AM64x MCU+ SDK  09.01.00
Datasheet

Table of Contents

Introduction

This datasheet provides the performance numbers of various device drivers in MCU PLUS SDK for AM64X

Generic Setup details

SOC Details Values
Core R5F
Core Operating Speed 800 MHz
Cache Status Enabled
Optimization Details Values
Build Profile Release
R5F Compiler flags -mcpu=cortex-r5 -mfloat-abi=hard -mfpu=vfpv3-d16 -Wall -Werror -g -mthumb -Wno-gnu-variable-sized-type-not-at-end -Wno-unused-function
R5F Linker flags -Wl,–diag_suppress=10063 -Wl,–ram_model -Wl,–reread_libs
Code Placement MSRAM
Data Placement MSRAM

Performance Numbers

SBL OSPI performance

AM64X-EVM

  • Software/Application used : sbl_ospi and ipc_notify_echo
  • Size of sbl_ospi appimage : 256 KB
  • Size of ipc_notify_echo appimage : 77 KB
  • Cores present in the appimage : m4f0-0, r5f0-0, r5f0-1, r5f1-0, r5f1-1
  • Boot Media Clock : 166.667 MHz (Octal DDR mode)
Boot time breakdown Time (ms)
ROM : init + SBL load from flash 12.00
SBL : SYSFW Load 12.159
SBL : System Init 0.553
SBL : Drivers_open 0.280
SBL : Board_driversOpen 22.23
SBL : Sciclient Get Version 9.9
SBL : CPU Load 38.25
SBL : Total time taken 95.372
  • The time taken for Board_driversOpen (around 20 ms) is mostly for the PHY tuning of OSPI. If this needs to be further reduced, one can pre-train the PHY, note down delay values and set it directly instead of the tuning procedure.
  • Most of the time taken for the CPU load is in loading the M4F. Other CPUs take ~1.5ms each. This needs more investigation. Possible reason is the M4F IRAM and DRAM initialization time.
  • Here the CPU load or section copy takes place from the OSPI memory to the respective memory directly, this would be slower that mem to mem copy.
  • The time taken for Sciclient Get Version can be avoided if the version check is disabled

SBL SD performance

  • Software/Application used : sbl_sd and adc_singleshot
  • Size of sbl_sd appimage : 300 KB
  • Size of adc_singleshot appimage : 34 KB
  • Cores present in the appimage : r5f0-0
  • SD card read speed : 12.5 MBps mode
Boot time breakdown Time (ms)
ROM : init + SBL load from flash 12.00
SBL : SYSFW Load 12.161
SBL : System Init 0.131
SBL : Drivers_open 13.958
SBL : Board_driversOpen 0.00
SBL : Sciclient Get Version 9.892
SBL : File read from SD Card 6.48
SBL : CPU Load 57.09
-------------------------------------— -----------—
SBL : Total time taken 111.712
  • The MMCSD driver and SD card initialization is done as part of Drivers_open, so Board_driversOpen happens instantaneously.
  • Most of the time taken for the CPU load is in loading the M4F. Other CPUs take ~1.5ms each. This needs more investigation. Possible reason is the M4F IRAM and DRAM initialization time.
  • The CPU load is faster in this case because SD bootloader is at its core a memory bootloader. Appimage file from SD card is read into the memory (this takes 15 ms in this case). The CPU load now is mostly memcpy in the OCRAM. This would be quite fast. The only caveat here is that the buffer size to receive appimage is allocated in OCRAM, so it's limited. This is not the case in OSPI.
  • The time taken for Sciclient Get Version can be avoided if the version check is disabled

XIP Benchmark

  • Software/Application used : xip_benchmark
  • FIR operation
Caching status Cycles taken
Code/Data fully cached 26750
Code/Data not cached 53540
Code/Data not cached 1 of 10 iterations 29552
  • MEMCPY operation
Caching status Cycles taken
Code/Data fully cached 1565
Code/Data not cached 3473
Code/Data not cached 1 of 10 iterations 1759

MCAN performance

  • Internal loopback mode of operation
  • Memory Mode : TX Buffer Mode, RX FIFO Mode
  • MCAN CLK : 80MHz
  • CPU : R5F
Frame Type Arbitration BitRate(Mbps) Data BitRate(Mbps) Arb Phase bits Data Phase bits Throughput (Msg/Sec)
CAN FD STANDARD FORMAT 1 5 27 538 6666
CAN FD EXTENDED FORMAT 1 5 46 538 5780

MCSPI performance

MCSPI driver performance in different modes

  • measurement is provided for Master mode in Loopback configuration with TX and RX.
  • Transfer time captured with driver API in different operation mode.
  • Throughput comparison is added for transfer of 400 Bytes with different word width and corresponding number of words.
  • Time
  • CPU : R5F
  • Transfer Length : 400 Bytes
  • SPI Clock speed : 50MHz
Number of Words Word Width (Bits) Polled mode Throughput / Transfer time Interrupt mode (Mbps) Throughput / Transfer time Dma mode (Mbps) Throughput / Transfer time
400 08 15.63 Mbps / 204.78 us 23.75 Mbps / 134.76 us 0.91 Mbps / 3500.59 us
200 16 32.49 Mbps / 98.48 us 31.46 Mbps / 101.71 us 0.95 Mbps / 3356.64 us
100 32 38.82 Mbps / 82.43 us 37.58 Mbps / 85.16 us 0.97 Mbps / 3284.78 us
  • Theoretically for 400 Bytes at 50MHz time required for clocks is 64us.
  • Additionally hardware adds 160ns + 1bit time delay between each word transfer as measured in the scope

CPSW Performance

TCP Test

  • Software/Application used : enet_lwip_cpsw
  • iperf test type : TCP iperf
  • iperf command used : iperf -c 192.168.0.158 -i 10 -t 100 -r

TCP Performance(am64x/243x emvs):

TCP direction B/W (Mb/s) CPU load(%)
TCP RX 93.4 45.37
TCP TX 93.3 57.42
TCP Biderectional TX = 87 + RX = 87 93.94

TCP Performance(am243x-lp):

TCP direction B/W (Mb/s) CPU load(%)
TCP RX 93.35 31.01
TCP TX 93.30 34.92
TCP Biderectional TX = 93.20 + RX = 93.2 63.28

UDP Test

  • Software/Application used : enet_lwip_cpsw
  • iperf test type : UDP iperf
  • iperf command used : iperf -c 192.168.0.158 -u -b 60M -l 256 -i 10 -t 100 -r

UDP TX Performance(am64x/243x emvs):

  • For Packet Size: 1500 B
Tx Side BW/Packet Size CPU load(%) Packet loss(%) Latency
25 Mbps 100 0 -
50 Mbps 100 0.03 -
100 Mbps 100 0.07 -

UDP TX Performance(am243x-lp):

  • For Packet Size: 1500 B
Tx Side BW/Packet Size CPU load(%) Packet loss(%) Latency
25 Mbps 100 0 -
50 Mbps 100 0 -
100 Mbps 100 0 -

UDP RX Performance(am64x/243x emvs):

  • For Packet Size: 256 B
Tx Side BW/Packet Size CPU load(%) Packet loss(%) Latency
25 Mbps 52.26 0.08 -
50 Mbps 60.34 41 -
100 Mbps - - -
  • For Packet Size: 512 B
Tx Side BW/Packet Size CPU load(%) Packet loss(%) Latency
25 Mbps 30.83 0 -
50 Mbps 56.74 0.09 -
100 Mbps 65.61 41 -
  • For Packet Size: 1500 B
Tx Side BW/Packet Size CPU load(%) Packet loss(%) Latency
25 Mbps 16.84 0 -
50 Mbps 28.93 0 -
100 Mbps 53.16 0.06 -
Max(158 Mbps) 80.83 1.1 -

UDP RX Performance(am243x-lp):

  • For Packet Size: 256 B
Tx Side BW/Packet Size CPU load(%) Packet loss(%) Latency
25 Mbps 42 0 -
50 Mbps 49 41 -
100 Mbps - - -
  • For Packet Size: 512 B
Tx Side BW/Packet Size CPU load(%) Packet loss(%) Latency
25 Mbps 24 0 -
50 Mbps 45 0.05 -
100 Mbps 61 41 -
  • For Packet Size: 1500 B
Tx Side BW/Packet Size CPU load(%) Packet loss(%) Latency
25 Mbps 12 0 -
50 Mbps 21 0 -
100 Mbps 38 0.03 -

IPC performance

IPC NOTIFY

  • 10000 messages are sent and average one way message latency is measured
Local Core Remote Core Average Message Latency (us)
r5f0-0 m4f0-0 1.49
r5f0-0 r5f0-1 0.78
r5f0-0 r5f1-0 0.83
r5f0-0 r5f1-1 0.91
r5f0-0 a530-0 0.00
r5f0-0 a530-1 0.00

IPC RPMSG

  • 10000 messages are sent and average one way message latency is measured
Local Core Remote Core Message Size Average Message Latency (us)
r5f0-0 r5f0-1 4 0.571
r5f0-0 r5f1-0 4 0.573
r5f0-0 r5f1-1 4 0.573
r5f0-0 m4f0-0 4 1.138
r5f0-0 r5f0-1 32 0.775
r5f0-0 r5f0-1 64 1.034
r5f0-0 r5f0-1 112 1.413
r5f0-0 m4f0-0 32 1.666
r5f0-0 m4f0-0 64 2.268
r5f0-0 m4f0-0 112 3.179

MATHLIB

MATHLIB BENCHMARK

  • Calculated for the 500 samples taken between 0 and 2 * Pi
  • Trignometric function timings compared between the optimized Mathlib mcusdk implementation and the compiler mathlib version
  • The max error for each operation between the optimized Mathlib mcusdk functions and the compiler mathlib version is printed
    Function Err Max Cycles Mathlib (mcusdk) avg cycles Mathlib (mcusdk) max cycles mathlib (clang) avg cycles mathlib (clang)
    sin 0.0000007150 52 52.226002 758 277.294006
    cos 0.0000002870 64 64.103996 689 278.225983
    sincos sin 0.0000001790 79 79.223999 467 274.265991
    sincos cos 0.0000001900
    asin 0.0000003430 73 73.098000 1160 431.116028
    acos 0.0000004770 74 74.096001 1010 385.179993
    atan 0.0000005360 85 85.089996 900 373.325989
    atan2 0.0000007150 119 106.730003 1150 479.428009

SA2UL

PKA RSA SIGN VERIFY

  • Software/Application used : test_sa2ul_pka
  • Supported keys : 4K and 2K
  • CPU with operating speed : R5F with 800MHZ
  • OS used : nortos
    ECDSA Sign/sec Verify/sec Sign and verify/sec
    2048 632 8849 589
    4096 97 2801 94

SHA

  • Software/Application used : test_sa2ul_sha
  • Code Placement : OCMC
  • Data Placement : OCMC
  • Input Data sizes : 512B, 1KB, 2KB, 4KB, 8KB, 16KB and 32KB
  • CPU with operating speed : R5F with 800MHZ
    SHA Size Performance (Mbps)
    512 32.00 KB 2041.659690
    512 16.00 KB 1814.239493
    512 8.00 KB 1422.878389
    512 4.00 KB 987.025114
    512 2.00 KB 602.546775
    512 1024.00 B 333.652378
    512 512.00 B 174.669510
    256 32.00 KB 1581.002209
    256 16.00 KB 1403.678616
    256 8.00 KB 1143.161154
    256 4.00 KB 827.030949
    256 2.00 KB 534.573188
    256 1024.00 B 312.552461
    256 512.00 B 171.398682

PKA ECDSA

  • Software/Application used : test_sa2ul_pka
  • Supported Curves : p-256 and p-384
  • CPU with operating speed : R5F with 800MHZ
  • OS used : nortos
    ECDSA Sign/sec Verify/sec Sign and verify/sec
    256 1136 693 430
    384 586 349 218

AES

  • Software/Application used : test_sa2ul_aes
  • Code Placement : OCMC
  • Data Placement : OCMC
  • Input Data sizes : 512B, 1KB, 2KB, 4KB, 8KB, 16KB and 32KB
  • CPU with operating speed : R5F with 800MHZ
    Key Length operation Size Performance (Mbps)
    128 Encryption 32.00 KB 1495.924845
    128 Decryption 32.00 KB 1844.947655
    128 Encryption 16.00 KB 1392.216897
    128 Decryption 16.00 KB 1665.728356
    128 Encryption 8.00 KB 1178.228235
    128 Decryption 8.00 KB 1339.109113
    128 Encryption 4.00 KB 918.707507
    128 Decryption 4.00 KB 1023.600156
    128 Encryption 2.00 KB 651.192369
    128 Decryption 2.00 KB 701.895684
    128 Encryption 1024.00 B 409.933071
    128 Decryption 1024.00 B 423.140496
    128 Encryption 512.00 B 232.727273
    128 Decryption 512.00 B 239.427152
    256 Encryption 32.00 KB 1333.277387
    256 Decryption 32.00 KB 1521.251732
    256 Encryption 16.00 KB 1219.558037
    256 Decryption 16.00 KB 1377.222638
    256 Encryption 8.00 KB 1046.608376
    256 Decryption 8.00 KB 1153.066925
    256 Encryption 4.00 KB 823.316583
    256 Decryption 4.00 KB 896.893390
    256 Encryption 2.00 KB 611.086764
    256 Decryption 2.00 KB 637.788915
    256 Encryption 1024.00 B 388.269447
    256 Decryption 1024.00 B 403.820322
    256 Encryption 512.00 B 228.014752
    256 Decryption 512.00 B 230.923185

RSA ENCRYPT DECRYPT

  • Software/Application used : test_sa2ul_rsa
  • Code Placement : OCMC
  • Supported keys : 4K and 2K
  • CPU with operating speed : R5F with 800MHZ
  • Software/Application used : test_sa2ul_rsa
    Key Length operation Size Performance(Mbps)
    2048 Encryption 256.00 B 0.554920
    2048 Decryption 256.00 B 1.295509
    4096 Encryption 512.00 B 0.597262
    4096 Decryption 512.00 B 0.400676

USB

NET Driver ( RNDIS )

  • Measures TCP only TX bandwidth at every 1 sec interval using standard lwip-perf application.
  • Software/Applicaiton used : rndis_nortos
  • Input media : USB 2.0
  • Linux Host application used : iperf
  • CPU with operating speed : R5F with 800MHz
  • lwip-webserver ip address : 192.168.7.1
  • RNDIS Host ip address : 192.168.7.2
  • TCP window size : 85.0 KByte
ID Interval Transfer Bandwidth
0 0.0- 1.0 sec 4.25 MBytes 35.7 Mbits/sec
1 1.0- 2.0 sec 4.12 MBytes 34.6 Mbits/sec
2 2.0- 3.0 sec 4.12 MBytes 34.6 Mbits/sec
3 3.0- 4.0 sec 4.12 MBytes 34.6 Mbits/sec
4 4.0- 5.0 sec 4.12 MBytes 34.6 Mbits/sec
5 5.0- 6.0 sec 4.12 MBytes 34.6 Mbits/sec
6 6.0- 7.0 sec 4.12 MBytes 34.6 Mbits/sec
7 7.0- 8.0 sec 4.12 MBytes 34.6 Mbits/sec
8 8.0- 9.0 sec 4.25 MBytes 35.7 Mbits/sec
9 9.0-10.0 sec 4.12 MBytes 34.6 Mbits/sec
10 0.0-10.0 sec 41.5 MBytes 34.8 Mbits/sec