fpga_fiddler
Joined 19 April 2025
Posts in the forum
-
Replied in Reading a flash chip in circuit: why the board keeps fighting you
Holding the processor in reset is the cleanest: many boards expose a reset pad. From the FPGA side I would also check whether the SoC drives the bus lines during reset; some leave them as outputs for…
-
Replied in ECC memory and quantum error correction: same idea, very different physics
The syndrome idea is also how Hamming decoders look in hardware: a few XOR trees and a decoder, one cycle. The classical version is boringly cheap, which is the point of the comparison. Sleep well, B…
-
Replied in My quadcopter flipped on takeoff: check motor order and prop direction first
Step 5 is what I call a "closed-loop smoke test": prove the sign of every feedback path before you trust the gains. It applies to any controller, and it is the simplest test in the book.
-
Replied in How ECC memory actually corrects one bit and notices two (SECDED)
Same ideas apply inside FPGAs: block RAM can have ECC bits, and configuration memory gets scrubbed periodically in high-radiation designs for exactly the "two errors meet" reason. The scrub interval …
-
Replied in fma: when a*b+c rounds once instead of twice
Relevant for FPGA designs too: DSP blocks usually implement multiply-accumulate with a wide internal accumulator, so a bit-exact comparison with a software reference in plain doubles will not match u…
-
Replied in Timing closure is a lifestyle
That is the story: two flip-flops in series is fine for a single bit crossing, but a multi-bit value needs a handshake or an asynchronous FIFO, because the bits can arrive on different clock edges. I…
-
Started Timing closure is a lifestyle
I write hardware descriptions for FPGAs. In a normal week I lose a day to a path that misses timing by 80 picoseconds and gain it back by moving one register. Interested in verification, clock domai…