Age | Commit message (Collapse) | Author |
|
|
|
|
|
The e31's init.c calls puts intsead of printf, which oddly enough is a
lot bigger: since we wrap printf, puts pulls in a lot of newlib. This
adds a wrapped puts so it's very small.
|
|
There's a handful of things that went wrong here:
* The read-only data sections were mapped to flash, which is very slow.
I just put them in the data segment, so they end up in the scratchpad.
This is about a 10x hit, so it's really important.
* The toolchain was an old version, which didn't have a fast memcpy
implementation on 32-bit systems. This is about a 2x hit.
* Some compiler flags were incorrect, including
* -Os instead of -O3
* Missing -mexplicit-relocs
* Missing -DNOENUM
* Missing -falign-functions=4
I haven't checked how much those hurt
With this, I get
$ make software BOARD=freedom-e300-hifive1 PROGRAM=dhrystone LINK_TARGET=dhrystone
$ make upload BOARD=freedom-e300-hifive1 PROGRAM=dhrystone LINK_TARGET=dhrystone
Execution starts, 10000000 runs through Dhrystone
Execution ends
Final values of the variables used in the benchmark:
Int_Glob: 5
should be: 5
Bool_Glob: 1
should be: 1
Ch_1_Glob: A
should be: A
Ch_2_Glob: B
should be: B
Arr_1_Glob[8]: 7
should be: 7
Arr_2_Glob[8][7]: 10000010
should be: Number_Of_Runs + 10
Ptr_Glob->
Ptr_Comp: -2147470264
should be: (implementation-dependent)
Discr: 0
should be: 0
Enum_Comp: 2
should be: 2
Int_Comp: 17
should be: 17
Str_Comp: DHRYSTONE PROGRAM, SOME STRING
should be: DHRYSTONE PROGRAM, SOME STRING
Next_Ptr_Glob->
Ptr_Comp: -2147470264
should be: (implementation-dependent), same as above
Discr: 0
should be: 0
Enum_Comp: 1
should be: 1
Int_Comp: 18
should be: 18
Str_Comp: DHRYSTONE PROGRAM, SOME STRING
should be: DHRYSTONE PROGRAM, SOME STRING
Int_1_Loc: 5
should be: 5
Int_2_Loc: 13
should be: 13
Int_3_Loc: 7
should be: 7
Enum_Loc: 1
should be: 1
Str_1_Loc: DHRYSTONE PROGRAM, 1'ST STRING
should be: DHRYSTONE PROGRAM, 1'ST STRING
Str_2_Loc: DHRYSTONE PROGRAM, 2'ND STRING
should be: DHRYSTONE PROGRAM, 2'ND STRING
Microseconds for one run through Dhrystone: 1.3
Dhrystones per Second: 714285.6
which is 1.55 DMIPS/MHz at 262 MHz. It's still a bit slower than our
current stuff, but I don't remember what was actually in the HiFive1 so
I'm not sure what we should be getting. I verified the clock is
accurate with a stopwatch. I haven't bothered to go look through the
binary, but I think we're about 10 cycles off so it should be managable.
|
|
SPIFlash controller is. This allows it to work for newer versions of the E300 Arty Dev Kit as well.
|
|
|
|
|
|
|
|
registers
|
|
|
|
|
|
This just prints "hello world" on two cores. It contains an example of
how to initialize a multi-core system using IPIs, and a simple spin
lock.
|
|
printf doesn't fit in the scratchpad, but since there's really no reason
to call it on constant strings it can be replaced with puts. With this
change, the "hello" example fits in the scratchpad.
|
|
Everything still defaults to the flash, but users can optionally select
the scratchpad. Note that you have to be pretty careful about your
scratchpad programs, most of them won't fit. For example, printf is too
big to fit in the scratchpad.
|
|
* examples ported to ilg build plugin
* project cleanup
* CoreplexIP-E31 ilg projects
* E51FPGA ilg projects
* Tested Debug
* debug launch files
* E31 Debug Launch Files
* removed typo project
* E51 launch files. Forgotten E31 File
* Missing coreplexip files
* examples ported to ilg build plugin
* project cleanup
* CoreplexIP-E31 ilg projects
* E51FPGA ilg projects
* Tested Debug
* debug launch files
* E31 Debug Launch Files
* removed typo project
* E51 launch files. Forgotten E31 File
* Missing coreplexip files
* starting fresh
* HiFive1 demo_gpio and libwrap
* hifive1 hello
* debug launchers for hello and demo_gpio
* hifive1 led_fade
* led_fade: Since E300 Arty Dev Kit doesn't have a PRCI, the led_fade demo doesn't really work on it.
* update include paths to ease generating stand-alone zips
* Adding E51 Examples
* E51 demo launch files
* E31 Demos
* E31 demo launch files
|
|
Since our loader doesn't support multiple sections anyway, there's
really no reason to have all these sections floating around. They're
causing trouble due to misalignment so it's easiest to just group them
together so we can properly enforce alignment.
|
|
|
|
I'm hoping this will make everything more likely to align. We can't use
the other mechanism because our loader is lazy and assumes all the
sections are contiguous.
|
|
|
|
Without this I get a message that looks like
Program has exited with code 0x/0000008
which doesn't make any sense. This prints
Progam has exited with code:0x80000008
|
|
Without these alignment directives the sections are only required to be
aligned on word-sized boundries, but we sometimes require double-word
alignment. This allows the linker to sanely emit these sections.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
first, then using it as the PLL source. This is also safer as it is less risk of using PLL out of its range.
|
|
exclude it if there is not PRCI_BASE_ADDR on the system.
|
|
or closest match)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Benchmarking
|
|
Provide get_timer_value() and get_timer_freq() and use them. On Arty,
they use mcycle and the known-fixed core frequency, whereas on HiFive1
they use mtime and the known-fixed mtime frequency.
|
|
- Warm up I$ first.
- Correct for integer division truncation error.
- Wait for an RTC clock edge before starting the timing loop,
which removes an error proportional to the number of loop
iterations, allowing us to run for far less time.
|
|
|
|
ensure Flash is loaded correctly.
|
|
This improves the instruction stream's spatial locality.
|
|
The symbol may be overridden and end up out of range of JAL.
|
|
|
|
Remove unncessary srst delay when connecting with OpenOCD to HiFive1
|
|
|
|
|