Make necessary changes to support DIV -> [SUF]Div. This changes llvm to
have three division instructions: signed, unsigned, floating point. The
bytecode and assembler are bacwards compatible, however.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@31195 91177308-0d34-0410-b5e6-96231b3b80d8
This patch implements the first increment for the Signless Types feature.
All changes pertain to removing the ConstantSInt and ConstantUInt classes
in favor of just using ConstantInt.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@31063 91177308-0d34-0410-b5e6-96231b3b80d8
SimplifyDemandedBits. The idea is that some operations can be simplified if
not all of the computed elements are needed. Some targets (like x86) have a
large number of intrinsics that operate on a single element, but pass other
elts through unmodified. If those other elements are not needed, the
intrinsics can be simplified to scalar operations, and insertelement ops can
be removed.
This turns (f.e.):
ushort %Convert_sse(float %f) {
%tmp = insertelement <4 x float> undef, float %f, uint 0 ; <<4 x float>> [#uses=1]
%tmp10 = insertelement <4 x float> %tmp, float 0.000000e+00, uint 1 ; <<4 x float>> [#uses=1]
%tmp11 = insertelement <4 x float> %tmp10, float 0.000000e+00, uint 2 ; <<4 x float>> [#uses=1]
%tmp12 = insertelement <4 x float> %tmp11, float 0.000000e+00, uint 3 ; <<4 x float>> [#uses=1]
%tmp28 = tail call <4 x float> %llvm.x86.sse.sub.ss( <4 x float> %tmp12, <4 x float> < float 1.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00 > ) ; <<4 x float>> [#uses=1]
%tmp37 = tail call <4 x float> %llvm.x86.sse.mul.ss( <4 x float> %tmp28, <4 x float> < float 5.000000e-01, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00 > ) ; <<4 x float>> [#uses=1]
%tmp48 = tail call <4 x float> %llvm.x86.sse.min.ss( <4 x float> %tmp37, <4 x float> < float 6.553500e+04, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00 > ) ; <<4 x float>> [#uses=1]
%tmp59 = tail call <4 x float> %llvm.x86.sse.max.ss( <4 x float> %tmp48, <4 x float> zeroinitializer ) ; <<4 x float>> [#uses=1]
%tmp = tail call int %llvm.x86.sse.cvttss2si( <4 x float> %tmp59 ) ; <int> [#uses=1]
%tmp69 = cast int %tmp to ushort ; <ushort> [#uses=1]
ret ushort %tmp69
}
into:
ushort %Convert_sse(float %f) {
entry:
%tmp28 = sub float %f, 1.000000e+00 ; <float> [#uses=1]
%tmp37 = mul float %tmp28, 5.000000e-01 ; <float> [#uses=1]
%tmp375 = insertelement <4 x float> undef, float %tmp37, uint 0 ; <<4 x float>> [#uses=1]
%tmp48 = tail call <4 x float> %llvm.x86.sse.min.ss( <4 x float> %tmp375, <4 x float> < float 6.553500e+04, float undef, float undef, float undef > ) ; <<4 x float>> [#uses=1]
%tmp59 = tail call <4 x float> %llvm.x86.sse.max.ss( <4 x float> %tmp48, <4 x float> < float 0.000000e+00, float undef, float undef, float undef > ) ; <<4 x float>> [#uses=1]
%tmp = tail call int %llvm.x86.sse.cvttss2si( <4 x float> %tmp59 ) ; <int> [#uses=1]
%tmp69 = cast int %tmp to ushort ; <ushort> [#uses=1]
ret ushort %tmp69
}
which improves codegen from:
_Convert_sse:
movss LCPI1_0, %xmm0
movss 4(%esp), %xmm1
subss %xmm0, %xmm1
movss LCPI1_1, %xmm0
mulss %xmm0, %xmm1
movss LCPI1_2, %xmm0
minss %xmm0, %xmm1
xorps %xmm0, %xmm0
maxss %xmm0, %xmm1
cvttss2si %xmm1, %eax
andl $65535, %eax
ret
to:
_Convert_sse:
movss 4(%esp), %xmm0
subss LCPI1_0, %xmm0
mulss LCPI1_1, %xmm0
movss LCPI1_2, %xmm1
minss %xmm1, %xmm0
xorps %xmm1, %xmm1
maxss %xmm1, %xmm0
cvttss2si %xmm0, %eax
andl $65535, %eax
ret
This is just a first step, it can be extended in many ways. Testcase here:
Transforms/InstCombine/vec_demanded_elts.ll
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@30752 91177308-0d34-0410-b5e6-96231b3b80d8
Remove the Function pointer cast in these calls, converting it to
a cast of argument.
%tmp60 = tail call int cast (int (ulong)* %str to int (int)*)( int 10 )
%tmp60 = tail call int cast (int (ulong)* %str to int (int)*)( uint %tmp51 )
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28953 91177308-0d34-0410-b5e6-96231b3b80d8
the program. This exposes more opportunities for the instcombiner, and implements
vec_shuffle.ll:test6
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28487 91177308-0d34-0410-b5e6-96231b3b80d8
When doing the initial pass of constant folding, if we get a constantexpr,
simplify the constant expr like we would do if the constant is folded in the
normal loop.
This fixes the missed-optimization regression in
Transforms/InstCombine/getelementptr.ll last night.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28224 91177308-0d34-0410-b5e6-96231b3b80d8
1. Implement InstCombine/deadcode.ll by not adding instructions in unreachable
blocks (due to constants in conditional branches/switches) to the worklist.
This causes them to be deleted before instcombine starts up, leading to
better optimization.
2. In the prepass over instructions, do trivial constprop/dce as we go. This
has the effect of improving the effectiveness of #1. In addition, it
*significantly* speeds up instcombine on test cases with large amounts of
constant folding code (for example, that produced by code specialization
or partial evaluation). In one example, it speeds up instcombine from
0.0589s to 0.0224s with a release build (a 2.6x speedup).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28215 91177308-0d34-0410-b5e6-96231b3b80d8
Make the "fold (and (cast A), (cast B)) -> (cast (and A, B))" transformation
only apply when both casts really will cause code to be generated. If one or
both doesn't, then this xform doesn't remove a cast.
This fixes Transforms/InstCombine/2006-05-06-Infloop.ll
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@28141 91177308-0d34-0410-b5e6-96231b3b80d8
Make the insert/extract elt -> shuffle code more aggressive.
This fixes CodeGen/PowerPC/vec_shuffle.ll
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27728 91177308-0d34-0410-b5e6-96231b3b80d8
aggressive in some cases where LLVMGCC 4 is inserting casts for no reason.
This implements InstCombine/cast.ll:test27/28.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27620 91177308-0d34-0410-b5e6-96231b3b80d8
%tmp = cast <4 x uint> %tmp to <4 x int> ; <<4 x int>> [#uses=1]
%tmp = cast <4 x int> %tmp to <4 x float> ; <<4 x float>> [#uses=1]
into:
%tmp = cast <4 x uint> %tmp to <4 x float> ; <<4 x float>> [#uses=1]
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27355 91177308-0d34-0410-b5e6-96231b3b80d8
%tmp = cast <4 x uint>* %testData to <4 x int>* ; <<4 x int>*> [#uses=1]
%tmp = load <4 x int>* %tmp ; <<4 x int>> [#uses=1]
to this:
%tmp = load <4 x uint>* %testData ; <<4 x uint>> [#uses=1]
%tmp = cast <4 x uint> %tmp to <4 x int> ; <<4 x int>> [#uses=1]
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@27353 91177308-0d34-0410-b5e6-96231b3b80d8
the pointer is known to come from either a global variable, alloca or
malloc. This allows us to compile this:
P = malloc(28);
memset(P, 0, 28);
into explicit stores on PPC instead of a memset call.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@26577 91177308-0d34-0410-b5e6-96231b3b80d8
Transforms/InstCombine/vec_narrow.ll. This add support for narrowing
extract_element(insertelement) also.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@26538 91177308-0d34-0410-b5e6-96231b3b80d8
Make this code more powerful by using ComputeMaskedBits instead of looking
for an AND operand. This lets us fold this:
int %test23(int %a) {
%tmp.1 = and int %a, 1
%tmp.2 = seteq int %tmp.1, 0
%tmp.3 = cast bool %tmp.2 to int ;; xor tmp1, 1
ret int %tmp.3
}
into: xor (and a, 1), 1
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@26396 91177308-0d34-0410-b5e6-96231b3b80d8
and ComputeMaskedBits to match the new improved versions in instcombine.
Tested against all of multisource/benchmarks on ppc.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@26238 91177308-0d34-0410-b5e6-96231b3b80d8
1. Teach GetConstantInType to handle boolean constants.
2. Teach instcombine to fold (compare X, CST) when X has known 0/1 bits.
Testcase here: set.ll:test22
3. Improve the "(X >> c1) & C2 == 0" folding code to allow a noop cast
between the shift and and. More aggressive bitfolding for other reasons
was turning signed shr's into unsigned shr's, leaving the noop cast in
the way.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@26131 91177308-0d34-0410-b5e6-96231b3b80d8
This allows us to simplify on conditions where bits are not known, but they
are not demanded either! This also fixes a couple of bugs in
ComputeMaskedBits that were exposed during this work.
In the future, swaths of instcombine should be removed, as this code
subsumes a bunch of ad-hockery.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@26122 91177308-0d34-0410-b5e6-96231b3b80d8
1. Teach it new tricks: in particular how to propagate through signed shr and sexts.
2. Teach it to return a bitset of known-1 and known-0 bits, instead of just zero.
3. Teach instcombine (AND X, C) to fold when we know all C bits of X.
This implements Regression/Transforms/InstCombine/bittest.ll, and allows
future things to be simplified.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@26087 91177308-0d34-0410-b5e6-96231b3b80d8
instruction onto the worklist (in case they are now dead).
Add a really trivial local DSE implementation to help out bitfield code.
We now fold this:
struct S {
unsigned char a : 1, b : 1, c : 1, d : 2, e : 3;
S();
};
S::S() : a(0), b(0), c(1), d(0), e(6) {}
to this:
void %_ZN1SC1Ev(%struct.S* %this) {
entry:
%tmp.1 = getelementptr %struct.S* %this, int 0, uint 0
store ubyte 38, ubyte* %tmp.1
ret void
}
much earlier (in gccas instead of only in gccld after DSE runs).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@26050 91177308-0d34-0410-b5e6-96231b3b80d8
is just as efficient as MVIZ and is also more general.
Fix a few minor bugs introduced in recent patches
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@26036 91177308-0d34-0410-b5e6-96231b3b80d8
mask. This allows the code to be simpler and more efficient.
Also, generalize some of the cases in MVIZ a bit, making it slightly more aggressive.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@26035 91177308-0d34-0410-b5e6-96231b3b80d8
'demanded bits', inspired by Nate's work in the dag combiner. This isn't
complete, but needs to unrelated instcombiner changes to continue.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@26033 91177308-0d34-0410-b5e6-96231b3b80d8
Turn A / (C1 << N), where C1 is "1<<C2" into A >> (N+C2) [udiv only].
Tested with: rem.ll:test5, div.ll:test10
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@26003 91177308-0d34-0410-b5e6-96231b3b80d8
the shifts.
This allows us to fold this (which is the 'integer add a constant' sequence
from cozmic's scheme compmiler):
int %x(uint %anf-temporary776) {
%anf-temporary777 = shr uint %anf-temporary776, ubyte 1
%anf-temporary800 = cast uint %anf-temporary777 to int
%anf-temporary804 = shl int %anf-temporary800, ubyte 1
%anf-temporary805 = add int %anf-temporary804, -2
%anf-temporary806 = or int %anf-temporary805, 1
ret int %anf-temporary806
}
into this:
int %x(uint %anf-temporary776) {
%anf-temporary776 = cast uint %anf-temporary776 to int
%anf-temporary776.mask1 = add int %anf-temporary776, -2
%anf-temporary805 = or int %anf-temporary776.mask1, 1
ret int %anf-temporary805
}
note that instcombine already knew how to eliminate the AND that the two
shifts fold into. This is tested by InstCombine/shift.ll:test26
-Chris
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@25128 91177308-0d34-0410-b5e6-96231b3b80d8
Add support for specifying alignment and size of setjmp jmpbufs.
No targets currently do anything with this information, nor is it presrved
in the bytecode representation. That's coming up next.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@24196 91177308-0d34-0410-b5e6-96231b3b80d8
a few times in crafty:
OLD: %tmp.36 = div int %tmp.35, 8 ; <int> [#uses=1]
NEW: %tmp.36 = div uint %tmp.35, 8 ; <uint> [#uses=0]
OLD: %tmp.19 = div int %tmp.18, 8 ; <int> [#uses=1]
NEW: %tmp.19 = div uint %tmp.18, 8 ; <uint> [#uses=0]
OLD: %tmp.117 = div int %tmp.116, 8 ; <int> [#uses=1]
NEW: %tmp.117 = div uint %tmp.116, 8 ; <uint> [#uses=0]
OLD: %tmp.92 = div int %tmp.91, 8 ; <int> [#uses=1]
NEW: %tmp.92 = div uint %tmp.91, 8 ; <uint> [#uses=0]
Which all turn into shrs.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@24190 91177308-0d34-0410-b5e6-96231b3b80d8
8 times in vortex, allowing the srems to be turned into shrs:
OLD: %tmp.104 = rem int %tmp.5.i37, 16 ; <int> [#uses=1]
NEW: %tmp.104 = rem uint %tmp.5.i37, 16 ; <uint> [#uses=0]
OLD: %tmp.98 = rem int %tmp.5.i24, 16 ; <int> [#uses=1]
NEW: %tmp.98 = rem uint %tmp.5.i24, 16 ; <uint> [#uses=0]
OLD: %tmp.91 = rem int %tmp.5.i19, 8 ; <int> [#uses=1]
NEW: %tmp.91 = rem uint %tmp.5.i19, 8 ; <uint> [#uses=0]
OLD: %tmp.88 = rem int %tmp.5.i14, 8 ; <int> [#uses=1]
NEW: %tmp.88 = rem uint %tmp.5.i14, 8 ; <uint> [#uses=0]
OLD: %tmp.85 = rem int %tmp.5.i9, 1024 ; <int> [#uses=2]
NEW: %tmp.85 = rem uint %tmp.5.i9, 1024 ; <uint> [#uses=0]
OLD: %tmp.82 = rem int %tmp.5.i, 512 ; <int> [#uses=2]
NEW: %tmp.82 = rem uint %tmp.5.i1, 512 ; <uint> [#uses=0]
OLD: %tmp.48.i = rem int %tmp.5.i.i161, 4 ; <int> [#uses=1]
NEW: %tmp.48.i = rem uint %tmp.5.i.i161, 4 ; <uint> [#uses=0]
OLD: %tmp.20.i2 = rem int %tmp.5.i.i, 4 ; <int> [#uses=1]
NEW: %tmp.20.i2 = rem uint %tmp.5.i.i, 4 ; <uint> [#uses=0]
it also occurs 9 times in gcc, but with odd constant divisors (1009 and 61)
so the payoff isn't as great.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@24189 91177308-0d34-0410-b5e6-96231b3b80d8
one use (but one is a cast). This handles the very common case of:
X = alloc [n x byte]
Y = cast X to somethingbetter
seteq X, null
In order to avoid infinite looping when there are multiple casts, we only
allow this if the xform is strictly increasing the alignment of the
allocation.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23961 91177308-0d34-0410-b5e6-96231b3b80d8
where the second has less alignment required. If we had explicit alignment
support in the IR, we could handle this case, but we can't until we do.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23960 91177308-0d34-0410-b5e6-96231b3b80d8
This is useful for 178.galgel where resolution of dope vectors (by the
optimizer) causes the scales to become apparent.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23328 91177308-0d34-0410-b5e6-96231b3b80d8
if () { store A -> P; } else { store B -> P; }
into a PHI node with one store, in the most trival case. This implements
load.ll:test10.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23324 91177308-0d34-0410-b5e6-96231b3b80d8
load are exactly consequtive. This is picked up by other passes, but this
triggers thousands of times in fortran programs that use static locals
(and is thus a compile-time speedup).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23320 91177308-0d34-0410-b5e6-96231b3b80d8
BasicBlock's removePredecessor routine. This requires shuffling around
the definition and implementation of hasContantValue from Utils.h,cpp into
Instructions.h,cpp
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22664 91177308-0d34-0410-b5e6-96231b3b80d8
Because the instcombine has to scan the entire function when it starts up
to begin with, we might as well do it in DFO so we can nuke unreachable code.
This fixes: Transforms/InstCombine/2005-07-07-DeadPHILoop.ll
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22348 91177308-0d34-0410-b5e6-96231b3b80d8
It is actually always true. This fixes PR586 and
Transforms/InstCombine/2005-06-16-SetCCOrSetCCMiscompile.ll
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22236 91177308-0d34-0410-b5e6-96231b3b80d8
in. This tends to get cases like this:
X = cast ubyte to int
Y = shr int X, ...
Tested by: shift.ll:test24
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@21775 91177308-0d34-0410-b5e6-96231b3b80d8
the result, turn signed shift rights into unsigned shift rights if possible.
This leads to later simplification and happens *often* in 176.gcc. For example,
this testcase:
struct xxx { unsigned int code : 8; };
enum codes { A, B, C, D, E, F };
int foo(struct xxx *P) {
if ((enum codes)P->code == A)
bar();
}
used to be compiled to:
int %foo(%struct.xxx* %P) {
%tmp.1 = getelementptr %struct.xxx* %P, int 0, uint 0 ; <uint*> [#uses=1]
%tmp.2 = load uint* %tmp.1 ; <uint> [#uses=1]
%tmp.3 = cast uint %tmp.2 to int ; <int> [#uses=1]
%tmp.4 = shl int %tmp.3, ubyte 24 ; <int> [#uses=1]
%tmp.5 = shr int %tmp.4, ubyte 24 ; <int> [#uses=1]
%tmp.6 = cast int %tmp.5 to sbyte ; <sbyte> [#uses=1]
%tmp.8 = seteq sbyte %tmp.6, 0 ; <bool> [#uses=1]
br bool %tmp.8, label %then, label %UnifiedReturnBlock
Now it is compiled to:
%tmp.1 = getelementptr %struct.xxx* %P, int 0, uint 0 ; <uint*> [#uses=1]
%tmp.2 = load uint* %tmp.1 ; <uint> [#uses=1]
%tmp.2 = cast uint %tmp.2 to sbyte ; <sbyte> [#uses=1]
%tmp.8 = seteq sbyte %tmp.2, 0 ; <bool> [#uses=1]
br bool %tmp.8, label %then, label %UnifiedReturnBlock
which is the difference between this:
foo:
subl $4, %esp
movl 8(%esp), %eax
movl (%eax), %eax
shll $24, %eax
sarl $24, %eax
testb %al, %al
jne .LBBfoo_2
and this:
foo:
subl $4, %esp
movl 8(%esp), %eax
movl (%eax), %eax
testb %al, %al
jne .LBBfoo_2
This occurs 3243 times total in the External tests, 215x in povray,
6x in each f2c'd program, 1451x in 176.gcc, 7x in crafty, 20x in perl,
25x in gap, 3x in m88ksim, 25x in ijpeg.
Maybe this will cause a little jump on gcc tommorow :)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@21715 91177308-0d34-0410-b5e6-96231b3b80d8
This implements set.ll:test20.
This triggers 2x on povray, 9x on mesa, 11x on gcc, 2x on crafty, 1x on eon,
6x on perlbmk and 11x on m88ksim.
It allows us to compile these two functions into the same code:
struct s { unsigned int bit : 1; };
unsigned foo(struct s *p) {
if (p->bit)
return 1;
else
return 0;
}
unsigned bar(struct s *p) { return p->bit; }
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@21690 91177308-0d34-0410-b5e6-96231b3b80d8
