This case returns the value in ST(0) and then has to convert it to an SSE
register. This causes significant codegen ugliness in some cases. For
example in the trivial fp-stack-direct-ret.ll testcase we used to generate:
_bar:
subl $28, %esp
call L_foo$stub
fstpl 16(%esp)
movsd 16(%esp), %xmm0
movsd %xmm0, 8(%esp)
fldl 8(%esp)
addl $28, %esp
ret
because we move the result of foo() into an XMM register, then have to
move it back for the return of bar.
Instead of hacking ever-more special cases into the call result lowering code
we take a much simpler approach: on x86-32, fp return is modeled as always
returning into an f80 register which is then truncated to f32 or f64 as needed.
Similarly for a result, we model it as an extension to f80 + return.
This exposes the truncate and extensions to the dag combiner, allowing target
independent code to hack on them, eliminating them in this case. This gives
us this code for the example above:
_bar:
subl $12, %esp
call L_foo$stub
addl $12, %esp
ret
The nasty aspect of this is that these conversions are not legal, but we want
the second pass of dag combiner (post-legalize) to be able to hack on them.
To handle this, we lie to legalize and say they are legal, then custom expand
them on entry to the isel pass (PreprocessForFPConvert). This is gross, but
less gross than the code it is replacing :)
This also allows us to generate better code in several other cases. For
example on fp-stack-ret-conv.ll, we now generate:
_test:
subl $12, %esp
call L_foo$stub
fstps 8(%esp)
movl 16(%esp), %eax
cvtss2sd 8(%esp), %xmm0
movsd %xmm0, (%eax)
addl $12, %esp
ret
where before we produced (incidentally, the old bad code is identical to what
gcc produces):
_test:
subl $12, %esp
call L_foo$stub
fstpl (%esp)
cvtsd2ss (%esp), %xmm0
cvtss2sd %xmm0, %xmm0
movl 16(%esp), %eax
movsd %xmm0, (%eax)
addl $12, %esp
ret
Note that we generate slightly worse code on pr1505b.ll due to a scheduling
deficiency that is unrelated to this patch.
llvm-svn: 46307
Fixed CellSPU's A-form (local store) address mode, so that all globals,
externals, constant pool and jump table symbols are now wrapped within
a SPUISD::AFormAddr pseudo-instruction. This now identifies all local
store memory addresses, although it requires a bit of legerdemain during
instruction selection to properly select loads to and stores from local
store, properly generating "LQA" instructions.
Also added mul_ops.ll test harness for exercising integer multiplication.
llvm-svn: 46142
1. Legalize now always promotes truncstore of i1 to i8.
2. Remove patterns and gunk related to truncstore i1 from targets.
3. Rename the StoreXAction stuff to TruncStoreAction in TLI.
4. Make the TLI TruncStoreAction table a 2d table to handle from/to conversions.
5. Mark a wide variety of invalid truncstores as such in various targets, e.g.
X86 currently doesn't support truncstore of any of its integer types.
6. Add legalize support for truncstores with invalid value input types.
7. Add a dag combine transform to turn store(truncate) into truncstore when
safe.
The later allows us to compile CodeGen/X86/storetrunc-fp.ll to:
_foo:
fldt 20(%esp)
fldt 4(%esp)
faddp %st(1)
movl 36(%esp), %eax
fstps (%eax)
ret
instead of:
_foo:
subl $4, %esp
fldt 24(%esp)
fldt 8(%esp)
faddp %st(1)
fstps (%esp)
movl 40(%esp), %eax
movss (%esp), %xmm0
movss %xmm0, (%eax)
addl $4, %esp
ret
llvm-svn: 46140
and the spill is its kill. However, if the local allocator has determined the
register has not been modified (possible when its value was reloaded), it would
not issue a restore. In that case, mark the last use of the virtual register as
kill.
llvm-svn: 46111
It's not safe to use the two value CombineTo variant to combine away a dead load.
e.g.
v1, chain2 = load chain1, loc
v2, chain3 = load chain2, loc
v3 = add v2, c
Now we replace use of v1 with undef, use of chain2 with chain1.
ReplaceAllUsesWith() will iterate through uses of the first load and update operands:
v1, chain2 = load chain1, loc
v2, chain3 = load chain1, loc
v3 = add v2, c
Now the second load is the same as the first load, SelectionDAG cse will ensure
the use of second load is replaced with the first load.
v1, chain2 = load chain1, loc
v3 = add v1, c
Then v1 is replaced with undef and bad things happen.
llvm-svn: 46099
it should work, but I have no machine to test
it on. Committed because it will at least
cause no harm, and maybe someone can test it
for me!
llvm-svn: 46098
make the 'fp return in ST(0)' optimization smart enough to
look through token factor nodes. THis allows us to compile
testcases like CodeGen/X86/fp-stack-retcopy.ll into:
_carg:
subl $12, %esp
call L_foo$stub
fstpl (%esp)
fldl (%esp)
addl $12, %esp
ret
instead of:
_carg:
subl $28, %esp
call L_foo$stub
fstpl 16(%esp)
movsd 16(%esp), %xmm0
movsd %xmm0, 8(%esp)
fldl 8(%esp)
addl $28, %esp
ret
Still not optimal, but much better and this is a trivial patch. Fixing
the rest requires invasive surgery that is is not llvm 2.2 material.
llvm-svn: 46054
- struct_2.ll: Completely unaligned load/store testing
- call_indirect.ll, struct_1.ll: Add test lines to exercise
X-form [$reg($reg)] addressing
At this point, loads and stores should be under control (he says
in an optimistic tone of voice.)
llvm-svn: 45882
- Cleaned up custom load/store logic, common code is now shared [see note
below], cleaned up address modes
- More test cases: various intrinsics, structure element access (load/store
test), updated target data strings, indirect function calls.
Note: This patch contains a refactoring of the LoadSDNode and StoreSDNode
structures: they now share a common base class, LSBaseSDNode, that
provides an interface to their common functionality. There is some hackery
to access the proper operand depending on the derived class; otherwise,
to do a proper job would require finding and rearranging the SDOperands
sent to StoreSDNode's constructor. The current refactor errs on the
side of being conservatively and backwardly compatible while providing
functionality that reduces redundant code for targets where loads and
stores are custom-lowered.
llvm-svn: 45851
Likewise fix up a bunch of other libcalls. While
there I remove NEG_F32 and NEG_F64 since they are
not used anywhere. This fixes 9 Ada ACATS failures.
llvm-svn: 45833
the code generated is not wonderful. This turns a miscompilation into
a code quality bug (noted in the ppc readme). This fixes PR642, which
is over 2 years old (!). Nate, please review this.
llvm-svn: 45742
values, which means doing extra legalization work.
It would be easier to get this kind of thing right if
there was some documentation...
llvm-svn: 45472
eliminating the llvm.x86.sse2.loadl.pd intrinsic?), one shuffle optzn
may be done (if shufps is better than pinsw, Evan, please review), and
we already know about LICM of simple instructions.
llvm-svn: 45407
define void @f() {
...
call i32 @g()
...
}
define void @g() {
...
}
The hazards are:
- @f and @g have GC, but they differ GC. Inlining is invalid. This
may never occur.
- @f has no GC, but @g does. g's GC must be propagated to @f.
The other scenarios are safe:
- @f and @g have the same GC.
- @f and @g have no GC.
- @g has no GC.
This patch adds inliner checks for the former two scenarios.
llvm-svn: 45351
SelectionDAG::getConstant, in the same way as vector floating-point
constants. This allows the legalize expansion code for @llvm.ctpop and
friends to be usable with vector types.
llvm-svn: 44954
possible before resorting to pextrw and pinsrw.
- Better codegen for v4i32 shuffles masquerading as v8i16 or v16i8 shuffles.
- Improves (i16 extract_vector_element 0) codegen by recognizing
(i32 extract_vector_element 0) does not require a pextrw.
llvm-svn: 44836
methods are new to Function:
bool hasCollector() const;
const std::string &getCollector() const;
void setCollector(const std::string &);
void clearCollector();
The assembly representation is as such:
define void @f() gc "shadow-stack" { ...
The implementation uses an on-the-side table to map Functions to
collector names, such that there is no overhead. A StringPool is
further used to unique collector names, which are extremely
likely to be unique per process.
llvm-svn: 44769
_foo:
movl $12, %eax
andl 4(%esp), %eax
movl _array(%eax), %eax
ret
instead of:
_foo:
movl 4(%esp), %eax
shrl $2, %eax
andl $3, %eax
movl _array(,%eax,4), %eax
ret
As it turns out, this triggers all the time, in a wide variety of
situations, for example, I see diffs like this in various programs:
- movl 8(%eax), %eax
- shll $2, %eax
- andl $1020, %eax
- movl (%esi,%eax), %eax
+ movzbl 8(%eax), %eax
+ movl (%esi,%eax,4), %eax
- shll $2, %edx
- andl $1020, %edx
- movl (%edi,%edx), %edx
+ andl $255, %edx
+ movl (%edi,%edx,4), %edx
Unfortunately, I also see stuff like this, which can be fixed in the
X86 backend:
- andl $85, %ebx
- addl _bit_count(,%ebx,4), %ebp
+ shll $2, %ebx
+ andl $340, %ebx
+ addl _bit_count(%ebx), %ebp
llvm-svn: 44656
optimized. This avoids creating illegal divisions when the combiner is
running after legalize; this fixes PR1815. Also, it produces better
code in the included testcase by avoiding the subtract and multiply
when the division isn't optimized.
llvm-svn: 44341
sometimes emit "zero" and "all one" vectors multiple times,
for example:
_test2:
pcmpeqd %mm0, %mm0
movq %mm0, _M1
pcmpeqd %mm0, %mm0
movq %mm0, _M2
ret
instead of:
_test2:
pcmpeqd %mm0, %mm0
movq %mm0, _M1
movq %mm0, _M2
ret
This patch fixes this by always arranging for zero/one vectors
to be defined as v4i32 or v2i32 (SSE/MMX) instead of letting them be
any random type. This ensures they get trivially CSE'd on the dag.
This fix is also important for LegalizeDAGTypes, as it gets unhappy
when the x86 backend wants BUILD_VECTOR(i64 0) to be legal even when
'i64' isn't legal.
This patch makes the following changes:
1) X86TargetLowering::LowerBUILD_VECTOR now lowers 0/1 vectors into
their canonical types.
2) The now-dead patterns are removed from the SSE/MMX .td files.
3) All the patterns in the .td file that referred to immAllOnesV or
immAllZerosV in the wrong form now use *_bc to match them with a
bitcast wrapped around them.
4) X86DAGToDAGISel::SelectScalarSSELoad is generalized to handle
bitcast'd zero vectors, which simplifies the code actually.
5) getShuffleVectorZeroOrUndef is updated to generate a shuffle that
is legal, instead of generating one that is illegal and expecting
a later legalize pass to clean it up.
6) isZeroShuffle is generalized to handle bitcast of zeros.
7) several other minor tweaks.
This patch is definite goodness, but has the potential to cause random
code quality regressions. Please be on the lookout for these and let
me know if they happen.
llvm-svn: 44310
node A gets back into the DAG again because it was hiding in
one of the node maps: make sure that node replacement happens
in those maps too.
llvm-svn: 44263
can be eliminated by the allocator is the destination and source targets the
same register. The most common case is when the source and destination registers
are in different class. For example, on x86 mov32to32_ targets GR32_ which
contains a subset of the registers in GR32.
The allocator can do 2 things:
1. Set the preferred allocation for the destination of a copy to that of its source.
2. After allocation is done, change the allocation of a copy destination (if
legal) so the copy can be eliminated.
This eliminates 443 extra moves from 403.gcc.
llvm-svn: 43662
transformation. Previously, it's restricted by ensuring the number of load uses
is one. Now the restriction is loosened up by allowing setcc uses to be
"extended" (e.g. setcc x, c, eq -> setcc sext(x), sext(c), eq).
llvm-svn: 43465
FE.
- Explicitly pass in the alignment of the load & store.
- XFAIL 2007-10-23-UnalignedMemcpy.ll because llc has a bug that crashes on
unaligned pointers.
llvm-svn: 43398
and the compaison is against a constant value, try eliminate the stride
by moving the compare instruction to another stride and change its
constant operand accordingly. e.g.
loop:
...
v1 = v1 + 3
v2 = v2 + 1
if (v2 < 10) goto loop
=>
loop:
...
v1 = v1 + 3
if (v1 < 30) goto loop
llvm-svn: 43336
- Avoid attempting stride-reuse in the case that there are users that
aren't addresses. In that case, there will be places where the
multiplications won't be folded away, so it's better to try to
strength-reduce them.
- Several SSE intrinsics have operands that strength-reduction can
treat as addresses. The previous item makes this more visible, as
any non-address use of an IV can inhibit stride-reuse.
- Make ValidStride aware of whether there's likely to be a base
register in the address computation. This prevents it from thinking
that things like stride 9 are valid on x86 when the base register is
already occupied.
Also, XFAIL the 2007-08-10-LEA16Use32.ll test; the new logic to avoid
stride-reuse elimintes the LEA in the loop, so the test is no longer
testing what it was intended to test.
llvm-svn: 43231
To do this it is necessary to add a "always inline" argument to the
memcpy node. For completeness I have also added this node to memmove
and memset. I have also added getMem* functions, because the extra
argument makes it cumbersome to use getNode and because I get confused
by it :-)
llvm-svn: 43172
enabled by passing -tailcallopt to llc. The optimization is
performed if the following conditions are satisfied:
* caller/callee are fastcc
* elf/pic is disabled OR
elf/pic enabled + callee is in module + callee has
visibility protected or hidden
llvm-svn: 42870
basic arithmetic works.
Rename RTLIB long double functions to distinguish
different flavors of long double; the lib functions
have different names, alas.
llvm-svn: 42644
The only generated code difference is that now we call memcpy when
the size of the array is unknown. This matches GCC behavior and is
better since the run time value can be arbitrarily large.
llvm-svn: 42433
both results with a single div or idiv instruction. This uses new X86ISD
nodes for DIV and IDIV which are introduced during the legalize phase
so that the SelectionDAG's CSE can automatically eliminate redundant
computations.
llvm-svn: 42308
LLVM now enforces the following prototypes for the write barriers:
<ty>* @llvm.gcread(<ty2>*, <ty>**)
void @llvm.gcwrite(<ty>*, <ty2>*, <ty>**)
And for @llvm.gcroot, the first stack slot is verified to be an alloca or a
bitcast of an alloca.
Fixes test/CodeGen/Generic/GC/lower_gcroot.ll, which violated these.
llvm-svn: 42051
Coping 100MB array (after a warmup) shows that glibc 2.6.1 implementation on
x86-64 (core 2) is 30% faster (from 0.270917s to 0.188079s)
llvm-svn: 41479
see if the base register is already occupied before assuming it can be
used. This fixes bogus code generation in the accompanying testcase.
llvm-svn: 41049