olin wrote:Just an update, I was able to run the SDRAM on 150MHz for more than 3 hours with 0 errors, then gave up. I also connected a heat sink and a fan (Sunon MC25100V2-000U-A99, Vapo-Bearing, 16.0dB). I found out the fan works when powered by 3.3V (spec. is 5V) with lower RPM (although it is not advertised feature) so it is more silent. To power it by 3.3V I used P4 connector pin 1 and 2, but I plan to update the IO board and make an alternative fan connector for 3.3V. On touch the heat-sink is slightly warm (under load for ~ 40 minutes), my thermocouple displayed ~32 deg.C which should be OK.
I have also discovered that a fan (here no heatsink on CPU) is helping to stabilize the clock and enables higher SDRAM frequency usability. I has able to run at 150 MHz for 12 hours with 2 errors. Normally the counter reaches 10 errors after few minutes without the fan. I have added 10x20 passive heatsink to the memory chip but it does not bring any enhancement. The key is in the cooling of the SoC/FPGA I would say.
I have also observed that by design (code not inspected yet) the mister binary is running 100% on a single core all the time. Killing the process is bringing back idle cycles cooldown to the chip. I need to investigate why the binary is in free run mode, could be due to a while ( true ) loop effect.