index
:
vecmathlib
master
vecmathlib forked from https://bitbucket.org/eschnett/vecmathlib for POWER8 improvements
Raptor Engineering, LLC
summary
refs
log
tree
commit
diff
stats
log msg
author
committer
range
path:
root
/
vec_avx_fp16_16.h
Commit message (
Expand
)
Author
Age
Files
Lines
*
Correct type name __m256i
Erik Schnetter
2015-10-29
1
-14
/
+14
*
Reformat source code with clang-format
Erik Schnetter
2015-10-16
1
-652
/
+519
*
Begin to implement AVX2 support for 16-bit types
Erik Schnetter
2015-10-16
1
-0
/
+29
*
Use AVX2 intrinsics if available
Erik Schnetter
2015-09-03
1
-11
/
+100
*
Provide integer comparison operafors for AVX fp8 and fp16 vectors
Erik Schnetter
2014-06-07
1
-0
/
+6
*
Implement ifthen with boolvec arguments
Erik Schnetter
2013-07-07
1
-4
/
+8
*
Simplify return type specifications
Erik Schnetter
2013-07-07
1
-4
/
+4
*
Do not require C++11 any more
Erik Schnetter
2013-07-06
1
-8
/
+8
*
Simplify all() and any() implementations
Erik Schnetter
2013-07-05
1
-4
/
+4
*
Implement maxval and minval reduction operations
Erik Schnetter
2013-07-04
1
-0
/
+2
*
Do not use type punning for converting between vectors and elements -- gcc 4....
Erik Schnetter
2013-07-03
1
-6
/
+22
*
Whitespace change in asm intrinsics
Erik Schnetter
2013-07-02
1
-1
/
+1
*
Rename implementation files to indicate vector size
Erik Schnetter
2013-06-17
1
-0
/
+582