From: Luo Xionghu <xionghu.luo@intel.com>
Date: Tue, 16 Sep 2014 03:24:48 +0000 (+0800)
Subject: improve the build performance of vector type built-in function.
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=565d1eb00d9a5219c2848b3674e40ac07cb48b89;p=contrib%2Fbeignet.git

improve the build performance of vector type built-in function.

this patch was lost during the libocl merge. resubmit it to improve the
vector function performance.

please refer to e2db890596eea0a6eb741e11e576a38952f1ed1e for detail.

Signed-off-by: Luo Xionghu <xionghu.luo@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>
---

diff --git a/backend/src/libocl/script/gen_vector.py b/backend/src/libocl/script/gen_vector.py
index a91dfcf..de28552 100755
--- a/backend/src/libocl/script/gen_vector.py
+++ b/backend/src/libocl/script/gen_vector.py
@@ -289,9 +289,42 @@ class builtinProto():
             formatStr += ';'
             self.append(formatStr)
             return 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 += '\n    uret.va[i] = '
+            if self.prefix == 'relational' and self.functionName != 'bitselect' and self.functionName != 'select':
+              formatStr += '-'
+            formatStr += '{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:
@@ -326,10 +359,10 @@ 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: