aaron/ispc
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
1,111 Commits 6 Branches 36 Tags
6827001c1d04a5c73538e0dd10a3ef5d32ca198d
Commit Graph

1111 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Jean-Luc Duprat
6827001c1d Merge pull request #406 from pengtu/master 
Fix ISPC with LLVM TOT build problem
 2012-11-22 09:27:10 -08:00
Peng Tu
16b0806d40 Fix LLVM TOT build issue. 2012-11-21 19:09:10 -08:00
Jean-Luc Duprat
2129b1e27d knc.h: Fixed __rsqrt_varying_float() to use _mm512_invsqrt_ps() instead of _mm512_invsqrt_pd() 
This was a typo.
 2012-11-21 15:40:35 -08:00
Jean-Luc Duprat
a267762f59 Merge pull request #404 from mmp/master 
Fix build with LLVM top-of-tree
 2012-11-21 10:37:40 -08:00
Jean-Luc Duprat
65ca795030 Merge pull request #405 from jbrodman/master 
Tweaked Scalar Repl of Aggregates Optimization
 2012-11-19 13:12:26 -08:00
Matt Pharr
e82b649ec0 Fix build with LLVM top-of-tree (various changes to clang entrypoints). 2012-11-16 11:04:11 -08:00
james.brodman
275cdb1713 Merge branch 'master' of https://github.com/ispc/ispc 2012-11-14 13:30:45 -05:00
Jean-Luc Duprat
d3b86dcc90 KNC: fix implementation of __all() to use KNCni mask test instructions... 2012-11-14 09:24:01 -08:00
james.brodman
c736b75075 Merge branch 'master' of https://github.com/ispc/ispc 2012-11-13 17:08:09 -05:00
Jean-Luc Duprat
b601331362 Approximation for inverse sqrt and reciprocal provided in fast math mode. 
RCP was actually slow in fast math mode
   Inverse sqrt did not expose fast approximation
 2012-11-13 14:01:35 -08:00
ptu1
32d44a5b9e Merge branch 'master' of ssh://fmygit6001.fm.intel.com:29418/ssg_dpd_tpi_ispc-ispc_git 2012-11-13 12:47:13 -08:00
ptu1
810784da1f Set the ScalarReplAggregate maximum structure size based on target vector width. 2012-11-13 12:35:45 -08:00
james.brodman
d517b37f3f Merge branch 'master' of https://github.com/ispc/ispc 2012-11-09 10:14:18 -05:00
Jean-Luc Duprat
adeef0af01 Merge pull request #403 from jbrodman/master 
Fixed =/== error for KNC intrinsic implementation of __all()
 2012-11-08 13:57:42 -08:00
james.brodman
97ddc1ed10 Fixed =/== error in __all() 2012-11-08 16:30:12 -05:00
james.brodman
bf580648a1 Merge branch 'master' of https://github.com/ispc/ispc 2012-11-06 12:03:27 -05:00
Jean-Luc Duprat
ecc54fa0eb Merge pull request #402 from pengtu/master 
Fix a bug where an unsigned index variable in subscript is sxt to 64 bit
 2012-11-05 21:51:38 -08:00
Peng Tu
04d32ae3e6 Inside LLVM, both signed and unsigned integer are represented with the same type - i32 - effectively a signed int32. On 64 bit target, we must generate explicit sxt/zxt during the LLVM IR creation to promote the array index into 64 bit. Otherwise, an unsigned int index becomes signed int index in the LLVM IR. 
I limit the fix to uniformed index to avoid widening a varying index vector to 64 bits.  This means that the 32 bit values in the varying indices must be positive and smaller than 2^31 at the runtime for a program to behave correctly.
 2012-11-05 15:02:15 -08:00
james.brodman
a18b3ae88e Merge branch 'master' of https://github.com/ispc/ispc 2012-10-31 15:25:41 -04:00
james.brodman
e57801a5d1 Typo Fix 2012-10-31 15:25:26 -04:00
ingowald
da4390aede Merge pull request #401 from pengtu/master 
Fix a "continue" handling bug in foreach_unique/foreach_active
 2012-10-30 01:46:01 -07:00
Peng Tu
9e85667219 Merge remote branch 'upstream/master' 2012-10-29 22:51:22 -07:00
Peng Tu
b80867d473 Move the call to RestoreContinuedLanes from bbBody to the correct place of bbCheckForMore for foreach_unique and foreach_active. 2012-10-29 17:27:11 -07:00
Jean-Luc Duprat
d742dcce59 Merge pull request #400 from jbrodman/master 
Fixes a compile error in examples/intrinsics/sse4.h. Assignment was used instead of equality comparison.
 2012-10-26 14:08:56 -07:00
james.brodman
7a7af3d5f9 Merge branch 'master' of https://github.com/jbrodman/ispc 2012-10-26 16:55:53 -04:00
jbrodman
e323b1d0ad Fixed compile error: == instead of = 2012-10-26 16:55:28 -04:00
james.brodman
3c18c7a713 Fixed compile error: == instead of = 2012-10-26 16:52:54 -04:00
james.brodman
7c16292cb7 Merge branch 'master' of https://github.com/ispc/ispc 2012-10-24 13:49:04 -04:00
Gerrit Code Review
d665e2e85b Initial empty repository 2012-10-24 09:53:29 -07:00
Matt Pharr
172a189c6f Fix build with LLVM top-of-tree 2012-10-17 11:11:50 -07:00
Matt Pharr
406fbab40e Fix bugs in declarations of __any, __all, and __none in examples/intrinsics. 
They return bool, not vector of bool.
 2012-10-17 10:55:50 -07:00
Matt Pharr
09dc217f8c Fix hex constant in lParseInteger() (missing an f) 2012-10-16 06:03:33 -07:00
Matt Pharr
9002837750 Remove incorrect assert in tasksys.cpp 2012-10-15 10:43:46 -07:00
Matt Pharr
411d5b44ef Add ISPC_HAS_RAND definition on targets that have a HW RNG. 
This lets us check for a functioning rdrand() call in the stdlib
more reliably.  Fixes issue #333.
 2012-10-03 09:18:12 -07:00
Matt Pharr
360cc8044e Improve RNG documentation. 
Issue #390.
 2012-10-03 08:33:43 -07:00
Matt Pharr
ec2e9b5e79 Fix typo in assert() documentation. 
Issue #388.
 2012-10-03 08:26:38 -07:00
Matt Pharr
881dba61e4 Fix build with LLVM top-of-tree 2012-09-28 06:07:01 -07:00
Matt Pharr
6412876f64 Remove unused __reduce_add_uint{32,64} target functions. 
The stdilb code just calls the signed int{32,64} functions,
which gives the right result for the unsigned case anyway.
The various targets didn't consistently define the unsigned
variants in any case.
 2012-09-28 05:55:41 -07:00
Matt Pharr
538d51cbfe Add GMRES example 2012-09-20 14:06:55 -07:00
Jean-Luc Duprat
3dd9ff3d84 knc.h: 
Properly pick up on ISPC_FORCE_ALIGNED_MEMORY when --opt=force-aligned-memory is used
	Fixed usage of loadunpack and packstore to use proper memory offset
	Fixed implementation of __masked_load_*() __masked_store_*() incorrectly (un)packing the lanes loaded
	Cleaned up usage of _mm512_undefined_*(), it is now mostly confined to constructor
	Minor cleanups

knc2x.h
	Fixed usage of loadunpack and packstore to use proper memory offset
	Fixed implementation of __masked_load_*() __masked_store_*() incorrectly (un)packing the lanes loaded
	Properly pick up on ISPC_FORCE_ALIGNED_MEMORY when --opt=force-aligned-memory is used
	__any() and __none() speedups.
	Cleaned up usage of _mm512_undefined_*(), it is now mostly confined to constructor
 2012-09-19 17:11:04 -07:00
Ingo Wald
7f386923b0 Merge branch 'master' of https://github.com/ispc/ispc 2012-09-17 15:54:25 +02:00
Ingo Wald
d2312b1fbd now using the ASSUME_ALIGNED flag in knc.h 2012-09-17 15:54:00 +02:00
Ingo Wald
6655373ac3 commit test 2012-09-17 15:51:37 +02:00
Ingo Wald
d492af7bc0 64-bit gather/scatter, aligned load/store, i8 support 2012-09-17 03:39:02 +02:00
Matt Pharr
230a7b7374 Fix bug with floating-point constant zero vectors. 
Issue #377.
 2012-09-14 14:24:51 -07:00
Jean-Luc Duprat
4204a752f7 Merge branch 'master' of https://github.com/ispc/ispc 2012-09-14 14:12:49 -07:00
Jean-Luc Duprat
0e88d5f97f Fixed unaligned masked stores on KNC 2012-09-14 14:11:41 -07:00
Matt Pharr
a13e7f2435 #define ISPC_FORCE_ALIGNED_MEMORY, if appropriate, in C++ output. 2012-09-14 13:53:12 -07:00
Matt Pharr
be2108260e Add --opt=force-aligned-memory option. 
This forces all vector loads/stores to be done assuming that the given
pointer is aligned to the vector size, thus allowing the use of sometimes
more-efficient instructions.  (If it isn't the case that the memory is
aligned, the program will fail!).
 2012-09-14 13:49:45 -07:00
Matt Pharr
59b0a2b208 Mark __any(), __all(), and __none() as internal after they're linked in. 
This fixes multiple symbol definition errors when compiling a single binary
for multiple ISA targets.
 2012-09-14 13:32:42 -07:00