Use clmul for CRC32.

The crc32 instructions are non-standard and not supported by upstream
clang.

According to perftest, this only slows things down by a few cycles

before:
I00003 crc32_perftest.c:33] CRC32 computed in 11343 cycles.
I00004 crc32_perftest.c:33] CRC32 computed in 11317 cycles.
I00005 crc32_perftest.c:33] CRC32 computed in 11314 cycles.
I00006 crc32_perftest.c:33] CRC32 computed in 11314 cycles.
I00007 crc32_perftest.c:33] CRC32 computed in 11314 cycles.
I00008 crc32_perftest.c:33] CRC32 computed in 11314 cycles.
I00009 crc32_perftest.c:33] CRC32 computed in 11314 cycles.
I00010 crc32_perftest.c:33] CRC32 computed in 11314 cycles.
I00011 crc32_perftest.c:33] CRC32 computed in 11314 cycles.
I00012 crc32_perftest.c:33] CRC32 computed in 11314 cycles.

after:
I00003 crc32_perftest.c:33] CRC32 computed in 11358 cycles.
I00004 crc32_perftest.c:33] CRC32 computed in 11319 cycles.
I00005 crc32_perftest.c:33] CRC32 computed in 11318 cycles.
I00006 crc32_perftest.c:33] CRC32 computed in 11318 cycles.
I00007 crc32_perftest.c:33] CRC32 computed in 11318 cycles.
I00008 crc32_perftest.c:33] CRC32 computed in 11318 cycles.
I00009 crc32_perftest.c:33] CRC32 computed in 11318 cycles.
I00010 crc32_perftest.c:33] CRC32 computed in 11318 cycles.
I00011 crc32_perftest.c:33] CRC32 computed in 11318 cycles.

Signed-off-by: Kor Nielsen <[email protected]>

Author: korran

sw/device/lib/base/crc32.c

@@ -10,26 +10,40 @@
 #include "sw/device/lib/base/memory.h"
 
 #ifdef OT_PLATFORM_RV32
+enum {
+  /**
+   * CRC32 polynomial.
+   */
+  kCrc32Poly = 0xedb88320,
+  kCrc32Mu = 0xf7011641,
+};
+
+
 OT_WARN_UNUSED_RESULT
-static uint32_t crc32_internal_add8(uint32_t ctx, uint8_t byte) {
-  ctx ^= byte;
+static uint32_t crc32_i(uint32_t x) {
+  uint32_t result;
   asm(".option push;"
-      ".option arch, +zbr0p93;"
-      "crc32.b %0, %1;"
+      ".option arch, +zbc;"
+      "clmul %[result], %[x], %[mu];"
+      "clmulr %[result], %[result], %[poly];"
       ".option pop;"
-      : "+r"(ctx));
-  return ctx;
+      : [result] "=&r"(result)
+      : [x] "r"(x),
+        [mu] "r"(kCrc32Mu),
+        [poly] "r"(kCrc32Poly));
+    return result;
+}
+
+OT_WARN_UNUSED_RESULT
+static uint32_t crc32_internal_add8(uint32_t ctx, uint8_t byte) {
+  ctx ^= byte;
+  return crc32_i(ctx << 24) ^ (ctx >> 8);
 }
 
 OT_WARN_UNUSED_RESULT
 static uint32_t crc32_internal_add32(uint32_t ctx, uint32_t word) {
   ctx ^= word;
-  asm(".option push;"
-      ".option arch, +zbr0p93;"
-      "crc32.w %0, %1;"
-      ".option pop;"
-      : "+r"(ctx));
-  return ctx;
+  return crc32_i(ctx);
 }
 #else
 enum {