maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
82,467 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

170 Commits

Author SHA1 Message Date
Eric Christopher 1bbc7086ff Rewrite handling of 64-bit palignr intrinsics to be vector shuffles. 
Stop multiplying constant by 8 accordingly in the header and change
intrinsic definition for what types we expect.

Add to existing palignr test to check that we're emitting the correct things.

llvm-svn: 101332
 2010-04-15 01:43:08 +00:00
Chris Lattner dd6697b4fa improve altivec c++ support by adding casts, patch by 
Anton Yartsev!

llvm-svn: 101281
 2010-04-14 20:35:39 +00:00
Chris Lattner dad4062b4d implement altivec.h and a bunch of support code, patch by Anton Yartsev! 
llvm-svn: 101215
 2010-04-14 03:54:58 +00:00
Chris Lattner 4b73cfabac rename llvm::llvm_report_error -> llvm::report_fatal_error 
llvm-svn: 100708
 2010-04-07 22:58:06 +00:00
Eric Christopher 2fbd4050e9 Fix typo. 
llvm-svn: 100079
 2010-04-01 03:07:20 +00:00
Eric Christopher 5464e5ae00 First start at wmmintrin.h file with Intel AES-NI instructions. 
llvm-svn: 100077
 2010-04-01 03:03:35 +00:00
Daniel Dunbar 6a6199de67 Fix 80 col violations. 
llvm-svn: 99648
 2010-03-26 20:17:17 +00:00
Eric Christopher bd9a3aecd6 This is just a simple v4si * v4si, make it so. 
llvm-svn: 99587
 2010-03-26 00:51:28 +00:00
Anders Carlsson 91e18c93c4 Make the license header in smmintrin.h match the other SSE headers. 
llvm-svn: 99384
 2010-03-24 05:31:31 +00:00
Chris Lattner 7eac805bb0 fix PR6658: inline isn't a keyword in C89 mode, use __inline__ instead. 
llvm-svn: 99190
 2010-03-22 18:14:12 +00:00
Eric Christopher 08f135274d Add sse4.2 header and builtin support. 
llvm-svn: 99051
 2010-03-20 07:43:28 +00:00
Eric Christopher 86af0bae8a Add a newline at the end of the file. 
llvm-svn: 99026
 2010-03-20 01:19:04 +00:00
Eric Christopher 6ed351ab2d For legacy compatibility add a varargs.h header. 
llvm-svn: 99025
 2010-03-20 01:18:30 +00:00
Eric Christopher 33124e20c7 Migrate typedefs to the top level of xmmintrin.h and remove the same 
one from emmintrin.h.

llvm-svn: 99020
 2010-03-20 01:08:47 +00:00
Eric Christopher 8c6f61394f Add remaining sse4.1 intrinsics and builtins. 
llvm-svn: 98587
 2010-03-15 23:22:58 +00:00
Eric Christopher 6932b2e8b7 Add SSE4 packed integer comparisons and corresponding intrinsics. 
llvm-svn: 98323
 2010-03-12 01:22:33 +00:00
Eric Christopher e486f68b59 Integer array extraction for sse4.1. 
llvm-svn: 98305
 2010-03-11 23:50:18 +00:00
Eric Christopher e7594305bc Add packed integer array insertion. 
llvm-svn: 98299
 2010-03-11 23:36:29 +00:00
Eric Christopher 1dca62055a Add insert/extract_ps and related random macros. 
llvm-svn: 98114
 2010-03-10 00:50:58 +00:00
Ted Kremenek 0a4a8326c1 Add preprocessor guards to the definitions of size_t and wchar_t, and #undef NULL before defining it. 
This addresses potential issues with system headers reported in <rdar://problem/7727159>.

llvm-svn: 98006
 2010-03-08 23:23:45 +00:00
Ted Kremenek 4c9862ca1d Place the definition of 'va_list' within a preprocessor guard. This matches the behavior of GCC, and avoids potential conflicts with system headers (e.g., stdio.h). Fixes <rdar://problem/7727145>. 
llvm-svn: 98003
 2010-03-08 23:13:05 +00:00
Eric Christopher 4c70358296 Add sse4.1 packed min and max intrinsics. 
llvm-svn: 97907
 2010-03-07 07:00:42 +00:00
Eric Christopher 7288890b51 Add load hint instruction intrinsic. 
llvm-svn: 97904
 2010-03-07 06:29:09 +00:00
Eric Christopher 87990fe5df Add in support for dword multiply and fp dot product intrinsics. 
llvm-svn: 97902
 2010-03-07 06:17:19 +00:00
Eric Christopher b0759be4d0 Fix _MM_FROUND_NEARBYINT and move rounding intrinsics to macros. 
llvm-svn: 97874
 2010-03-06 10:31:44 +00:00
Eric Christopher 94567c04bb First start on smmintrin.h, rounding and blending. 
llvm-svn: 97717
 2010-03-04 02:56:19 +00:00
Chris Lattner e983eae273 add two aliases for SSE functions we already have, fixing PR6316. 
llvm-svn: 96363
 2010-02-16 18:21:25 +00:00
Chris Lattner b18093e467 fix PR6187: various load functions in xmmintrin.h were missing 'const'. 
emmintrin looks ok.

llvm-svn: 94998
 2010-02-01 20:14:14 +00:00
Chris Lattner 0afd3a23cd fix a bug in the _MM_TRANSPOSE4_PS definition, patch by Brian Sumner from 
PR6138

llvm-svn: 94669
 2010-01-27 07:54:50 +00:00
Chris Lattner 4debb32fdd _mm_xor_ps does a xor not a nxor. The other 'xor' builtins look fine, 
but this one is wrong.  Thanks to Tanya for noticing this.

llvm-svn: 92881
 2010-01-07 00:36:41 +00:00
Nate Begeman 67dfd4236a Revert mmx palignr to use an intrinsic, since mmx shuffle patterns are missing. 
llvm-svn: 91269
 2009-12-14 05:15:02 +00:00
Nate Begeman 72ec6bc6f4 Support x86's PALIGNR instruction without the use of a palignr intrinsic. 
llvm-svn: 91264
 2009-12-14 04:57:03 +00:00
Chris Lattner 399df12fb1 minimal fix for PR5743 
llvm-svn: 91032
 2009-12-10 01:38:15 +00:00
Douglas Gregor df72af5935 Pick up MB_LEN_MAX as defined by the system <limits.h>, when it's provided there 
llvm-svn: 90879
 2009-12-08 21:35:00 +00:00
Ken Dyck f540ae5ab3 Define SIG_ATOMIC_MIN and SIG_ATOMIC_MAX in terms of __SIG_ATOMIC_WIDTH__. 
llvm-svn: 89598
 2009-11-22 15:47:12 +00:00
Ken Dyck 33211d9658 Avoid unwanted expansion in macros that paste together INT<n>_C(v) and 
UINT<n>_C(v) macros. 

llvm-svn: 89461
 2009-11-20 16:49:10 +00:00
Ken Dyck 8dcc21420b Avoid unwanted expansion in macros that paste together INT<n>_MIN, INT<n>_MAX, 
and UINT<n>_MAX defintions.

llvm-svn: 89460
 2009-11-20 16:44:38 +00:00
Ken Dyck 764a5f3881 Avoid unwanted macro expansion in macros that paste together int<n>_t and 
uint<n>_t definitions.

llvm-svn: 89459
 2009-11-20 16:37:35 +00:00
Ken Dyck aff01ceb95 Define WCHAR_MIN and WCHAR_MAX in terms of __WCHAR_WIDTH__ for consistency with 
other limit macros.

llvm-svn: 89355
 2009-11-19 15:53:08 +00:00
Ken Dyck f0b343f5b7 Parameterize WINT_MIN and WINT_MAX with __WINT_WIDTH__ to support arbitrary 
widths. This corrects the values of these definitions for MSP430 and PIC16.

llvm-svn: 89350
 2009-11-19 14:35:19 +00:00
Ken Dyck 279ed5189c Construct definition of SIZE_MAX from __SIZE_WIDTH__ to support targets of 
arbitrary widths.

llvm-svn: 89347
 2009-11-19 14:03:24 +00:00
Ken Dyck 8af6035ac9 Construct the macro body of PTRDIFF_MAX and PTRDIFF_MIN from __PTRDIFF_WIDTH__. 
llvm-svn: 89343
 2009-11-19 12:33:01 +00:00
Ken Dyck 68fa5afada Construct INTPTR_MIN, INTPTR_MAX, and UINTPTR_MAX from the exact-width limit 
macros corresponding to __INTPTR_WIDTH__.

llvm-svn: 89239
 2009-11-18 20:36:29 +00:00
Ken Dyck 2d4371d666 Define intptr_t and uintptr_t in terms of their equivalent exact-width types. 
llvm-svn: 89237
 2009-11-18 20:24:13 +00:00
Ken Dyck ac11b7b625 Define INTMAX_C and UINTMAX_C in terms of the corresponding exact-width 
INTn_C and UINTn_C macros.

llvm-svn: 89226
 2009-11-18 19:42:57 +00:00
Ken Dyck 63c8ef8256 Define INTMAX_MIN, INTMAX_MAX, and UINTMAX_MAX in terms of the limit macros for 
their corresponding exact-width type. 

llvm-svn: 89224
 2009-11-18 19:22:15 +00:00
Ken Dyck 47181584f1 Define intmax_t and uintmax_t as the [u]intN_t type corresponding to 
__INTMAX_WIDTH__.

llvm-svn: 89221
 2009-11-18 18:57:04 +00:00
Ken Dyck 19ac306c2c Replace (-INT8_C(128)), which uses an illegally out-of-range argument for 
INT8_C, with (-INT8_C(127)-1) in the definition of INT8_MIN. Apply similar
changes to the definitions of INT16_MIN and INT24_MIN.

llvm-svn: 89120
 2009-11-17 18:29:12 +00:00
Ken Dyck f78dc738a5 Use the INTn_C integer constant macros to generate limit constants with correct 
suffixes. This corrects the suffixes for the limit constants of the 32-bit
types on MSP430 and PIC16, and the 64-bit types on PPC64, SystemZ, X86_64.

llvm-svn: 89101
 2009-11-17 16:26:27 +00:00
Ken Dyck e115235705 Remove unnecessary parens around the bodies of integer constant macros. C99 
requires that their arguments be decimal, hex, octal constants---no signs
allowed---making the parens unnecessary.

llvm-svn: 89095
 2009-11-17 13:54:02 +00:00