[Beignet] [PATCH v2] improve the build performance of vector type built-in function.

[xionghu.luo at intel.com]

From: LuoXionghu <xionghu.luo at intel.com>

expand the gentypen with loop to reduce the redundant inline for more
than 4 components type.

v2: add the  greater than 4 componets conditon to avoid performace
degration.

Signed-off-by: Luo Xionghu <xionghu.luo at intel.com>
---
 backend/src/gen_builtin_vector.py | 42 +++++++++++++++++++++++++++++++++------
 1 file changed, 36 insertions(+), 6 deletions(-)

diff --git a/backend/src/gen_builtin_vector.py b/backend/src/gen_builtin_vector.py
index b100bbf..15dbaf4 100755
--- a/backend/src/gen_builtin_vector.py
+++ b/backend/src/gen_builtin_vector.py
@@ -283,9 +283,39 @@ class builtinProto():
                 formatStr += '{0} {1}param{2}'.format(ptype[0], pointerStr, n)
 
         formatStr += ')'
-        formatStr = self.append(formatStr, '{{return ({0}{1})('.format(vtype[0], vtype[1]))
-        self.indent = len(formatStr)
-        for j in range(0, vtype[1]):
+        if self.functionName != 'select' and ptypeSeqs[0] == ptypeSeqs[self.paramCount-1] and ptype[1] > 4:
+            formatStr += '\n{ \n  union{'
+            formatStr = self.append(formatStr, '    {0} va[{1}];'.format(vtype[0], vtype[1]))
+            formatStr = self.append(formatStr, '    {0}{1} vv{2};'.format(vtype[0], vtype[1], vtype[1]))
+            formatStr += '\n  }uret;'
+            formatStr += '\n  union{'
+            formatStr = self.append(formatStr, '    {0} pa[{1}];'.format(ptype[0], ptype[1]))
+            formatStr = self.append(formatStr, '    {0}{1} pv{2};'.format(ptype[0], ptype[1], ptype[1]))
+            formatStr += '\n  }'
+            for n in range(0, self.paramCount):
+              formatStr += 'usrc{0}'.format(n)
+              if n+1 != self.paramCount:
+                formatStr +=', '
+            formatStr += ';'
+
+            for n in range(0, self.paramCount):
+              formatStr = self.append(formatStr, '  usrc{0}.pv{1} = param{2};'.format(n, ptype[1], n))
+            formatStr = self.append(formatStr, '  for(int i =0; i < {0}; i++)'.format(ptype[1]))
+            formatStr = self.append(formatStr, '    uret.va[i] = {0}('.format(self.functionName))
+
+            for n in range(0, self.paramCount):
+              formatStr += 'usrc{0}.pa[i]'.format(n)
+              if n+1 != self.paramCount:
+                formatStr +=', '
+            formatStr += ');'
+            formatStr = self.append(formatStr, ' return uret.vv{0};'.format(vtype[1]))
+            formatStr += '\n}'
+            formatStr = self.append(formatStr)
+            return formatStr
+        else:
+          formatStr = self.append(formatStr, '{{return ({0}{1})('.format(vtype[0], vtype[1]))
+          self.indent = len(formatStr)
+          for j in range(0, vtype[1]):
             if (j != 0):
                 formatStr += ','
                 if (j + 1) % 2 == 0:
@@ -320,10 +350,10 @@ class builtinProto():
 
             formatStr += ')'
 
-        formatStr += '); }\n'
-        self.append(formatStr)
+          formatStr += '); }\n'
+          self.append(formatStr)
 
-        return formatStr
+          return formatStr
 
     def output(self):
         for line in self.outputStr:
-- 
1.8.1.2