From 6ef46f71c743507a0e2ae0eef14dce0539b0ff52 Mon Sep 17 00:00:00 2001
From: nagachika <nagachika@ruby-lang.org>
Date: Sat, 20 Mar 2021 14:23:45 +0900
Subject: merge revision(s) 511b55bcefc81c036294dc9a544d14bd342acd3b: [Backport
 #17215]

	Enable arm64 optimizations that exist for power/x86 (#3393)

	* Enable unaligned accesses on arm64

	64-bit Arm platforms support unaligned accesses.

	Running the string benchmarks this change improves performance
	by an average of 1.04x, min .96x, max 1.21x, median 1.01x

	* arm64 enable gc optimizations

	Similar to x86 and powerpc optimizations.

	|       |compare-ruby|built-ruby|
	|:------|-----------:|---------:|
	|hash1  |       0.225|     0.237|
	|       |           -|     1.05x|
	|hash2  |       0.110|     0.110|
	|       |       1.00x|         -|

	* vm_exec.c: improve performance for arm64

	|                               |compare-ruby|built-ruby|
	|:------------------------------|-----------:|---------:|
	|vm_array                       |     26.501M|   27.959M|
	|                               |           -|     1.06x|
	|vm_attr_ivar                   |     21.606M|   31.429M|
	|                               |           -|     1.45x|
	|vm_attr_ivar_set               |     21.178M|   26.113M|
	|                               |           -|     1.23x|
	|vm_backtrace                   |       6.621|     6.668|
	|                               |           -|     1.01x|
	|vm_bigarray                    |     26.205M|   29.958M|
	|                               |           -|     1.14x|
	|vm_bighash                     |    504.155k|  479.306k|
	|                               |       1.05x|         -|
	|vm_block                       |     16.692M|   21.315M|
	|                               |           -|     1.28x|
	|block_handler_type_iseq        |       5.083|     7.004|
	|                               |           -|     1.38x|
	---
	 gc.c                           | 13 +++++++++++++
	 gc.h                           |  2 ++
	 include/ruby/internal/config.h |  2 ++
	 regint.h                       |  2 +-
	 siphash.c                      |  2 +-
	 st.c                           |  2 +-
	 vm_exec.c                      |  8 ++++++++
	 7 files changed, 28 insertions(+), 3 deletions(-)
---
 gc.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'gc.c')

diff --git a/gc.c b/gc.c
index 73faf46b12..b06fdc5b27 100644
--- a/gc.c
+++ b/gc.c
@@ -1153,6 +1153,19 @@ tick(void)
     return val;
 }
 
+#elif defined(__aarch64__) &&  defined(__GNUC__)
+typedef unsigned long tick_t;
+#define PRItick "lu"
+
+static __inline__ tick_t
+tick(void)
+{
+    unsigned long val;
+    __asm__ __volatile__ ("mrs %0, cntvct_el0", : "=r" (val));
+    return val;
+}
+
+
 #elif defined(_WIN32) && defined(_MSC_VER)
 #include <intrin.h>
 typedef unsigned __int64 tick_t;
-- 
cgit v1.2.3