How can CLZ equivalent be achieved on Cortex-M0 where this instruction is missing?

Looking for alternates for this instruction.

If you are interested in a better performance that beats the pants out of the brute force solution proposed above, you might use the following implementation:

static __INLINE uint32_t __CLZ(uint32_t x) {
    extern uint8_t const log2Lkup[256];

    if (x >= 0x00010000U) {
        if (x >= 0x01000000U) {
            return 8U - log2Lkup[x >> 24];
        }
        else {
            return 16U - log2Lkup[x >> 16];
        }
    }
    else {
        if (x >= 0x00000100U) {
            return 24U - log2Lkup[x >> 8];
        }
        else {
            return 32U - log2Lkup[x];
        }
    }
}

The function would need the log2 (binary logarithm) lookup table defined in a .c file:

uint8_t const log2Lkup[256] = {
  0U, 1U, 2U, 2U, 3U, 3U, 3U, 3U, 4U, 4U, 4U, 4U, 4U, 4U, 4U, 4U,
  5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U,
  6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U,
  6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U,
  7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U,
  7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U,
  7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U,
  7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U,
  8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U,
  8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U,
  8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U,
  8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U,
  8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U,
  8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U,
  8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U,
  8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U
};

The __CLZ() implementation proposed above does not have loops and is deterministic, meaning that it takes the same number of instructions for all arguments x. It is better than most other algorithms you can find online, including the methods from the "Hacker's Delight" and Anderson's bit twiddling hacks (interested folks can google for these).

--Miro

static __INLINE uint32_t __CLZ(uint32_t x) { extern uint8_t const log2Lkup[256]; if (x >= 0x00010000U) { if (x >= 0x01000000U) { return 8U - log2Lkup[x >> 24]; } else { return 16U - log2Lkup[x >> 16]; } } else { if (x >= 0x00000100U) { return 24U - log2Lkup[x >> 8]; } else { return 32U - log2Lkup[x]; } } }

uint8_t const log2Lkup[256] = { 0U, 1U, 2U, 2U, 3U, 3U, 3U, 3U, 4U, 4U, 4U, 4U, 4U, 4U, 4U, 4U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 5U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 6U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 7U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U, 8U };