Performace benchmarks: PARTNER-Jet vs 3 other Japanese ICE venders
To demonstrate the superior performance of the PARTNER-Jet, KMC conducted tests using an T-Engine MC9328MX1 (Model TTM101-001 with ARM920T core), one of the most popular development platform for ARM920 series supplied from Yokogawa Digital Computer Corporation. T-Engine is an effective cross-platform measure of system performance because it is widely supported by several ICEs. All tests except ETM trace functionality was done with this board.
KMC also conducted tests using KMC's KZ-ARM9EXPCI-01 Model 4 (EPXA4F672C3), another most popular development platform for ARM, which supports ETM trace functionality. ETM trace functionality test was done with this board.
T-Engine MC9328MX1 (ARM920T core)
KZ-ARM9EXPCI-01 Model 4 (EPXA4F672C3)
KMC ran the benchmark tests using commonly used ICE operations, including file download and upload, step execution, FLASH ROM writing, debug information loading, ETM trace speed and capacity. We measured the time to execute each action or operation and compared the performance of all actions.
Testing Environment:
Processor:
|
Pentium 4 2GHz
|
Memory:
|
512MB
|
Operating system:
|
Window 2000
|
Target boards:
-
T-Engine MC9328MX1 (ARM920T core)
Model number: TTM101-001
Yokogawa Digital Computer Corporation
* All tests except ETM trace functionality was done with this board.
-
KZ-ARM9EXPCI-01 Model 4 (EPXA4F672C3)
Kyoto Microcomputer Co., Ltd.
* ETM trace functionality test was done with this board.
Tested ICEs:
KMC tested several small ICEs for ARM processors available from several major companies which are ranging from 298,000 yen to 598,000 yen (approx. $3,000 to $6,000).
- PARTNER-Jet (USB 2.0 and Ethernet)
Kyoto Microcomputer Co., Ltd.
- JTAG ICE "A" (USB 2.0)
Major brand A
- JTAG ICE "B" (USB 1.1)
Major brand B
- JTAG ICE "C" (USB 1.1)
Major brand C
ICE settings:
Settings for each ICE is shown below. JTAG clock frequency is set manually so that each ICE can debug the target board at the highest speed. I/O system on the target board is initialized after activating debugger.
ICE model
|
PARTNER-Jet
|
JTAG ICE "A"
|
JTAG ICE "B"
|
JTAG ICE "C"
|
Supported connection types
|
USB 2.0 and Ethernet
|
USB 2.0
|
USB 1.1
|
USB 1.1
|
JTAG clock frequency
|
43 MHz
|
24.5 MHz
|
16.66 MHz
|
12.5 MHz
|
- Note
- PARTNER-Jet has a functionality to measure comsumption time of a command and the measured time is as accurate as within 1/100 second.
To demonstrate the superior performance of the PARTNER-Jet, KMC conducted tests by downloading a 4MB binary file into target memory and measured time for the operation. For upload, we transferred 4MB of data on the target memory to host machine. We measured a comsumption time with a stopwatch from a command entry to the next command prompt in the command window. We also ensured that the time was accurate enough to match the one entering command from GUI window. ICEs with USB 2.0 interface are also measured via USB 1.1 hub so that the communication speed is normalized in USB 1.1 capability.
Benchmark result #1: Downoad and Upload speed
ICE model
|
PARTNER-Jet
|
JTAG ICE "A"
|
JTAG ICE "B"
|
JTAG ICE "C"
|
Connection type
|
USB 2.0
|
USB 2.0
|
USB 1.1
|
USB 1.1
|
Download time
|
1.67 sec
(2452.7 KB/sec)
|
5.8 sec
(706.2 KB/sec)
|
17.8 sec
(230.1 KB/sec)
|
30.1 sec
(136.1 KB/sec)
|
Upload time
|
1.98 sec
(2068.7 KB/sec)
|
9.2 sec
(445.2 KB/sec)
|
23.8 sec
(172.1 KB/sec)
|
35.8 sec
(114.4 KB/sec)
|
Benchmark result #2: USB 1.1 equivalent
ICE model
|
PARTNER-Jet
|
JTAG ICE "A"
|
Connection type
|
USB 2.0 via USB 1.1 hub
|
USB 2.0 via USB 1.1 hub
|
Download time
|
4.26 sec
(961.5 KB/sec)
|
9.1 sec
(450.1 KB/sec)
|
Upload time
|
5.77 sec
(709.9 KB/sec)
|
14.2 sec
(288.5 KB/sec)
|
*The best (fastest) value in the test is shown in red.
To demonstrate the superior performance of the PARTNER-Jet, KMC conducted tests by downloading (writing) a 1MB binary file into target FLASH memory and measured time for the operation. The test was done after clearing (zero-ing) the target FLASH memory. Furthermore, if the ICE allows to allocate working area in user RAM space, time using that working area is also measured. The time measurement was done is the same way with downloading a binary file.
Benchmark result #3: FLASH memory writing speed
ICE model
|
PARTNER-Jet
|
JTAG ICE "A"
|
JTAG ICE "B"
|
JTAG ICE "C"
|
Connection type
|
USB 2.0
|
USB 2.0
|
USB 1.1
|
USB 1.1
|
Writing time
(using working RAM)
|
8.0 sec
(128 KB/sec)
|
9.5 sec
(107.8 KB/sec)
|
8.0 sec
(128 KB/sec)
|
18.1 sec
(56.6 KB/sec)
|
Writing time
|
22.1 sec
(46.3 KB/sec)
|
45.2 sec
(22.7 KB/sec)
|
132.4 sec
(7.7 KB/sec)
|
---
(not applicable)
|
*The best (fastest) value in the test is shown in red.
To demonstrate the superior performance of the PARTNER-Jet, KMC conducted tests by stepping through small NOP loop and measured time required for 1,000 steps in machine language level. The program code is as follows:
Address
|
Code
|
Mnemonic
|
08100004
|
E1A00000
|
NOP
|
08100008
|
E1A00000
|
NOP
|
0810000C
|
E1A00000
|
NOP
|
08100010
|
E1A00000
|
NOP
|
08100014
|
E1A00000
|
NOP
|
08100018
|
EAFFFFF8
|
B 08100000
|
The initial program counter value was set to 0x08100000. The time measurement was done is the same way with downloading a binary file.
Benchmark result #4: Step execution speed
ICE model
|
PARTNER-Jet
|
JTAG ICE "A"
|
JTAG ICE "B"
|
JTAG ICE "C"
|
Connection type
|
USB 2.0
|
USB 2.0
|
USB 1.1
|
USB 1.1
|
Execution time
|
2.94 sec
(340.1 steps/sec)
|
9.1 sec
(109.9 steps/sec)
|
203.4 sec
(4.9 steps/sec)
|
55.9 sec
(17.9 steps/sec)
|
Benchmark result #5: USB 1.1 equivalent
ICE model
|
PARTNER-Jet
|
JTAG ICE "A"
|
Connection type
|
USB 2.0 via USB 1.1 hub
|
USB 2.0 via USB 1.1 hub
|
Execution time
|
12.1 sec
(82.6 steps/sec)
|
49.9 sec
(20.0 steps/sec)
|
*The best (fastest) value in the test is shown in red.
To demonstrate the superior performance of the PARTNER-Jet, KMC conducted tests by downloading a debug information of a Linux kernel (vm.out with debug information, approx. 27MB in size) to debugger and measured time for the operation. If any kind of format conversion is required, format conversion time is added to the measured time.
Benchmark result #6: Debug information loading speed
ICE model
|
PARTNER-Jet
|
JTAG ICE "A"
|
JTAG ICE "B"
|
JTAG ICE "C"
|
Connection type
|
USB 2.0
|
USB 2.0
|
USB 1.1
|
USB 1.1
|
| Execution time |
2.86 sec
(0.98 seconds using stabs compression)
|
14.2 sec
(3.8 seconds for loading, 10.4 seconds for format conversion)
|
1.5 sec
|
3.7 sec
|
*The best (fastest) value in the test is shown in red.
*stabs is a standard data compression method and the PARTNER supprts it.
To demonstrate the superior performance of the PARTNER-Jet, KMC conducted tests by measuring the maximum core clock frequency using KZ-ARM9EXPCI-01 Model 4 target board. We measured the maximum core clock frequency making sure the testing ICE can trace the target board by using dhry.out sample file.
Benchmark result #7: ETM trace speed
ICE model
|
PARTNER-Jet
|
JTAG ICE "A"
|
JTAG ICE "B"
|
JTAG ICE "C"
|
Connection type
|
USB 2.0
|
USB 2.0
|
USB 1.1
|
USB 1.1
|
Maximum core clock frequency
|
247MHz
|
200MHz
|
Not applicable
(No ETM)
|
200MHz
|
*The best (fastest) value in the test is shown in red.
To demonstrate the superior performance of the PARTNER-Jet, KMC conducted tests by measuring the maximum ETM trace capacity (depth). We measured it by counting number of trace packet using dhry.out sample file.
Benchmark result #8: Step execution speed
| ICE model |
PARTNER-Jet
Model 30
|
PARTNER-Jet
Model 20
|
JTAG ICE "A"
|
JTAG ICE "B"
|
JTAG ICE "C"
|
Maximum trace capacity (depth) at 200MHz
|
1,600,000 packets
|
400,000 packets
|
180,000 packets
|
Not applicable
(No ETM)
|
260,000 packets
|
*The best (fastest) value in the test is shown in red.
KMC, the KMC logo, PARTNER, PARTNER-Jet, PARTNER-JetM, exeGCC, JTAG-Ether, and Eclipse for PARTNER Cross DevKit are trademarks of Kyoto Microcomputer Co., Ltd. Product and company names mentioned herein may be trademarks of their respective companies. Product specifications are subject to change without notice. This material is provided for informational purposes only; KMC assumes no liability related to its use.
