maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
30,766 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

30766 Commits

Author SHA1 Message Date
Evan Cheng 08f2f0d145 Invalidate last use of a reused register if the use is a deleted noop copy. 
llvm-svn: 34839
 2007-03-02 05:41:42 +00:00
Chris Lattner 9c7e5e365d argument lowering should copy from the vreg shadows of live-in arguments 
passed in registers, not directly from the pregs themselves.

llvm-svn: 34838
 2007-03-02 05:12:29 +00:00
Chris Lattner fc2f52128a add a note 
llvm-svn: 34837
 2007-03-02 05:04:52 +00:00
Owen Anderson a0d8da67c1 Fix a typo. 
llvm-svn: 34836
 2007-03-02 05:03:07 +00:00
Reid Spencer cf8175617d Use a better algorithm for rounding sqrt results. Change the FIXME about 
this to a NOTE: because pari/gp results start to get rounded incorrectly
after 192 bits of precision. APInt and pari/gp never differ by more than
1, but APInt is more accurate because it does not lose precision after 192
bits as does pari/gp.

llvm-svn: 34834
 2007-03-02 04:21:55 +00:00
Nick Lewycky cf87f9eef5 Implement unionWith. 
llvm-svn: 34833
 2007-03-02 03:33:05 +00:00
Chris Lattner 4bd8cda3f0 switch the inliner from being recursive to being iterative. 
llvm-svn: 34832
 2007-03-02 03:11:20 +00:00
Reid Spencer e1336b4086 Fix an unequal bitwidth issue. 
llvm-svn: 34831
 2007-03-02 02:59:25 +00:00
Chris Lattner 73f2825957 grammaro 
llvm-svn: 34830
 2007-03-02 02:57:34 +00:00
Evan Cheng 934405cf03 Make it 64-bit safe. 
llvm-svn: 34829
 2007-03-02 02:31:37 +00:00
Reid Spencer c44bdae16b Add a FIXME 
llvm-svn: 34828
 2007-03-02 02:01:34 +00:00
Reid Spencer 91643aa96f Fix a typo. 
llvm-svn: 34826
 2007-03-02 01:31:31 +00:00
Reid Spencer c442c84c8f Fix a problem where shifting by 64-bits leads to incorrect results on PPC 
but not on X86 becuase shift by word size is "undefined".

llvm-svn: 34825
 2007-03-02 01:19:42 +00:00
Dale Johannesen 32bc81341b eliminate unnecessary reset of SP in epilog on darwin 
llvm-svn: 34824
 2007-03-02 01:17:17 +00:00
Reid Spencer 197adfaa0a Reverse a premature commital. 
llvm-svn: 34822
 2007-03-02 00:31:39 +00:00
Reid Spencer 2e54a15943 Prefer non-virtual calls to ConstantInt::isZero over virtual calls to 
Constant::isNullValue() in situations where it is possible.

llvm-svn: 34821
 2007-03-02 00:28:52 +00:00
Reid Spencer 3f770e4afd Add a non-virtual test for zero, isZero, and rename isUnitValue isOne. 
These will be used in upcoming patches to avoid virtual function call when
the client knows it is a ConstantInt.

llvm-svn: 34820
 2007-03-02 00:27:06 +00:00
Reid Spencer 76b2ce19fc Add an abs() function to get the absolute value. 
llvm-svn: 34819
 2007-03-01 23:37:09 +00:00
Reid Spencer 1b8dfcbaaa Combine two lines that can be. 
llvm-svn: 34818
 2007-03-01 23:30:25 +00:00
Reid Spencer 1700b52b8b Remove virtual keyword from method that doesn't need to be virtual. 
llvm-svn: 34817
 2007-03-01 23:20:52 +00:00
Reid Spencer caace8cffd Make it possible to create an SCEVUnknown from an APInt as well as an int. 
llvm-svn: 34816
 2007-03-01 22:28:51 +00:00
Reid Spencer fa63226751 Although probably not necessary, guard against a potential assertion by 
using isNullValue() instead of getZExtValue() == 0.

llvm-svn: 34815
 2007-03-01 21:54:37 +00:00
Reid Spencer 17797076ef Use isUnitValue() instead of getZExtValue() == 1 which will prevent an 
assert if the ConstantInt's value is large.

llvm-svn: 34814
 2007-03-01 21:51:23 +00:00
Reid Spencer 9c61acc450 Add an isUnitValue method for comparison against 1. This just follows a 
common pattern with isNullValue, isAllOnesValue, etc. It also helps to
prevent things like getZExtValue() == 1, which could assert for large
bitwidths.

llvm-svn: 34813
 2007-03-01 21:50:41 +00:00
Owen Anderson 90db545350 Use GCC intrinsics when available, and use smarter fallbacks when not. 
llvm-svn: 34812
 2007-03-01 21:16:30 +00:00
Reid Spencer bbd97b1edb Clarify the use of getValue/getSExtValue/getZExtValue and add the new 
APInt constructor.

llvm-svn: 34811
 2007-03-01 21:05:33 +00:00
Reid Spencer 5b0548de77 Use APInt conversion to string so the result is correct regardless of the 
bit width of the ConstantInt being converted.

llvm-svn: 34810
 2007-03-01 21:00:32 +00:00
Reid Spencer 07761199e0 Make output for ConstantInt construction correct for any bitwidth. 
llvm-svn: 34809
 2007-03-01 20:55:43 +00:00
Reid Spencer 4326cf5c51 Use the APInt versions of the bit-wise conversions of float/double to int 
and back. While this is not strictly necessary, it does pave the way for
future changes in casting. It should now be possible to improve vector
casting to deal with un-equal fp/int sizes.

llvm-svn: 34808
 2007-03-01 20:44:23 +00:00
Reid Spencer 022e05fdab Add doubleToBits and floatToBits methods. 
llvm-svn: 34807
 2007-03-01 20:39:01 +00:00
Reid Spencer a9e6e31db6 Use modern variable name. ConstantUnsignedInt is long since dead. No 
functional change with this patch.

llvm-svn: 34806
 2007-03-01 20:27:41 +00:00
Jim Laskey 82af5943d1 Emit eh filter info. 
llvm-svn: 34805
 2007-03-01 20:26:43 +00:00
Jim Laskey 6458e6acb9 Collect eh filter info. 
llvm-svn: 34804
 2007-03-01 20:25:32 +00:00
Reid Spencer fa80a0e8a2 Use a simpler constructor for ConstantInt. 
llvm-svn: 34803
 2007-03-01 20:25:31 +00:00
Jim Laskey d5453d7b56 Lower eh filter intrinsic. 
llvm-svn: 34802
 2007-03-01 20:24:30 +00:00
Jim Laskey 14c5842a91 Add eh filter intrinsic. 
llvm-svn: 34801
 2007-03-01 20:23:39 +00:00
Reid Spencer f762893b9b Add bitsToDouble and bitsToFloat methods for re-interpretation of bits as FP. 
llvm-svn: 34800
 2007-03-01 20:06:51 +00:00
Reid Spencer df30e2a68b Wrap a long line. 
llvm-svn: 34799
 2007-03-01 19:48:16 +00:00
Reid Spencer b973047147 Avoid a potential assert out if the loop increment is > 64 bits. 
llvm-svn: 34798
 2007-03-01 19:45:00 +00:00
Reid Spencer 8ad254df8c Regenerate. 
llvm-svn: 34797
 2007-03-01 19:41:47 +00:00
Reid Spencer 24f1a0e78f The 64-bit constructor for ConstantInt changes from int64_t to uint64_t. 
This caused a warning for construction with -1. Avoid the warning by using
-1ULL instead.

llvm-svn: 34796
 2007-03-01 19:33:52 +00:00
Reid Spencer fad3f247e4 Construct ConstantInt with simpler constructor. 
llvm-svn: 34795
 2007-03-01 19:32:33 +00:00
Reid Spencer 666ea0d046 Use a simpler constructor when constructing ConstantInt. Also, replace 
verbose code to sext/trunc or zext/trunc and APInt with new methods on
that class.

llvm-svn: 34794
 2007-03-01 19:32:01 +00:00
Reid Spencer a127633716 Use a simpler constructor when constructing ConstantInst. 
llvm-svn: 34793
 2007-03-01 19:31:12 +00:00
Reid Spencer d1bbfa5aa6 Drop the ConstantInt(const Type&, const APInt&) constructor. It is 
redundant and more verbose than the ConstantInt(const APInt&) constructor.

llvm-svn: 34792
 2007-03-01 19:30:34 +00:00
Reid Spencer 2f6ad4d3c3 Make the static table of results in sqrt const. 
llvm-svn: 34791
 2007-03-01 17:47:31 +00:00
Reid Spencer 6ba8edc789 Fix last night's 445.gobmk breakage which was caused by comparison of 
APInt's of unequal bitwidth.

llvm-svn: 34790
 2007-03-01 17:17:21 +00:00
Reid Spencer 742d1704e1 Add methods for bit width modification: sextOrTrunc, zextOrTrunc. 
llvm-svn: 34789
 2007-03-01 17:15:32 +00:00
Anton Korobeynikov af8be4458f Ensure that fastcall'ed function is correctly mangled & stack is 
properly aligned

llvm-svn: 34788
 2007-03-01 16:29:22 +00:00
Nicolas Geoffray 75ab9799df Implemented the frameaddress intrinsic for PPC. 
llvm-svn: 34787
 2007-03-01 13:11:38 +00:00