RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-24 13:33:37 +02:00
Code Issues Projects Releases Wiki Activity
108,027 Commits 4 Branches 5 Tags 704 MiB
23706ac8f2
Commit Graph

288 Commits

Author SHA1 Message Date
Chandler Carruth
250dce460c Teach constant folding to perform conversions from constant floating 
point values to their integer representation through the SSE intrinsic
calls. This is the last part of a README.txt entry for which I have real
world examples.

llvm-svn: 123206
 2011-01-11 01:07:24 +00:00
Owen Anderson
4479341626 Fix a random missed optimization by making InstCombine more aggressive when determining which bits are demanded by 
a comparison against a constant.

llvm-svn: 123203
 2011-01-11 00:36:45 +00:00
Chris Lattner
c46188944e +0.0 vs -0.0 differences can be handled by looking at the user of the 
operation in some cases.

llvm-svn: 123190
 2011-01-10 21:01:17 +00:00
Chris Lattner
2bd48ecd43 expand on a note 
llvm-svn: 123145
 2011-01-10 00:33:01 +00:00
Chris Lattner
7926b7035f typo 
llvm-svn: 123142
 2011-01-09 23:48:41 +00:00
Chris Lattner
fc6d425076 xref a PR # 
llvm-svn: 123141
 2011-01-09 23:42:22 +00:00
Chandler Carruth
a4d454ae5e Add a note about the inability to model FP -> int conversions which 
perform rounding other than truncation in the IR. Common C code for this
turns into really an LLVM intrinsic call that blocks a lot of further
optimizations.

llvm-svn: 123135
 2011-01-09 22:36:18 +00:00
Chandler Carruth
2a30077fed Add a note about a missed FP optimization. 
llvm-svn: 123126
 2011-01-09 21:00:19 +00:00
Chandler Carruth
17c1672ea9 Another missed memset in std::vector initialization. 
llvm-svn: 123116
 2011-01-09 11:29:57 +00:00
Chandler Carruth
dcbd7b6eaa Fix a cut-paste-o so that the sample code is correct for my last note. 
Also, switch to a more clear 'sink' function with its declaration to
avoid any confusion about 'g'. Thanks for the suggestion Frits.

llvm-svn: 123113
 2011-01-09 10:10:59 +00:00
Chandler Carruth
3de0da8801 Another missed optimization of trivial vector code. 
llvm-svn: 123112
 2011-01-09 09:58:36 +00:00
Chandler Carruth
9220d9fa48 Add a note about vector's size-constructor producing dead stores. 
llvm-svn: 123111
 2011-01-09 09:58:33 +00:00
Chandler Carruth
815cbfb43c Add a note about a missed memset optimization from std::fill. 
llvm-svn: 123103
 2011-01-09 01:32:55 +00:00
Benjamin Kramer
62b5a4d14c Revert 122959, it needs more thought. Add it back to README.txt with additional notes. 
llvm-svn: 123030
 2011-01-07 20:42:20 +00:00
Chris Lattner
2fd8a095b1 With Benjamin's recent amazing patches, we should be able to do even better things :) 
llvm-svn: 122978
 2011-01-06 22:25:00 +00:00
Benjamin Kramer
4e31a65344 Add a note from llvmdev, this time with more info. 
llvm-svn: 122966
 2011-01-06 17:35:50 +00:00
Benjamin Kramer
33e41f4986 EarlyCSE does this now (and GVN always did it). 
llvm-svn: 122960
 2011-01-06 13:19:46 +00:00
Benjamin Kramer
5834b2bab8 InstCombine: If we call llvm.objectsize on a malloc call we can replace it with the size passed to malloc. 
llvm-svn: 122959
 2011-01-06 13:11:05 +00:00
Chris Lattner
40973baa5f add a note about object size from drystone, add a poorly optimized loop from 179.art. 
llvm-svn: 122954
 2011-01-06 07:41:22 +00:00
Chris Lattner
69ff12968c add a trivial instcombine missed in Dhrystone 
llvm-svn: 122953
 2011-01-06 07:09:23 +00:00
Chris Lattner
222b24e2de update a bunch of entries. 
llvm-svn: 122700
 2011-01-02 18:31:38 +00:00
Chris Lattner
f669d6a901 Allow loop-idiom to run on multiple BB loops, but still only scan the loop 
header for now for memset/memcpy opportunities.  It turns out that loop-rotate
is successfully rotating loops, but *DOESN'T MERGE THE BLOCKS*, turning "for 
loops" into 2 basic block loops that loop-idiom was ignoring.

With this fix, we form many *many* more memcpy and memsets than before, including
on the "history" loops in the viterbi benchmark, which look like this:

        for (j=0; j<MAX_history; ++j) {
          history_new[i][j+1] = history[2*i][j];
        }

Transforming these loops into memcpy's speeds up the viterbi benchmark from
11.98s to 3.55s on my machine.  Woo.

llvm-svn: 122685
 2011-01-02 07:58:36 +00:00
Chris Lattner
9dadac901f a missed __builtin_object_size case. 
llvm-svn: 122676
 2011-01-01 22:57:31 +00:00
Chris Lattner
e3e3cb83a5 various updates. 
llvm-svn: 122675
 2011-01-01 22:52:11 +00:00
Duncan Sands
aaddf57af9 Revert commit 122654 at the request of Chris, who reckons that instsimplify 
is the wrong hammer for this nail, and is probably right.

llvm-svn: 122661
 2011-01-01 20:08:02 +00:00
Duncan Sands
ec8b2b4cc5 Fix a README item by having InstructionSimplify do a mild form of value 
numbering, in which it considers (for example) "%a = add i32 %x, %y" and
"%b = add i32 %x, %y" to be equal because the operands are equal and the
result of the instructions only depends on the values of the operands.
This has almost no effect (it removes 4 instructions from gcc-as-one-file),
and perhaps slows down compilation: I measured a 0.4% slowdown on the large
gcc-as-one-file testcase, but it wasn't statistically significant.

llvm-svn: 122654
 2011-01-01 16:12:09 +00:00
Chris Lattner
8e3ff12790 add a note from llvmdev 
llvm-svn: 122603
 2010-12-28 18:45:02 +00:00
Benjamin Kramer
0a0e2c55c4 Remove/fix invalid README entries. The well thought out strcpy function doesn't return a pointer to the end of the string. 
llvm-svn: 122496
 2010-12-23 15:32:07 +00:00
Chris Lattner
3bc741a0d2 recognize an unsigned add with overflow idiom into uadd. 
This resolves a README entry and technically resolves PR4916,
but we still get poor code for the testcase in that PR because
GVN isn't CSE'ing uadd with add, filed as PR8817.

Previously we got:

_test7:                                 ## @test7
	addq	%rsi, %rdi
	cmpq	%rdi, %rsi
	movl	$42, %eax
	cmovaq	%rsi, %rax
	ret

Now we get:

_test7:                                 ## @test7
	addq	%rsi, %rdi
	movl	$42, %eax
	cmovbq	%rsi, %rax
	ret

llvm-svn: 122182
 2010-12-19 19:37:52 +00:00
Chris Lattner
63d08e3444 add another overflow idiom 
llvm-svn: 121854
 2010-12-15 07:28:58 +00:00
Chris Lattner
ec899c30d9 add a note about overflow idiom recognition. 
llvm-svn: 121853
 2010-12-15 07:25:55 +00:00
Chris Lattner
82b8cda077 add a shift/imul missed optimization 
llvm-svn: 121850
 2010-12-15 07:10:43 +00:00
Chris Lattner
d2022fee87 add a note about a SPEC hack that gcc mainline does. 
llvm-svn: 121849
 2010-12-15 06:38:24 +00:00
Chris Lattner
72f03b62a9 add a note 
llvm-svn: 121656
 2010-12-13 00:15:25 +00:00
Benjamin Kramer
a638216447 Generalize the and-icmp-select instcombine further by allowing selects of the form 
(x & 2^n) ? 2^m+C : C

we can offset both arms by C to get the "(x & 2^n) ? 2^m : 0" form, optimize the
select to a shift and apply the offset afterwards.

llvm-svn: 121609
 2010-12-11 10:49:22 +00:00
Benjamin Kramer
8d7096e8ca The srem -> urem transform is not safe for any divisor that's not a power of two. 
E.g. -5 % 5 is 0 with srem and 1 with urem.

Also addresses Frits van Bommel's comments.

llvm-svn: 120049
 2010-11-23 20:33:57 +00:00
Benjamin Kramer
c8e6037e7d InstCombine: Reduce "X shift (A srem B)" to "X shift (A urem B)" iff B is positive. 
This allows to transform the rem in "1 << ((int)x % 8);" to an and.

llvm-svn: 120028
 2010-11-23 18:52:42 +00:00
Benjamin Kramer
b5a2a81094 InstCombine: Implement X - A*-B -> X + A*B. 
llvm-svn: 119984
 2010-11-22 20:31:27 +00:00
Benjamin Kramer
632a91cba5 Implement the "if (X == 6 || X == 4)" -> "if ((X|2) == 6)" optimization. 
This currently only catches the most basic case, a two-case switch, but can be
extended later.

llvm-svn: 119964
 2010-11-22 09:45:38 +00:00
Chris Lattner
ed3b3d47f6 add some random notes. 
llvm-svn: 119925
 2010-11-21 07:05:31 +00:00
Chris Lattner
908a01328c optimize: 
void a(int x) { if (((1<<x)&8)==0) b(); }

into "x != 3", which occurs over 100 times in 403.gcc but in no
other program in llvm-test.

llvm-svn: 119922
 2010-11-21 06:44:42 +00:00
Chris Lattner
09bf382b8f tail calls on x86 are implemented. 
llvm-svn: 119920
 2010-11-21 06:10:27 +00:00
Chris Lattner
b3eff154cd add a note 
llvm-svn: 118806
 2010-11-11 18:23:57 +00:00
Chris Lattner
3514fa6b11 add pr# 
llvm-svn: 118797
 2010-11-11 17:17:56 +00:00
Chris Lattner
d7d7d5717b add a case we fail to devirt. 
llvm-svn: 118608
 2010-11-09 19:37:28 +00:00
Duncan Sands
c9c7d54930 Fix a README item: when doing a comparison with the result 
of a select instruction, see if doing the compare with the
true and false values of the select gives the same result.
If so, that can be used as the value of the comparison.

llvm-svn: 118378
 2010-11-07 16:12:23 +00:00
Benjamin Kramer
16b841c233 Add a note. 
llvm-svn: 118337
 2010-11-06 10:37:16 +00:00
Benjamin Kramer
2a44a539e2 Add constant folding for strspn and strcspn to SimplifyLibCalls. 
llvm-svn: 115116
 2010-09-30 00:58:35 +00:00
Chris Lattner
3203bf3688 idiom recognition should catch this. 
llvm-svn: 114304
 2010-09-19 00:37:34 +00:00
Nick Lewycky
3a15ba4d5e Add optimization to Target/README.txt. 
llvm-svn: 110543
 2010-08-08 07:04:25 +00:00
Benjamin Kramer
27eb255a70 Teach instcombine to transform 
(X >s -1) ? C1 : C2 and (X <s  0) ? C2 : C1
into ((X >>s 31) & (C2 - C1)) + C1, avoiding the conditional.

This optimization could be extended to take non-const C1 and C2 but we better
stay conservative to avoid code size bloat for now.

for
int sel(int n) {
     return n >= 0 ? 60 : 100;
}

we now generate
  sarl  $31, %edi
  andl  $40, %edi
  leal  60(%rdi), %eax

instead of
  testl %edi, %edi
  movl  $60, %ecx
  movl  $100, %eax
  cmovnsl %ecx, %eax

llvm-svn: 107866
 2010-07-08 11:39:10 +00:00
Eli Friedman
4cac2d90a2 Minor amendment to switch-lowering improvement. 
llvm-svn: 107569
 2010-07-03 08:43:32 +00:00
Eli Friedman
663bc3ce7e Note switch-lowering inefficiency. 
llvm-svn: 107565
 2010-07-03 07:38:12 +00:00
Eric Christopher
4c54014a1e Add another bswap idiom that isn't matched. 
llvm-svn: 107213
 2010-06-29 22:22:22 +00:00
Benjamin Kramer
01a44323f0 TODO-- 
llvm-svn: 106102
 2010-06-16 15:47:00 +00:00
Eli Friedman
b4ac3e405c Add README entry; based on testcase from Bill Hart. 
llvm-svn: 105878
 2010-06-12 05:54:27 +00:00
Chris Lattner
d5c391bba6 add a note 
llvm-svn: 104404
 2010-05-21 23:16:21 +00:00
Dan Gohman
4f9dc00cec Add a README entry. 
llvm-svn: 102906
 2010-05-03 14:31:00 +00:00
Chris Lattner
136547652d add a note 
llvm-svn: 101581
 2010-04-16 23:52:30 +00:00
Chris Lattner
3282f3d34f Implement rdar://7860110 (also in target/readme.txt) narrowing 
a load/or/and/store sequence into a narrower store when it is
safe.  Daniel tells me that clang will start producing this sort
of thing with bitfields, and this does  trigger a few dozen times
on 176.gcc produced by llvm-gcc even now.

This compiles code like CodeGen/X86/2009-05-28-DAGCombineCrash.ll 
into:

        movl    %eax, 36(%rdi)

instead of:

        movl    $4294967295, %eax       ## imm = 0xFFFFFFFF
        andq    32(%rdi), %rax
        shlq    $32, %rcx
        addq    %rax, %rcx
        movq    %rcx, 32(%rdi)

and each of the testcases into a single store.  Each of them used
to compile into craziness like this:

_test4:
	movl	$65535, %eax            ## imm = 0xFFFF
	andl	(%rdi), %eax
	shll	$16, %esi
	addl	%eax, %esi
	movl	%esi, (%rdi)
	ret

llvm-svn: 101343
 2010-04-15 04:48:01 +00:00
Chris Lattner
d14ff9f87b move PR6576 here. 
llvm-svn: 98194
 2010-03-10 21:42:42 +00:00
Chris Lattner
dbbd13f825 move PR6212 to this file. 
llvm-svn: 95624
 2010-02-09 00:11:10 +00:00
Eli Friedman
28884d637b Remove a completed item, add a couple new ones. 
llvm-svn: 94945
 2010-01-31 04:55:32 +00:00
Bob Wilson
f897b7b37e Improve isSafeToLoadUnconditionally to recognize that GEPs with constant 
indices are safe if the result is known to be within the bounds of the
underlying object.

llvm-svn: 94829
 2010-01-29 19:19:08 +00:00
Chris Lattner
82318209c4 reassociate should do this. 
llvm-svn: 94374
 2010-01-24 20:17:09 +00:00
Chris Lattner
e328ab9a00 add a note. 
llvm-svn: 94373
 2010-01-24 20:01:41 +00:00
Chris Lattner
8909d5aca5 implement a simple instcombine xform that has been in the 
readme forever.

llvm-svn: 94318
 2010-01-23 18:49:30 +00:00
Chris Lattner
fdc6162f82 add some notes, making posix-memalign be nocapture would be an easy improvement. 
llvm-svn: 94312
 2010-01-23 17:59:23 +00:00
Eli Friedman
0aade63ca6 Add some potentially interesting transformations to README. 
llvm-svn: 93797
 2010-01-18 22:36:59 +00:00
Duncan Sands
de0adbdf25 Fix a README item: have functionattrs look through selects and 
phi nodes when deciding which pointers point to local memory.
I actually checked long ago how useful this is, and it isn't
very: it hardly ever fires in the testsuite, but since Chris
wants it here it is!

llvm-svn: 92836
 2010-01-06 15:37:47 +00:00
Duncan Sands
4ef1119d94 Partially address a README by having functionattrs consider calls to 
memcpy, memset and other intrinsics that only access their arguments
to be readnone if the intrinsic's arguments all point to local memory.
This improves the testcase in the README to readonly, but it could in
theory be made readnone, however this would involve more sophisticated
analysis that looks through the memcpy.

llvm-svn: 92829
 2010-01-06 08:45:52 +00:00
Chris Lattner
ce3f5f3448 implement an instcombine xform needed by clang's codegen 
on the example in PR4216.  This doesn't trigger in the testsuite,
so I'd really appreciate someone scrutinizing the logic for
correctness.

llvm-svn: 92458
 2010-01-04 06:03:59 +00:00
Chris Lattner
44298d184a Teach codegen to lower llvm.powi to an efficient (but not optimal) 
multiply sequence when the power is a constant integer.  Before, our
codegen for std::pow(.., int) always turned into a libcall, which was
really inefficient.

This should also make many gfortran programs happier I'd imagine.

llvm-svn: 92388
 2010-01-01 03:32:16 +00:00
Chris Lattner
0ea2e3d444 update this. To take the next step, llvm.powi should be generalized to work 
on integers as well and codegen should lower them to branch trees.

llvm-svn: 92382
 2010-01-01 01:29:26 +00:00
Eli Friedman
392adbdd7d More info on this transformation. 
llvm-svn: 91230
 2009-12-12 23:23:43 +00:00
Eli Friedman
38a7d3b32e Remove some stuff that's already implemented. Also, remove the note about 
merging x >u 5 and x <s 20 because it's impossible to implement.

llvm-svn: 91228
 2009-12-12 21:41:48 +00:00
Chris Lattner
b46655e25c expand note. 
llvm-svn: 90429
 2009-12-03 07:43:46 +00:00
Chris Lattner
6b86618a2b add a note 
llvm-svn: 90428
 2009-12-03 07:41:54 +00:00
Chris Lattner
40d74cea6b update and consolidate the load pre notes. 
llvm-svn: 90050
 2009-11-29 02:19:52 +00:00
Chris Lattner
0df78ea645 add a deadargelim note. 
llvm-svn: 90009
 2009-11-27 17:12:30 +00:00
Chris Lattner
c0b92ff385 This testcase is actually only partially redundant, and requires 
the FIXME I added yesterday to be implemented.

llvm-svn: 90008
 2009-11-27 16:53:57 +00:00
Chris Lattner
225a88f4ab this (and probably several others) are now done. 
llvm-svn: 89982
 2009-11-27 00:35:04 +00:00
Chris Lattner
4824ebfded Teach memdep to phi translate bitcasts. This allows us to compile 
the example in GCC PR16799 to:

LBB1_2:                                                     ## %bb1
	movl	%eax, %eax
	subq	%rax, %rdi
	movq	%rdi, (%rcx)
	movl	(%rdi), %eax
	testl	%eax, %eax
	je	LBB1_2

instead of:

LBB1_2:                                                     ## %bb1
	movl	(%rdi), %ecx
	subq	%rcx, %rdi
	movq	%rdi, (%rax)
	cmpl	$0, (%rdi)
	je	LBB1_2

llvm-svn: 89978
 2009-11-26 23:41:07 +00:00
Chris Lattner
9c88c96b3f Teach basicaa that x|c == x+c when the c bits of x are clear. This 
allows us to compile the example in readme.txt into:

LBB1_1:                                                     ## %bb
	movl	4(%rdx,%rax), %ecx
	movl	%ecx, %esi
	imull	(%rdx,%rax), %esi
	imull	%esi, %ecx
	movl	%esi, 8(%rdx,%rax)
	imull	%ecx, %esi
	movl	%ecx, 12(%rdx,%rax)
	movl	%esi, 16(%rdx,%rax)
	imull	%ecx, %esi
	movl	%esi, 20(%rdx,%rax)
	addq	$16, %rax
	cmpq	$4000, %rax
	jne	LBB1_1

instead of:

LBB1_1: 
	movl	(%rdx,%rax), %ecx
	imull	4(%rdx,%rax), %ecx
	movl	%ecx, 8(%rdx,%rax)
	imull	4(%rdx,%rax), %ecx
	movl	%ecx, 12(%rdx,%rax)
	imull	8(%rdx,%rax), %ecx
	movl	%ecx, 16(%rdx,%rax)
	imull	12(%rdx,%rax), %ecx
	movl	%ecx, 20(%rdx,%rax)
	addq	$16, %rax
	cmpq	$4000, %rax
	jne	LBB1_1

GCC (4.2) doesn't seem to be able to eliminate the loads in this 
testcase either, it generates:

L2:
	movl	(%rdx), %eax
	imull	4(%rdx), %eax
	movl	%eax, 8(%rdx)
	imull	4(%rdx), %eax
	movl	%eax, 12(%rdx)
	imull	8(%rdx), %eax
	movl	%eax, 16(%rdx)
	imull	12(%rdx), %eax
	movl	%eax, 20(%rdx)
	addl	$4, %ecx
	addq	$16, %rdx
	cmpl	$1002, %ecx
	jne	L2

llvm-svn: 89952
 2009-11-26 16:26:43 +00:00
Chris Lattner
677b93d4c8 teach basicaa that A[i] != A[i+1]. 
llvm-svn: 89951
 2009-11-26 16:18:10 +00:00
Chris Lattner
0b862edca3 update some notes slightly 
llvm-svn: 89913
 2009-11-26 01:51:18 +00:00
Nick Lewycky
b73208f294 Add a complex missed optimization opportunity I came across while investigating 
bug 5438.

llvm-svn: 88855
 2009-11-15 17:51:23 +00:00
Chris Lattner
0dd2fe1e1e another const prop failure. 
llvm-svn: 86848
 2009-11-11 17:54:02 +00:00
Chris Lattner
20da198cb6 add a note 
llvm-svn: 86847
 2009-11-11 17:51:27 +00:00
Chris Lattner
bc9996444e add a note 
llvm-svn: 86756
 2009-11-10 23:47:45 +00:00
Chris Lattner
67aac80393 I did this a week or two ago 
llvm-svn: 86754
 2009-11-10 23:40:49 +00:00
Nick Lewycky
2b3ac2b1a7 Improve tail call elimination to handle the switch statement. 
llvm-svn: 86403
 2009-11-07 21:10:15 +00:00
Chris Lattner
7f61fbfcca add a note from PR5313 
llvm-svn: 86146
 2009-11-05 18:19:19 +00:00
Bill Wendling
8f96a88125 Add new note. 
llvm-svn: 85341
 2009-10-27 23:30:07 +00:00
Bill Wendling
cb9a2f20d5 Move and clarify note. 
llvm-svn: 85334
 2009-10-27 22:48:31 +00:00
Chris Lattner
81c06b943c this is done. 
llvm-svn: 85041
 2009-10-25 06:17:51 +00:00
Chris Lattner
d1dbcae98f some stuff is done, we still have constantexpr simplification to do. 
llvm-svn: 84943
 2009-10-23 07:00:55 +00:00
Chris Lattner
2363ec8194 IPSCCP is missing stuff. 
llvm-svn: 84725
 2009-10-21 01:10:37 +00:00
Chris Lattner
d24ead5c1e add a note 
llvm-svn: 82442
 2009-09-21 06:04:07 +00:00
Chris Lattner
64e3a9984b one case handled, expanded another testcase inline. 
llvm-svn: 82427
 2009-09-21 02:53:57 +00:00