yuzu-emu/mbedtls
2
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Limit compiler hint to compilers that are known to benefit from it

Browse source 
Signed-off-by: Dave Rodgman <dave.rodgman@arm.com>
This commit is contained in:
Dave Rodgman 2024-01-23 09:36:34 +00:00
parent 075f8797ac
commit 00b530e395
1 changed files with 33 additions and 17 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

50
library/common.h
View file

@ -199,30 +199,40 @@ static inline void mbedtls_xor(unsigned char *r,
uint8x16_t x = veorq_u8(v1, v2);
vst1q_u8(r + i, x);
}
#if defined(__IAR_SYSTEMS_ICC__)
/* This if statement helps some compilers (e.g., IAR) optimise out the byte-by-byte tail case
* where n is a constant multiple of 16.
* It makes no difference for others (e.g. recent gcc and clang) if n is a compile-time
* constant, and very little difference if n is not a compile-time constant. */
if (n % 16 != 0)
* For other compilers (e.g. recent gcc and clang) it makes no difference if n is a compile-time
* constant, and is a very small perf regression if n is not a compile-time constant. */
if (n % 16 == 0) {
return;
}
#endif
#elif defined(MBEDTLS_ARCH_IS_X64) || defined(MBEDTLS_ARCH_IS_ARM64)
/* This codepath probably only makes sense on architectures with 64-bit registers */
for (; (i + 8) <= n; i += 8) {
uint64_t x = mbedtls_get_unaligned_uint64(a + i) ^ mbedtls_get_unaligned_uint64(b + i);
mbedtls_put_unaligned_uint64(r + i, x);
}
if (n % 8 != 0)
#if defined(__IAR_SYSTEMS_ICC__)
if (n % 8 == 0) {
return;
}
#endif
#else
for (; (i + 4) <= n; i += 4) {
uint32_t x = mbedtls_get_unaligned_uint32(a + i) ^ mbedtls_get_unaligned_uint32(b + i);
mbedtls_put_unaligned_uint32(r + i, x);
}
if (n % 4 != 0)
#if defined(__IAR_SYSTEMS_ICC__)
if (n % 4 == 0) {
return;
}
#endif
#endif
{
for (; i < n; i++) {
r[i] = a[i] ^ b[i];
}
#endif
for (; i < n; i++) {
r[i] = a[i] ^ b[i];
}
}
@ -268,23 +278,29 @@ static inline void mbedtls_xor_no_simd(unsigned char *r,
uint64_t x = mbedtls_get_unaligned_uint64(a + i) ^ mbedtls_get_unaligned_uint64(b + i);
mbedtls_put_unaligned_uint64(r + i, x);
}
#if defined(__IAR_SYSTEMS_ICC__)
/* This if statement helps some compilers (e.g., IAR) optimise out the byte-by-byte tail case
* where n is a constant multiple of 16.
* It makes no difference for others (e.g. recent gcc and clang) if n is a compile-time
* constant, and very little difference if n is not a compile-time constant. */
if (n % 8 != 0)
* For other compilers (e.g. recent gcc and clang) it makes no difference if n is a compile-time
* constant, and is a very small perf regression if n is not a compile-time constant. */
if (n % 8 == 0) {
return;
}
#endif
#else
for (; (i + 4) <= n; i += 4) {
uint32_t x = mbedtls_get_unaligned_uint32(a + i) ^ mbedtls_get_unaligned_uint32(b + i);
mbedtls_put_unaligned_uint32(r + i, x);
}
if (n % 4 != 0)
#if defined(__IAR_SYSTEMS_ICC__)
if (n % 4 == 0) {
return;
}
#endif
#endif
{
for (; i < n; i++) {
r[i] = a[i] ^ b[i];
}
#endif
for (; i < n; i++) {
r[i] = a[i] ^ b[i];
}
}