From 89e7997622038f82115f34dbb4ea382e02bed163 Mon Sep 17 00:00:00 2001 From: Alan Wu Date: Tue, 30 Jul 2019 21:36:05 -0400 Subject: Combine call info and cache to speed up method invocation To perform a regular method call, the VM needs two structs, `rb_call_info` and `rb_call_cache`. At the moment, we allocate these two structures in separate buffers. In the worst case, the CPU needs to read 4 cache lines to complete a method call. Putting the two structures together reduces the maximum number of cache line reads to 2. Combining the structures also saves 8 bytes per call site as the current layout uses separate two pointers for the call info and the call cache. This saves about 2 MiB on Discourse. This change improves the Optcarrot benchmark at least 3%. For more details, see attached bugs.ruby-lang.org ticket. Complications: - A new instruction attribute `comptime_sp_inc` is introduced to calculate SP increase at compile time without using call caches. At compile time, a `TS_CALLDATA` operand points to a call info struct, but at runtime, the same operand points to a call data struct. Instruction that explicitly define `sp_inc` also need to define `comptime_sp_inc`. - MJIT code for copying call cache becomes slightly more complicated. - This changes the bytecode format, which might break existing tools. [Misc #16258] --- mjit.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'mjit.c') diff --git a/mjit.c b/mjit.c index 3ae9410179..f1e3934326 100644 --- a/mjit.c +++ b/mjit.c @@ -46,7 +46,16 @@ mjit_copy_job_handler(void *data) const struct rb_iseq_constant_body *body = job->iseq->body; if (job->cc_entries) { - memcpy(job->cc_entries, body->cc_entries, sizeof(struct rb_call_cache) * (body->ci_size + body->ci_kw_size)); + unsigned int i; + struct rb_call_cache *sink = job->cc_entries; + const struct rb_call_data *calls = body->call_data; + const struct rb_kwarg_call_data *kw_calls = (struct rb_kwarg_call_data *)&body->call_data[body->ci_size]; + for (i = 0; i < body->ci_size; i++) { + *sink++ = calls[i].cc; + } + for (i = 0; i < body->ci_kw_size; i++) { + *sink++ = kw_calls[i].cc; + } } if (job->is_entries) { memcpy(job->is_entries, body->is_entries, sizeof(union iseq_inline_storage_entry) * body->is_size); -- cgit v1.2.3