lib: crc32_sw: 4 bit at a time implementation
Calculate crc32 4 bits at a time. The return value of the calculation is
identical to the previous 1 bit at a time implementation.
Results in a speed up of a factor 3 at the cost of using 64 bytes of
flash for a crc table.
Calculating crc32 of 128kB of flash on a 120MHz Kinetis MKE16F512
Cortex-M4 takes 99ms using the 1 bit at a time implementation, and 30ms
using the 4 bits at a time implementation.
The crc32 routine is used by subsys/canbus/canopen/canopen_program.c to
calculate crc of flash images.
Signed-off-by: Klaus H. Sorensen <khso@vestas.com>
diff --git a/lib/os/crc32_sw.c b/lib/os/crc32_sw.c
index a72f28c..5d74cd8 100644
--- a/lib/os/crc32_sw.c
+++ b/lib/os/crc32_sw.c
@@ -13,13 +13,21 @@
uint32_t crc32_ieee_update(uint32_t crc, const uint8_t *data, size_t len)
{
- crc = ~crc;
- for (size_t i = 0; i < len; i++) {
- crc = crc ^ data[i];
+ /* crc table generated from polynomial 0xedb88320 */
+ static const uint32_t table[16] = {
+ 0x00000000, 0x1db71064, 0x3b6e20c8, 0x26d930ac,
+ 0x76dc4190, 0x6b6b51f4, 0x4db26158, 0x5005713c,
+ 0xedb88320, 0xf00f9344, 0xd6d6a3e8, 0xcb61b38c,
+ 0x9b64c2b0, 0x86d3d2d4, 0xa00ae278, 0xbdbdf21c,
+ };
- for (uint8_t j = 0; j < 8; j++) {
- crc = (crc >> 1) ^ (0xEDB88320 & -(crc & 1));
- }
+ crc = ~crc;
+
+ for (size_t i = 0; i < len; i++) {
+ uint8_t byte = data[i];
+
+ crc = (crc >> 4) ^ table[(crc ^ byte) & 0x0f];
+ crc = (crc >> 4) ^ table[(crc ^ (byte >> 4)) & 0x0f];
}
return (~crc);
