0-rc4-1065-ayufan-g72e04c7b3e06 mit folgendem Inhalt rock64@rockpro64v2_0:/boot/dtbs/4.19.0-rc4-1065-ayufan-g72e04c7b3e06$ ls -la total 104 drwxr-xr-x 26 root root 4096 Sep 30 09:54 . drwxr-xr-x 6 root root 4096 Sep 30 09:55 .. drwxr-xr-x 2 root root 4096 Sep 30 09:54 al drwxr-xr-x 2 root root 4096 Sep 30 09:54 allwinner drwxr-xr-x 2 root root 4096 Sep 30 09:54 altera drwxr-xr-x 2 root root 4096 Sep 30 09:54 amd drwxr-xr-x 2 root root 4096 Sep 30 09:54 amlogic drwxr-xr-x 2 root root 4096 Sep 30 09:54 apm drwxr-xr-x 2 root root 4096 Sep 30 09:54 arm drwxr-xr-x 4 root root 4096 Sep 30 09:54 broadcom drwxr-xr-x 2 root root 4096 Sep 30 09:54 cavium drwxr-xr-x 2 root root 4096 Sep 30 09:54 exynos drwxr-xr-x 2 root root 4096 Sep 30 09:54 freescale drwxr-xr-x 2 root root 4096 Sep 30 09:54 hisilicon drwxr-xr-x 2 root root 4096 Sep 30 09:54 lg drwxr-xr-x 2 root root 4096 Sep 30 09:54 marvell drwxr-xr-x 2 root root 4096 Sep 30 09:54 mediatek drwxr-xr-x 2 root root 4096 Sep 30 09:54 nvidia drwxr-xr-x 2 root root 4096 Sep 30 09:54 qcom drwxr-xr-x 2 root root 4096 Sep 30 09:54 renesas drwxr-xr-x 2 root root 4096 Sep 30 09:54 rockchip drwxr-xr-x 2 root root 4096 Sep 30 09:54 socionext drwxr-xr-x 2 root root 4096 Sep 30 09:54 sprd drwxr-xr-x 2 root root 4096 Sep 30 09:54 synaptics drwxr-xr-x 2 root root 4096 Sep 30 09:54 xilinx drwxr-xr-x 2 root root 4096 Sep 30 09:54 zte Unter /boot/extlinux liegt dann die Datei extlinux.conf Die sieht bei mir dann so aus timeout 10 menu title select kernel label kernel-4.19.0-rc4-1065-ayufan-g72e04c7b3e06 kernel /boot/vmlinuz-4.19.0-rc4-1065-ayufan-g72e04c7b3e06 initrd /boot/initrd.img-4.19.0-rc4-1065-ayufan-g72e04c7b3e06 devicetreedir /boot/dtbs/4.19.0-rc4-1065-ayufan-g72e04c7b3e06 append rw panic=10 init=/sbin/init coherent_pool=1M ethaddr=${ethaddr} eth1addr=${eth1addr} serial=${serial#} cgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory swapaccount=1 root=LABEL=TEST rootwait rootfstype=ext4 label kernel-4.19.0-rc4-1065-ayufan-g72e04c7b3e06-memtest kernel /boot/vmlinuz-4.19.0-rc4-1065-ayufan-g72e04c7b3e06 initrd /boot/initrd.img-4.19.0-rc4-1065-ayufan-g72e04c7b3e06 devicetreedir /boot/dtbs/4.19.0-rc4-1065-ayufan-g72e04c7b3e06 append rw panic=10 init=/sbin/init coherent_pool=1M ethaddr=${ethaddr} eth1addr=${eth1addr} serial=${serial#} cgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory swapaccount=1 root=LABEL=TEST rootwait rootfstype=ext4 memtest Darunter kommen dann evt. die alten Kernel die installiert waren, das habe ich hier im Beispiel weg gelassen.
  • FrankMF

    ROCKPro64 wieder vorbestellbar

    ROCKPro64 rockpro64
    5
    0 Stimmen
    5 Beiträge
    1k Aufrufe
    FrankMF
    Meine Lieferung ist unterwegs Hello Mr. Frank Mankel, Order 62068 just shipped on July 18, 2018 from Shenzhen transit to Hong Kong DHL.
  • FrankMF

    nodejs & NodeBB

    ROCKPro64 rockpro64
    1
    1
    0 Stimmen
    1 Beiträge
    543 Aufrufe
    Niemand hat geantwortet
  • FrankMF

    stretch-minimal-rockpro64

    Verschoben Linux rockpro64
    3
    0 Stimmen
    3 Beiträge
    1k Aufrufe
    FrankMF
    Mal ein Test was der Speicher so kann. rock64@rockpro64:~/tinymembench$ ./tinymembench tinymembench v0.4.9 (simple benchmark for memory throughput and latency) ========================================================================== == Memory bandwidth tests == == == == Note 1: 1MB = 1000000 bytes == == Note 2: Results for 'copy' tests show how many bytes can be == == copied per second (adding together read and writen == == bytes would have provided twice higher numbers) == == Note 3: 2-pass copy means that we are using a small temporary buffer == == to first fetch data into it, and only then write it to the == == destination (source -> L1 cache, L1 cache -> destination) == == Note 4: If sample standard deviation exceeds 0.1%, it is shown in == == brackets == ========================================================================== C copy backwards : 2812.7 MB/s C copy backwards (32 byte blocks) : 2811.9 MB/s C copy backwards (64 byte blocks) : 2632.8 MB/s C copy : 2667.2 MB/s C copy prefetched (32 bytes step) : 2633.5 MB/s C copy prefetched (64 bytes step) : 2640.8 MB/s C 2-pass copy : 2509.8 MB/s C 2-pass copy prefetched (32 bytes step) : 2431.6 MB/s C 2-pass copy prefetched (64 bytes step) : 2424.1 MB/s C fill : 4887.7 MB/s (0.5%) C fill (shuffle within 16 byte blocks) : 4883.0 MB/s C fill (shuffle within 32 byte blocks) : 4889.3 MB/s C fill (shuffle within 64 byte blocks) : 4889.2 MB/s --- standard memcpy : 2807.3 MB/s standard memset : 4890.4 MB/s (0.3%) --- NEON LDP/STP copy : 2803.7 MB/s NEON LDP/STP copy pldl2strm (32 bytes step) : 2802.1 MB/s NEON LDP/STP copy pldl2strm (64 bytes step) : 2800.7 MB/s NEON LDP/STP copy pldl1keep (32 bytes step) : 2745.5 MB/s NEON LDP/STP copy pldl1keep (64 bytes step) : 2745.8 MB/s NEON LD1/ST1 copy : 2801.9 MB/s NEON STP fill : 4888.9 MB/s (0.3%) NEON STNP fill : 4850.1 MB/s ARM LDP/STP copy : 2803.8 MB/s ARM STP fill : 4893.0 MB/s (0.5%) ARM STNP fill : 4851.7 MB/s ========================================================================== == Framebuffer read tests. == == == == Many ARM devices use a part of the system memory as the framebuffer, == == typically mapped as uncached but with write-combining enabled. == == Writes to such framebuffers are quite fast, but reads are much == == slower and very sensitive to the alignment and the selection of == == CPU instructions which are used for accessing memory. == == == == Many x86 systems allocate the framebuffer in the GPU memory, == == accessible for the CPU via a relatively slow PCI-E bus. Moreover, == == PCI-E is asymmetric and handles reads a lot worse than writes. == == == == If uncached framebuffer reads are reasonably fast (at least 100 MB/s == == or preferably >300 MB/s), then using the shadow framebuffer layer == == is not necessary in Xorg DDX drivers, resulting in a nice overall == == performance improvement. For example, the xf86-video-fbturbo DDX == == uses this trick. == ========================================================================== NEON LDP/STP copy (from framebuffer) : 602.5 MB/s NEON LDP/STP 2-pass copy (from framebuffer) : 551.6 MB/s NEON LD1/ST1 copy (from framebuffer) : 667.1 MB/s NEON LD1/ST1 2-pass copy (from framebuffer) : 605.6 MB/s ARM LDP/STP copy (from framebuffer) : 445.3 MB/s ARM LDP/STP 2-pass copy (from framebuffer) : 428.8 MB/s ========================================================================== == Memory latency test == == == == Average time is measured for random memory accesses in the buffers == == of different sizes. The larger is the buffer, the more significant == == are relative contributions of TLB, L1/L2 cache misses and SDRAM == == accesses. For extremely large buffer sizes we are expecting to see == == page table walk with several requests to SDRAM for almost every == == memory access (though 64MiB is not nearly large enough to experience == == this effect to its fullest). == == == == Note 1: All the numbers are representing extra time, which needs to == == be added to L1 cache latency. The cycle timings for L1 cache == == latency can be usually found in the processor documentation. == == Note 2: Dual random read means that we are simultaneously performing == == two independent memory accesses at a time. In the case if == == the memory subsystem can't handle multiple outstanding == == requests, dual random read has the same timings as two == == single reads performed one after another. == ========================================================================== block size : single random read / dual random read 1024 : 0.0 ns / 0.0 ns 2048 : 0.0 ns / 0.0 ns 4096 : 0.0 ns / 0.0 ns 8192 : 0.0 ns / 0.0 ns 16384 : 0.0 ns / 0.0 ns 32768 : 0.0 ns / 0.0 ns 65536 : 4.5 ns / 7.2 ns 131072 : 6.8 ns / 9.7 ns 262144 : 9.8 ns / 12.8 ns 524288 : 11.4 ns / 14.7 ns 1048576 : 16.0 ns / 22.6 ns 2097152 : 114.0 ns / 175.3 ns 4194304 : 161.7 ns / 219.9 ns 8388608 : 190.7 ns / 241.5 ns 16777216 : 205.3 ns / 250.5 ns 33554432 : 212.9 ns / 255.5 ns 67108864 : 222.3 ns / 271.1 ns