[DONE]inter procedural optimisation

ChibiOS public support forum for all topics not covered by a specific support forum.

Moderators: RoccoMarco, lbednarz, tfAteba

Post Reply
User avatar
Giovanni
Site Admin
Posts: 14892
Joined: Wed May 27, 2009 8:48 am
Has thanked: 1202 times
Been thanked: 996 times

Re: inter procedural optimisation

Post by Giovanni »

If the code is better then probably it would be a good idea to make this the default mode and add an option to the makefiles. I will give it a try over the weekend.

Thanks for testing.

Giovanni
Top
User avatar
alex31
Posts: 445
Joined: Fri May 25, 2012 10:23 am
Has thanked: 57 times
Been thanked: 88 times

Re: inter procedural optimisation

Post by alex31 »

i had applied szmodz patches over master, and until now, it runs well, with or without link time optimization.

and i can confirm what szmodz has said, without the patches, after flashing, sometime mcu starts, sometime it need powercycling to start,
but with patches applied, it start every time directly after flashing without having to power cycle the mcu.

have not yet run bench to measure speed gain given by link time optimization.

Alexandre
Top
philj
Posts: 1
Joined: Fri Jul 19, 2013 3:18 am

Re: inter procedural optimisation

Post by philj »

I added szmodz patches to 2.6.0 and built the ARMCM4-STM32F407-DISCOVERY-G++
demo with the test report directed to usbserial. Here are the results.

Without -flto

*** ChibiOS/RT test suite
***
*** Kernel: 2.6.0
*** Compiled: Jul 18 2013 - 20:45:15
*** Compiler: GCC 4.7.3 20130312 (release) [ARM/embedded-4_7-branch revisio]
*** Architecture: ARMv7-ME
*** Core Variant: Cortex-M4
*** Port Info: Advanced kernel mode
*** Platform: STM32F4xx High Performance
*** Test Board: STMicroelectronics STM32F4-Discovery

----------------------------------------------------------------------------
--- Test Case 1.1 (Threads, enqueuing test #1)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 1.2 (Threads, enqueuing test #2)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 1.3 (Threads, priority change)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 1.4 (Threads, delays)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 2.1 (Semaphores, enqueuing)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 2.2 (Semaphores, timeout)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 2.3 (Semaphores, atomic signal-wait)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 2.4 (Binary Semaphores, functionality)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.1 (Mutexes, priority enqueuing test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.2 (Mutexes, priority inheritance, simple case)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.3 (Mutexes, priority inheritance, complex case)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.4 (Mutexes, priority return)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.5 (Mutexes, status)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.6 (CondVar, signal test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.7 (CondVar, broadcast test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.8 (CondVar, boost test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 4.1 (Messages, loop)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 5.1 (Mailboxes, queuing and timeouts)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 6.1 (Events, registration and dispatch)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 6.2 (Events, wait and broadcast)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 6.3 (Events, timeouts)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 7.1 (Heap, allocation and fragmentation test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 8.1 (Memory Pools, queue/dequeue)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 9.1 (Dynamic APIs, threads creation from heap)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 9.2 (Dynamic APIs, threads creation from memory pool)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 9.3 (Dynamic APIs, registry and references)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 10.1 (Queues, input queues)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 10.2 (Queues, output queues)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.1 (Benchmark, messages #1)
--- Score : 749345 msgs/S, 1498690 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.2 (Benchmark, messages #2)
--- Score : 608165 msgs/S, 1216330 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.3 (Benchmark, messages #3)
--- Score : 608165 msgs/S, 1216330 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.4 (Benchmark, context switch)
--- Score : 2510008 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.5 (Benchmark, threads, full cycle)
--- Score : 441725 threads/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.6 (Benchmark, threads, create only)
--- Score : 626327 threads/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.7 (Benchmark, mass reschedule, 5 threads)
--- Score : 190526 reschedules/S, 1143156 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.8 (Benchmark, round robin context switching)
--- Score : 1350940 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.9 (Benchmark, I/O Queues throughput)
--- Score : 1842024 bytes/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.10 (Benchmark, virtual timers set/reset)
--- Score : 1804914 timers/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.11 (Benchmark, semaphores wait/signal)
--- Score : 2643372 wait+signal/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.12 (Benchmark, mutexes lock/unlock)
--- Score : 1844556 lock+unlock/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.13 (Benchmark, RAM footprint)
--- System: 404 bytes
--- Thread: 72 bytes
--- Timer : 20 bytes
--- Semaph: 12 bytes
--- EventS: 4 bytes
--- EventL: 16 bytes
--- Mutex : 16 bytes
--- CondV.: 8 bytes
--- Queue : 36 bytes
--- MailB.: 40 bytes
--- Result: SUCCESS
----------------------------------------------------------------------------

Final result: SUCCESS

With -flto

*** ChibiOS/RT test suite
***
*** Kernel: 2.6.0
*** Compiled: Jul 18 2013 - 21:03:43
*** Compiler: GCC 4.7.3 20130312 (release) [ARM/embedded-4_7-branch revisio]
*** Architecture: ARMv7-ME
*** Core Variant: Cortex-M4
*** Port Info: Advanced kernel mode
*** Platform: STM32F4xx High Performance
*** Test Board: STMicroelectronics STM32F4-Discovery

----------------------------------------------------------------------------
--- Test Case 1.1 (Threads, enqueuing test #1)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 1.2 (Threads, enqueuing test #2)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 1.3 (Threads, priority change)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 1.4 (Threads, delays)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 2.1 (Semaphores, enqueuing)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 2.2 (Semaphores, timeout)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 2.3 (Semaphores, atomic signal-wait)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 2.4 (Binary Semaphores, functionality)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.1 (Mutexes, priority enqueuing test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.2 (Mutexes, priority inheritance, simple case)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.3 (Mutexes, priority inheritance, complex case)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.4 (Mutexes, priority return)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.5 (Mutexes, status)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.6 (CondVar, signal test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.7 (CondVar, broadcast test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.8 (CondVar, boost test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 4.1 (Messages, loop)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 5.1 (Mailboxes, queuing and timeouts)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 6.1 (Events, registration and dispatch)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 6.2 (Events, wait and broadcast)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 6.3 (Events, timeouts)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 7.1 (Heap, allocation and fragmentation test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 8.1 (Memory Pools, queue/dequeue)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 9.1 (Dynamic APIs, threads creation from heap)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 9.2 (Dynamic APIs, threads creation from memory pool)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 9.3 (Dynamic APIs, registry and references)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 10.1 (Queues, input queues)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 10.2 (Queues, output queues)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.1 (Benchmark, messages #1)
--- Score : 749398 msgs/S, 1498796 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.2 (Benchmark, messages #2)
--- Score : 608207 msgs/S, 1216414 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.3 (Benchmark, messages #3)
--- Score : 608207 msgs/S, 1216414 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.4 (Benchmark, context switch)
--- Score : 2510176 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.5 (Benchmark, threads, full cycle)
--- Score : 434888 threads/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.6 (Benchmark, threads, create only)
--- Score : 628715 threads/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.7 (Benchmark, mass reschedule, 5 threads)
--- Score : 200555 reschedules/S, 1203330 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.8 (Benchmark, round robin context switching)
--- Score : 1351020 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.9 (Benchmark, I/O Queues throughput)
--- Score : 1842148 bytes/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.10 (Benchmark, virtual timers set/reset)
--- Score : 1805032 timers/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.11 (Benchmark, semaphores wait/signal)
--- Score : 3197440 wait+signal/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.12 (Benchmark, mutexes lock/unlock)
--- Score : 1844684 lock+unlock/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.13 (Benchmark, RAM footprint)
--- System: 404 bytes
--- Thread: 72 bytes
--- Timer : 20 bytes
--- Semaph: 12 bytes
--- EventS: 4 bytes
--- EventL: 16 bytes
--- Mutex : 16 bytes
--- CondV.: 8 bytes
--- Queue : 36 bytes
--- MailB.: 40 bytes
--- Result: SUCCESS
----------------------------------------------------------------------------

Final result: SUCCESS

The code runs faster with -flto!

The compile took about 2 secs longer with -flto on my computer.

Phil
Top
User avatar
Giovanni
Site Admin
Posts: 14892
Joined: Wed May 27, 2009 8:48 am
Has thanked: 1202 times
Been thanked: 996 times

Re: inter procedural optimisation

Post by Giovanni »

Hi,

Interesting results, thanks, I will merge the changes in time for version 2.6.1.

Giovanni
Top
User avatar
alex31
Posts: 445
Joined: Fri May 25, 2012 10:23 am
Has thanked: 57 times
Been thanked: 88 times

Re: [TODO]inter procedural optimisation

Post by alex31 »

2.6.1 is out, but it seems that you did not include flto patches, lack of time ?

we can hope them in 2.6.2 ?

Alexandre
Top
User avatar
Giovanni
Site Admin
Posts: 14892
Joined: Wed May 27, 2009 8:48 am
Has thanked: 1202 times
Been thanked: 996 times

Re: [TODO]inter procedural optimisation

Post by Giovanni »

Hi,

It is marked as TODO, I will test it in 3.0 first and then decide if to backport to 2.6.x.

Giovanni
Top
User avatar
Giovanni
Site Admin
Posts: 14892
Joined: Wed May 27, 2009 8:48 am
Has thanked: 1202 times
Been thanked: 996 times

Re: [TODO]inter procedural optimisation

Post by Giovanni »

Hi,

I committed the LTO changes to the 3.0 branches, apparently it works correctly:

Without LTO:

Code: Select all

*** ChibiOS/RT test suite
***
*** Kernel:       3.0.0dev
*** Compiled:     Sep  9 2013 - 14:12:32
*** Compiler:     GCC 4.7.3 20130312 (release) [ARM/embedded-4_7-branch revision 196615]
*** Architecture: ARMv7-ME
*** Core Variant: Cortex-M4
*** Port Info:    Advanced kernel mode
*** Platform:     STM32F30x Analog & DSP
*** Test Board:   STMicroelectronics STM32F3-Discovery

----------------------------------------------------------------------------
--- Test Case 1.1 (Threads, enqueuing test #1)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 1.2 (Threads, enqueuing test #2)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 1.3 (Threads, priority change)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 1.4 (Threads, delays)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 2.1 (Semaphores, enqueuing)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 2.2 (Semaphores, timeout)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 2.3 (Semaphores, atomic signal-wait)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 2.4 (Binary Semaphores, functionality)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.1 (Mutexes, priority enqueuing test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.2 (Mutexes, priority return)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.3 (Mutexes, status)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.4 (CondVar, signal test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.5 (CondVar, broadcast test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.6 (CondVar, boost test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 4.1 (Messages, loop)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 5.1 (Mailboxes, queuing and timeouts)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 6.1 (Events, registration and dispatch)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 6.2 (Events, wait and broadcast)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 6.3 (Events, timeouts)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 7.1 (Heap, allocation and fragmentation test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 8.1 (Memory Pools, queue/dequeue)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 9.1 (Dynamic APIs, threads creation from heap)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 9.2 (Dynamic APIs, threads creation from memory pool)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 9.3 (Dynamic APIs, registry and references)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 10.1 (Queues, input queues)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 10.2 (Queues, output queues)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.1 (Benchmark, messages #1)
--- Score : 265671 msgs/S, 531342 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.2 (Benchmark, messages #2)
--- Score : 215560 msgs/S, 431120 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.3 (Benchmark, messages #3)
--- Score : 215560 msgs/S, 431120 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.4 (Benchmark, context switch)
--- Score : 935032 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.5 (Benchmark, threads, full cycle)
--- Score : 167435 threads/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.6 (Benchmark, threads, create only)
--- Score : 255309 threads/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.7 (Benchmark, mass reschedule, 5 threads)
--- Score : 65156 reschedules/S, 390936 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.8 (Benchmark, round robin context switching)
--- Score : 464500 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.9 (Benchmark, I/O Queues throughput)
--- Score : 551700 bytes/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.10 (Benchmark, virtual timers set/reset)
--- Score : 457118 timers/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.11 (Benchmark, semaphores wait/signal)
--- Score : 780456 wait+signal/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.12 (Benchmark, mutexes lock/unlock)
--- Score : 582972 lock+unlock/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.13 (Benchmark, RAM footprint)
--- System: 396 bytes
--- Thread: 68 bytes
--- Timer : 20 bytes
--- Semaph: 12 bytes
--- EventS: 4 bytes
--- EventL: 16 bytes
--- Mutex : 16 bytes
--- CondV.: 8 bytes
--- Queue : 36 bytes
--- MailB.: 40 bytes
--- Result: SUCCESS
----------------------------------------------------------------------------

Final result: SUCCESS


With LTO:

Code: Select all

*** ChibiOS/RT test suite
***
*** Kernel:       3.0.0dev
*** Compiled:     Sep  9 2013 - 15:35:24
*** Compiler:     GCC 4.7.3 20130312 (release) [ARM/embedded-4_7-branch revision 196615]
*** Architecture: ARMv7-ME
*** Core Variant: Cortex-M4
*** Port Info:    Advanced kernel mode
*** Platform:     STM32F30x Analog & DSP
*** Test Board:   STMicroelectronics STM32F3-Discovery

----------------------------------------------------------------------------
--- Test Case 1.1 (Threads, enqueuing test #1)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 1.2 (Threads, enqueuing test #2)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 1.3 (Threads, priority change)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 1.4 (Threads, delays)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 2.1 (Semaphores, enqueuing)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 2.2 (Semaphores, timeout)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 2.3 (Semaphores, atomic signal-wait)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 2.4 (Binary Semaphores, functionality)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.1 (Mutexes, priority enqueuing test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.2 (Mutexes, priority return)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.3 (Mutexes, status)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.4 (CondVar, signal test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.5 (CondVar, broadcast test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 3.6 (CondVar, boost test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 4.1 (Messages, loop)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 5.1 (Mailboxes, queuing and timeouts)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 6.1 (Events, registration and dispatch)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 6.2 (Events, wait and broadcast)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 6.3 (Events, timeouts)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 7.1 (Heap, allocation and fragmentation test)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 8.1 (Memory Pools, queue/dequeue)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 9.1 (Dynamic APIs, threads creation from heap)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 9.2 (Dynamic APIs, threads creation from memory pool)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 9.3 (Dynamic APIs, registry and references)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 10.1 (Queues, input queues)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 10.2 (Queues, output queues)
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.1 (Benchmark, messages #1)
--- Score : 285703 msgs/S, 571406 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.2 (Benchmark, messages #2)
--- Score : 228563 msgs/S, 457126 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.3 (Benchmark, messages #3)
--- Score : 228563 msgs/S, 457126 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.4 (Benchmark, context switch)
--- Score : 945784 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.5 (Benchmark, threads, full cycle)
--- Score : 165131 threads/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.6 (Benchmark, threads, create only)
--- Score : 258054 threads/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.7 (Benchmark, mass reschedule, 5 threads)
--- Score : 67795 reschedules/S, 406770 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.8 (Benchmark, round robin context switching)
--- Score : 533320 ctxswc/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.9 (Benchmark, I/O Queues throughput)
--- Score : 623352 bytes/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.10 (Benchmark, virtual timers set/reset)
--- Score : 479976 timers/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.11 (Benchmark, semaphores wait/signal)
--- Score : 941140 wait+signal/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.12 (Benchmark, mutexes lock/unlock)
--- Score : 581796 lock+unlock/S
--- Result: SUCCESS
----------------------------------------------------------------------------
--- Test Case 11.13 (Benchmark, RAM footprint)
--- System: 396 bytes
--- Thread: 68 bytes
--- Timer : 20 bytes
--- Semaph: 12 bytes
--- EventS: 4 bytes
--- EventL: 16 bytes
--- Mutex : 16 bytes
--- CondV.: 8 bytes
--- Queue : 36 bytes
--- MailB.: 40 bytes
--- Result: SUCCESS
----------------------------------------------------------------------------

Final result: SUCCESS


The feature will be official in 3.0.

Giovanni
Top
User avatar
Giovanni
Site Admin
Posts: 14892
Joined: Wed May 27, 2009 8:48 am
Has thanked: 1202 times
Been thanked: 996 times

Re: [TODO]inter procedural optimisation

Post by Giovanni »

BTW, the 3.0 branch is already usable: http://svn.code.sf.net/p/chibios/svn/br ... nel_3_dev/

Just not all platforms have been ported yet. So far: STM32L1, STM32F0, STM32F3, STM32F4.

Giovanni
Top
DrunkenDonkey
Posts: 124
Joined: Sun Aug 28, 2011 5:16 pm

Re: [DONE]inter procedural optimisation

Post by DrunkenDonkey »

Very nice performance gains, I'm eager to get some project to do so I can try my teeth on 3.0 :D
Top
User avatar
Giovanni
Site Admin
Posts: 14892
Joined: Wed May 27, 2009 8:48 am
Has thanked: 1202 times
Been thanked: 996 times

Re: [DONE]inter procedural optimisation

Post by Giovanni »

Yes, more than 20% on some tests and consistent gains in all tests is impressive, also code size is positively affected.

Giovanni
Top
Post Reply

Return to “General Support”