From WikiChip
Difference between revisions of "marvell/armada/618"
(→Block Diagram) |
|||
Line 159: | Line 159: | ||
|vfpv1=No | |vfpv1=No | ||
|vfpv2=No | |vfpv2=No | ||
− | |vfpv3= | + | |vfpv3=No |
− | |vfpv3-d16= | + | |vfpv3-d16=Yes |
|vfpv3-f16=No | |vfpv3-f16=No | ||
|vfpv4=No | |vfpv4=No |
Revision as of 14:48, 28 May 2017
Template:mpu ARMADA 618 was a 32-bit ARM microprocessor introduced by Marvell in 2009. This processor, which is based on Marvell's Sheeva PJ4 microarchitecture, operated at 1 GHz and supported up to 2 GiB of DDR3-1066 memory. The ARMADA 618 also incorporated a fairly powerful GPU.
Contents
Cache
- Main article: Sheeva PJ4 § Cache
Cache Organization
Cache is a hardware component containing a relatively small and extremely fast memory designed to speed up the performance of a CPU by preparing ahead of time the data it needs to read from a relatively slower medium such as main memory. The organization and amount of cache can have a large impact on the performance, power consumption, die size, and consequently cost of the IC. Cache is specified by its size, number of sets, associativity, block size, sub-block size, and fetch and write-back policies. Note: All units are in kibibytes and mebibytes. |
|||||||||||||||||||||||||
|
Memory controller
Integrated Memory Controller
|
||||||||||||||
|
Static Memory Controller
- 4 chip selects, up to 256 MB each
- Asynch/Sync operation up to 78 MHz
- A/D and AA/D Mode, x8 & x16 NOR Flash interface
- Support for VLIO or companion chips
NAND Flash Controller
- ONFI compliant controller supporting SLC and MLC NAND, x8 & x16, small block and large block
- 2 Chip Selects with up to 64GB of address space
- Support for 2 KB and 4 KB page sizes
- 2-bit detect/1-bit correct ECC & 16-bit correct BCH
MMC, SD and SDIO Controller
- 4x MMC/SD/SDIO/CE-ATA Controllers
- Supports MMC/eMMC v4.2, 4.3 and 4.4
- SDIO v 2.0, SDcard v2.1 and v3.0 (UHS-I)
- CE-ATA 1/4/8-Bit, SPI mode and boot suppor
Expansions
Expansion Options
|
||||||||||||||||||
|
Graphics
This chip has a custom integrated GPU capable of 45 million triangle strips per second, 250 Mpixel/s fill rate and offer full support for OpenGL ES 2.0 and 1.1 and Open VG 1.1.
- Integrated video accelerator supporting 30 fps 1080p decode and encode
- 1080p decode support for H.264 high profile, VC-1/WMV, MPEG-4, MPEG-2, H.263, On-2.
- 1080p encode support for h.264 high profile, MPEG-4, MPEG-2, H.263 and On-2
Hardware Accelerators
Marvell Wireless Trusted Module v3
- Hashing units: MD5, SHA-1, HMAC-SHA-1; SHA-224/SHA256 and HMAC, SHA-512 and HMAC, MD5 and HMAC-MD5
- Symmetric crypto: AES (128 to 256 & ECB, CBC, CTR/XTS modes), DES/3DES (ECB & CBC), RC4
- Asymmetric crypto: ECC (Prime field ECC, FIPS std curve EC-224/256, EC-DSA) & RSA (RSA key gen, PKCS#1 v1.5/v2.1 Digital Signatures, x.509 Digital Certificate), & DiffieHellman Key exchange. True HW RNG, FIPS 140-2 certification
Features
[Edit/Modify Supported Features]
Supported ARM Extensions & Processor Features
|
||||||
|
Block Diagram
Documents
Facts about "ARMADA 618 - Marvell"
has ecc memory support | false + |
l1$ size | 64 KiB (65,536 B, 0.0625 MiB) + |
l1d$ size | 32 KiB (32,768 B, 0.0313 MiB) + |
l1i$ size | 32 KiB (32,768 B, 0.0313 MiB) + |
l2$ size | 0.25 MiB (256 KiB, 262,144 B, 2.441406e-4 GiB) + |
max memory bandwidth | 7.942 GiB/s (8,132.608 MiB/s, 8.528 GB/s, 8,527.658 MB/s, 0.00776 TiB/s, 0.00853 TB/s) + |
max memory channels | 1 + |
supported memory type | DDR3-1066 + and DDR2-800 + |