Added ARM-Neon support for SIMD.SkipWhitespace*

Change-Id: Iaf210d029758723a7eeb7f28fc10cab7467889a9
Signed-off-by: Jun He <jun.he@arm.com>

doc/faq.md

@@ -256,7 +256,7 @@ Alternatively, if we don't want to explicitly refer to the root value of `addres
 
 3. What is SIMD? How it is applied in RapidJSON?
 
-   [SIMD](http://en.wikipedia.org/wiki/SIMD) instructions can perform parallel computation in modern CPUs. RapidJSON support Intel's SSE2/SSE4.2 to accelerate whitespace skipping. This improves performance of parsing indent formatted JSON. Define `RAPIDJSON_SSE2` or `RAPIDJSON_SSE42` macro to enable this feature. However, running the executable on a machine without such instruction set support will make it crash.
+   [SIMD](http://en.wikipedia.org/wiki/SIMD) instructions can perform parallel computation in modern CPUs. RapidJSON support Intel's SSE2/SSE4.2 and ARM's Neon to accelerate whitespace/tabspace/carriage-return/line-feed skipping. This improves performance of parsing indent formatted JSON. Define `RAPIDJSON_SSE2`, `RAPIDJSON_SSE42` or `RAPIDJSON_NEON` macro to enable this feature. However, running the executable on a machine without such instruction set support will make it crash.
 
 4. Does it consume a lot of memory?
 

doc/faq.zh-cn.md

@@ -257,7 +257,7 @@
 
 3. 什是是 SIMD？它如何用于 RapidJSON？
 
-   [SIMD](http://en.wikipedia.org/wiki/SIMD) 指令可以在现代 CPU 中执行并行运算。RapidJSON 支持了 Intel 的 SSE2/SSE4.2 去加速跳过空白字符。在解析含缩进的 JSON 时，这能提升性能。只要定义名为 `RAPIDJSON_SSE2` 或 `RAPIDJSON_SSE42` 的宏，就能启动这个功能。然而，若在不支持这些指令集的机器上执行这些可执行文件，会导致崩溃。
+   [SIMD](http://en.wikipedia.org/wiki/SIMD) 指令可以在现代 CPU 中执行并行运算。RapidJSON 支持使用 Intel 的 SSE2/SSE4.2 和 ARM 的 Neon 来加速对空白符、制表符、回车符和换行符的过滤处理。在解析含缩进的 JSON 时，这能提升性能。只要定义名为 `RAPIDJSON_SSE2` ，`RAPIDJSON_SSE42` 或 `RAPIDJSON_NEON` 的宏，就能启动这个功能。然而，若在不支持这些指令集的机器上执行这些可执行文件，会导致崩溃。
 
 4. 它会消耗许多内存么？
 

doc/internals.md

@@ -183,17 +183,20 @@ void SkipWhitespace(InputStream& s) {
 
 However, this requires 4 comparisons and a few branching for each character. This was found to be a hot spot.
 
-To accelerate this process, SIMD was applied to compare 16 characters with 4 white spaces for each iteration. Currently RapidJSON only supports SSE2 and SSE4.2 instructions for this. And it is only activated for UTF-8 memory streams, including string stream or *in situ* parsing. 
+To accelerate this process, SIMD was applied to compare 16 characters with 4 white spaces for each iteration. Currently RapidJSON supports SSE2, SSE4.2 and ARM Neon instructions for this. And it is only activated for UTF-8 memory streams, including string stream or *in situ* parsing.
 
-To enable this optimization, need to define `RAPIDJSON_SSE2` or `RAPIDJSON_SSE42` before including `rapidjson.h`. Some compilers can detect the setting, as in `perftest.h`:
+To enable this optimization, need to define `RAPIDJSON_SSE2`, `RAPIDJSON_SSE42` or `RAPIDJSON_NEON` before including `rapidjson.h`. Some compilers can detect the setting, as in `perftest.h`:
 
 ~~~cpp
 // __SSE2__ and __SSE4_2__ are recognized by gcc, clang, and the Intel compiler.
 // We use -march=native with gmake to enable -msse2 and -msse4.2, if supported.
+// Likewise, __ARM_NEON is used to detect Neon.
 #if defined(__SSE4_2__)
 #  define RAPIDJSON_SSE42
 #elif defined(__SSE2__)
 #  define RAPIDJSON_SSE2
+#elif defined(__ARM_NEON)
+#  define RAPIDJSON_NEON
 #endif
 ~~~
 

doc/internals.zh-cn.md

@@ -183,17 +183,20 @@ void SkipWhitespace(InputStream& s) {
 
 但是，这需要对每个字符进行4次比较以及一些分支。这被发现是一个热点。
 
-为了加速这一处理，RapidJSON 使用 SIMD 来在一次迭代中比较16个字符和4个空格。目前 RapidJSON 只支持 SSE2 和 SSE4.2 指令。同时它也只会对 UTF-8 内存流启用，包括字符串流或 *原位* 解析。
+为了加速这一处理，RapidJSON 使用 SIMD 来在一次迭代中比较16个字符和4个空格。目前 RapidJSON 支持 SSE2 ， SSE4.2 和 ARM Neon 指令。同时它也只会对 UTF-8 内存流启用，包括字符串流或 *原位* 解析。
 
-你可以通过在包含 `rapidjson.h` 之前定义 `RAPIDJSON_SSE2` 或 `RAPIDJSON_SSE42` 来启用这个优化。一些编译器可以检测这个设置，如 `perftest.h`：
+你可以通过在包含 `rapidjson.h` 之前定义 `RAPIDJSON_SSE2` ， `RAPIDJSON_SSE42` 或 `RAPIDJSON_NEON` 来启用这个优化。一些编译器可以检测这个设置，如 `perftest.h`：
 
 ~~~cpp
 // __SSE2__ 和 __SSE4_2__ 可被 gcc、clang 和 Intel 编译器识别：
 // 如果支持的话，我们在 gmake 中使用了 -march=native 来启用 -msse2 和 -msse4.2
+// 同样的， __ARM_NEON 被用于识别Neon
 #if defined(__SSE4_2__)
 #  define RAPIDJSON_SSE42
 #elif defined(__SSE2__)
 #  define RAPIDJSON_SSE2
+#elif defined(__ARM_NEON)
+#  define RAPIDJSON_NEON
 #endif
 ~~~
 

include/rapidjson/rapidjson.h

@@ -325,17 +325,17 @@
 #endif
 
 ///////////////////////////////////////////////////////////////////////////////
-// RAPIDJSON_SSE2/RAPIDJSON_SSE42/RAPIDJSON_SIMD
+// RAPIDJSON_SSE2/RAPIDJSON_SSE42/RAPIDJSON_NEON/RAPIDJSON_SIMD
 
 /*! \def RAPIDJSON_SIMD
     \ingroup RAPIDJSON_CONFIG
-    \brief Enable SSE2/SSE4.2 optimization.
+    \brief Enable SSE2/SSE4.2/Neon optimization.
 
     RapidJSON supports optimized implementations for some parsing operations
-    based on the SSE2 or SSE4.2 SIMD extensions on modern Intel-compatible
-    processors.
+    based on the SSE2, SSE4.2 or NEon SIMD extensions on modern Intel
+    or ARM compatible processors.
 
-    To enable these optimizations, two different symbols can be defined;
+    To enable these optimizations, three different symbols can be defined;
     \code
     // Enable SSE2 optimization.
     #define RAPIDJSON_SSE2
@@ -344,13 +344,17 @@
     #define RAPIDJSON_SSE42
     \endcode
 
-    \c RAPIDJSON_SSE42 takes precedence, if both are defined.
+    // Enable ARM Neon optimization.
+    #define RAPIDJSON_NEON
+    \endcode
+
+    \c RAPIDJSON_SSE42 takes precedence over SSE2, if both are defined.
 
     If any of these symbols is defined, RapidJSON defines the macro
     \c RAPIDJSON_SIMD to indicate the availability of the optimized code.
 */
 #if defined(RAPIDJSON_SSE2) || defined(RAPIDJSON_SSE42) \
-    || defined(RAPIDJSON_DOXYGEN_RUNNING)
+    || defined(RAPIDJSON_NEON) || defined(RAPIDJSON_DOXYGEN_RUNNING)
 #define RAPIDJSON_SIMD
 #endif
 

include/rapidjson/writer.h

@@ -32,6 +32,8 @@
 #include <nmmintrin.h>
 #elif defined(RAPIDJSON_SSE2)
 #include <emmintrin.h>
+#elif defined(RAPIDJSON_NEON)
+#include <arm_neon.h>
 #endif
 
 #ifdef _MSC_VER
@@ -619,7 +621,75 @@ inline bool Writer<StringBuffer>::ScanWriteUnescapedString(StringStream& is, siz
     is.src_ = p;
     return RAPIDJSON_LIKELY(is.Tell() < length);
 }
-#endif // defined(RAPIDJSON_SSE2) || defined(RAPIDJSON_SSE42)
+#elif defined(RAPIDJSON_NEON)
+template<>
+inline bool Writer<StringBuffer>::ScanWriteUnescapedString(StringStream& is, size_t length) {
+    if (length < 16)
+        return RAPIDJSON_LIKELY(is.Tell() < length);
+
+    if (!RAPIDJSON_LIKELY(is.Tell() < length))
+        return false;
+
+    const char* p = is.src_;
+    const char* end = is.head_ + length;
+    const char* nextAligned = reinterpret_cast<const char*>((reinterpret_cast<size_t>(p) + 15) & static_cast<size_t>(~15));
+    const char* endAligned = reinterpret_cast<const char*>(reinterpret_cast<size_t>(end) & static_cast<size_t>(~15));
+    if (nextAligned > end)
+        return true;
+
+    while (p != nextAligned)
+        if (*p < 0x20 || *p == '\"' || *p == '\\') {
+            is.src_ = p;
+            return RAPIDJSON_LIKELY(is.Tell() < length);
+        }
+        else
+            os_->PutUnsafe(*p++);
+
+    // The rest of string using SIMD
+    const uint8x16_t s0 = vmovq_n_u8('"');
+    const uint8x16_t s1 = vmovq_n_u8('\\');
+    const uint8x16_t s2 = vmovq_n_u8('\b');
+    const uint8x16_t s3 = vmovq_n_u8(32);
+
+    for (; p != endAligned; p += 16) {
+        const uint8x16_t s = vld1q_u8(reinterpret_cast<const uint8_t *>(p));
+        uint8x16_t x = vceqq_u8(s, s0);
+        x = vorrq_u8(x, vceqq_u8(s, s1));
+        x = vorrq_u8(x, vceqq_u8(s, s2));
+        x = vorrq_u8(x, vcltq_u8(s, s3));
+
+        x = vrev64q_u8(x);                     // Rev in 64
+        uint64_t low = vgetq_lane_u64(reinterpret_cast<uint64x2_t>(x), 0);   // extract
+        uint64_t high = vgetq_lane_u64(reinterpret_cast<uint64x2_t>(x), 1);  // extract
+
+        SizeType len = 0;
+        bool escaped = false;
+        if (low == 0) {
+            if (high != 0) {
+                unsigned lz = (unsigned)__builtin_clzll(high);
+                len = 8 + (lz >> 3);
+                escaped = true;
+            }
+        } else {
+            unsigned lz = (unsigned)__builtin_clzll(low);
+            len = lz >> 3;
+            escaped = true;
+        }
+        if (RAPIDJSON_UNLIKELY(escaped)) {   // some of characters is escaped
+            char* q = reinterpret_cast<char*>(os_->PushUnsafe(len));
+            for (size_t i = 0; i < len; i++)
+                q[i] = p[i];
+
+            p += len;
+            break;
+        }
+        vst1q_u8(reinterpret_cast<uint8_t *>(os_->PushUnsafe(16)), s);
+    }
+
+    is.src_ = p;
+    return RAPIDJSON_LIKELY(is.Tell() < length);
+}
+#endif // RAPIDJSON_NEON
 
 RAPIDJSON_NAMESPACE_END
 

test/perftest/perftest.h

@@ -24,10 +24,13 @@
 
 // __SSE2__ and __SSE4_2__ are recognized by gcc, clang, and the Intel compiler.
 // We use -march=native with gmake to enable -msse2 and -msse4.2, if supported.
+// Likewise, __ARM_NEON is used to detect Neon.
 #if defined(__SSE4_2__)
 #  define RAPIDJSON_SSE42
 #elif defined(__SSE2__)
 #  define RAPIDJSON_SSE2
+#elif defined(__ARM_NEON)
+#  define RAPIDJSON_NEON
 #endif
 
 #define RAPIDJSON_HAS_STDSTRING 1

test/perftest/rapidjsontest.cpp

@@ -28,6 +28,8 @@
 #define SIMD_SUFFIX(name) name##_SSE2
 #elif defined(RAPIDJSON_SSE42)
 #define SIMD_SUFFIX(name) name##_SSE42
+#elif defined(RAPIDJSON_NEON)
+#define SIMD_SUFFIX(name) name##_NEON
 #else
 #define SIMD_SUFFIX(name) name
 #endif

test/unittest/simdtest.cpp

@@ -21,6 +21,8 @@
 #  define RAPIDJSON_SSE42
 #elif defined(__SSE2__)
 #  define RAPIDJSON_SSE2
+#elif defined(__ARM_NEON)
+#  define RAPIDJSON_NEON
 #endif
 
 #define RAPIDJSON_NAMESPACE rapidjson_simd
@@ -41,6 +43,8 @@ using namespace rapidjson_simd;
 #define SIMD_SUFFIX(name) name##_SSE2
 #elif defined(RAPIDJSON_SSE42)
 #define SIMD_SUFFIX(name) name##_SSE42
+#elif defined(RAPIDJSON_NEON)
+#define SIMD_SUFFIX(name) name##_NEON
 #else
 #define SIMD_SUFFIX(name) name
 #endif