tcg: define CF_PARALLEL and use it for TB hashing along with CF_COUNT_MASK

This will enable us to decouple code translation from the value
of parallel_cpus at any given time. It will also help us minimize
TB flushes when generating code via EXCP_ATOMIC.

Note that the declaration of parallel_cpus is brought to exec-all.h
to be able to define there the "curr_cflags" inline.

Signed-off-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This commit is contained in:
Emilio G. Cota 2017-07-11 14:29:37 -04:00 committed by Richard Henderson
parent e89b28a635
commit 4e2ca83e71
10 changed files with 65 additions and 39 deletions

View file

@ -48,8 +48,8 @@
* xxhash32, customized for input variables that are not guaranteed to be
* contiguous in memory.
*/
static inline
uint32_t tb_hash_func6(uint64_t a0, uint64_t b0, uint32_t e, uint32_t f)
static inline uint32_t
tb_hash_func7(uint64_t a0, uint64_t b0, uint32_t e, uint32_t f, uint32_t g)
{
uint32_t v1 = TB_HASH_XX_SEED + PRIME32_1 + PRIME32_2;
uint32_t v2 = TB_HASH_XX_SEED + PRIME32_2;
@ -78,7 +78,7 @@ uint32_t tb_hash_func6(uint64_t a0, uint64_t b0, uint32_t e, uint32_t f)
v4 *= PRIME32_1;
h32 = rol32(v1, 1) + rol32(v2, 7) + rol32(v3, 12) + rol32(v4, 18);
h32 += 24;
h32 += 28;
h32 += e * PRIME32_3;
h32 = rol32(h32, 17) * PRIME32_4;
@ -86,6 +86,9 @@ uint32_t tb_hash_func6(uint64_t a0, uint64_t b0, uint32_t e, uint32_t f)
h32 += f * PRIME32_3;
h32 = rol32(h32, 17) * PRIME32_4;
h32 += g * PRIME32_3;
h32 = rol32(h32, 17) * PRIME32_4;
h32 ^= h32 >> 15;
h32 *= PRIME32_2;
h32 ^= h32 >> 13;