by non-CMP expressions. The executable test case (129821) would test
this as well, if we had an "-O0 -disable-arm-fast-isel" LLVM-GCC
tester. Alas, the ARM assembly would be very difficult to check with
FileCheck.
The thumb2-cbnz.ll test is affected; it generates larger code (tst.w
vs. cmp #0), but I believe the new version is correct.
rdar://problem/9298790
llvm-svn: 131261
If there is a store after the load node, then there is a chain, which means
that there is another user. Thus, asking hasOneUser would fail. Instead we
ask hasNUsesOfValue on the 'data' value.
llvm-svn: 131183
at the start of basic blocks to their common predecessor. It's actually quite
common (e.g. about 50 times in JM/lencod) and has shown to be a nice code size
benefit. e.g.
pushq %rax
testl %edi, %edi
jne LBB0_2
## BB#1:
xorb %al, %al
popq %rdx
ret
LBB0_2:
xorb %al, %al
callq _foo
popq %rdx
ret
=>
pushq %rax
xorb %al, %al
testl %edi, %edi
je LBB0_2
## BB#1:
callq _foo
LBB0_2:
popq %rdx
ret
rdar://9145558
llvm-svn: 131172
this clang will use .debug_frame in, for example,
clang -g -c -m32 test.c
This matches gcc's behaviour. It looks like .debug_frame is a bit bigger
than .eh_frame, but has the big advantage of not being allocated.
llvm-svn: 131140
often expressed as "x >= y ? x : y", there is a good chance we can extract
the existing "x >= y" from it and use that as a replacement for "max(x,y)==x".
llvm-svn: 131049
This can't be just an assertion, users can always write impossible inline
assembly. Such an assembly statement should be included in the error message.
llvm-svn: 131024
Most of these tests require a single mov instruction that can come either before
or after a 2-addr instruction. -join-physregs changes the behavior, but the
results are equivalent.
llvm-svn: 130891
landing pad as its successor.
SjLj exception handling jumps to the correct landing pad via a switch statement
that's generated right before code-gen. Loosen the constraint in the machine
instruction verifier to allow for this. Note, this isn't the most rigorous check
since we cannot determine where that switch statement came from. But it's
marginally better than turning this check off when SjLj exceptions are used.
<rdar://problem/9187612>
llvm-svn: 130881
Original message:
Teach MachineCSE how to do simple cross-block CSE involving physregs. This allows, for example, eliminating duplicate cmpl's on x86. Part of rdar://problem/8259436 .
llvm-svn: 130877
These tests all follow the same pattern:
mov r2, r0
movs r0, #0
$CMP r2, r1
it eq
moveq r0, #1
bx lr
The first 'mov' can be eliminated by rematerializing 'movs r0, #0' below the
test instruction:
$CMP r0, r1
mov.w r0, #0
it eq
moveq r0, #1
bx lr
So far, only physreg coalescing can do that. The register allocators won't yet
split live ranges just to eliminate copies. They can learn, but this particular
problem is not likely to show up in real code. It only appears because r0 is
used for both the function argument and return value.
llvm-svn: 130858
it is both inefficient and unexpected by dwarfdump. Change to
a DW_FORM_data4.
While in here, change the predicate name to reflect that the position
is not really absolute (it is an offset), just that the linker needs a
relocation.
llvm-svn: 130846
but according to my super-optimizer there are only two missed simplifications
of -instsimplify kind when compiling bzip2, and this is one of them. It amuses
me to have bzip2 be perfectly optimized as far as instsimplify goes!
llvm-svn: 130840
max(a,b) >= a -> true. According to my super-optimizer, these are
by far the most common simplifications (of the -instsimplify kind)
that occur in the testsuite and aren't caught by -std-compile-opts.
llvm-svn: 130780
model constants which can be added to base registers via add-immediate
instructions which don't require an additional register to materialize
the immediate.
llvm-svn: 130743
Currently the output should be almost identical to the one produced by CodeGen
to make the transition easier.
The only two differences I know of are:
* Some files get an extra advance loc of size 0. This will be fixed when
relaxations are enabled.
* The optimization of declaring an EH symbol as an external variable is not
implemented. This is a subset of adding the nounwind attribute, so we if really
this at -O0 we should probably do it at the IL level.
llvm-svn: 130623
This obviously helps a lot if the division would be turned into a libcall
(think i64 udiv on i386), but div is also one of the few remaining instructions
on modern CPUs that become more expensive when the bitwidth gets bigger.
This also helps register pressure on i386 when dividing chars, divb needs
two 8-bit parts of a 16 bit register as input where divl uses two registers.
int foo(unsigned char a) { return a/10; }
int bar(unsigned char a, unsigned char b) { return a/b; }
compiles into (x86_64)
_foo:
imull $205, %edi, %eax
shrl $11, %eax
ret
_bar:
movzbl %dil, %eax
divb %sil, %al
movzbl %al, %eax
ret
llvm-svn: 130615
a nice and tidy:
%x1 = load i32* %0, align 4
%1 = icmp eq i32 %x1, 1179403647
br i1 %1, label %if.then, label %if.end
instead of doing lots of loads and branches. May the FreeBSD bootloader
long fit in its allocated space.
llvm-svn: 130416
wider load would allow elimination of subsequent loads, and when the wider
load is still a native integer type. This eliminates a ton of loads on
various benchmarks involving struct fields, though it is somewhat hobbled
by clang not being very aggressive about field alignment.
This is yet another step along the way towards resolving PR6627.
llvm-svn: 130390
Modified LinearFunctionTestReplace to push the condition on the dead
list instead of eagerly deleting it. This can cause unnecessary
IV rewrites, which should have no effect on codegen and will not be an
issue once we stop generating canonical IVs.
llvm-svn: 130340
successors) and use inverse depth first search to traverse the BBs. However
that doesn't work when the CFG has infinite loops. Simply do a linear
traversal of all BBs work just fine.
rdar://9344645
llvm-svn: 130324
only check arguments with pointer types. Update the documentation
of IntrReadArgMem reflect this.
While here, add support for TBAA tags on intrinsic calls.
llvm-svn: 130317
more callee-saved registers and introduce copies. Only allows it if scheduling
a node above calls would end up lessen register pressure.
Call operands also has added ABI restrictions for register allocation, so be
extra careful with hoisting them above calls.
rdar://9329627
llvm-svn: 130245
1. Only run the early (in the module pass pipe) instcombine/simplifycfg
if the "unit at a time" passes they are cleaning up after runs.
2. Move the "clean up after the unroller" pass to the very end of the
function-level pass pipeline. Loop unroll uses instsimplify now,
so it doesn't create a ton of trash. Moving instcombine later allows
it to clean up after opportunities are exposed by GVN, DSE, etc.
3. Introduce some phase ordering tests for things that are specifically
intended to be simplified by the full optimizer as a whole.
This resolves PR2338, and is progress towards PR6627, which will be
generating code that looks similar to test2.
llvm-svn: 130241
when X has multiple uses. This is useful for exposing secondary optimizations,
but the X86 backend isn't ready for this when X has a single use. For example,
this can disable load folding.
This is inching towards resolving PR6627.
llvm-svn: 130238
return it as a clobber. This allows GVN to do smart things.
Enhance GVN to be smart about the case when a small load is clobbered
by a larger overlapping load. In this case, forward the value. This
allows us to compile stuff like this:
int test(void *P) {
int tmp = *(unsigned int*)P;
return tmp+*((unsigned char*)P+1);
}
into:
_test: ## @test
movl (%rdi), %ecx
movzbl %ch, %eax
addl %ecx, %eax
ret
which has one load. We already handled the case where the smaller
load was from a must-aliased base pointer.
llvm-svn: 130180
Fixes Thumb2 ADCS and SBCS lowering: <rdar://problem/9275821>.
t2ADCS/t2SBCS are now pseudo instructions, consistent with ARM, so the
assembly printer correctly prints the 's' suffix.
Fixes Thumb2 adde -> SBC matching to check for live/dead carry flags.
Fixes the internal ARM machine opcode mnemonic for ADCS/SBCS.
Fixes ARM SBC lowering to check for live carry (potential bug).
llvm-svn: 130048
fix bugs exposed by the gcc dejagnu testsuite:
1. The load may actually be used by a dead instruction, which
would cause an assert.
2. The load may not be used by the current chain of instructions,
and we could move it past a side-effecting instruction. Change
how we process uses to define the problem away.
llvm-svn: 130018
On x86 this allows to fold a load into the cmp, greatly reducing register pressure.
movzbl (%rdi), %eax
cmpl $47, %eax
->
cmpb $47, (%rdi)
This shaves 8k off gcc.o on i386. I'll leave applying the patch in README.txt to Chris :)
llvm-svn: 130005
This tends to happen a lot with bitfield code generated by clang. A simple example for x86_64 is
uint64_t foo(uint64_t x) { return (x&1) << 42; }
which used to compile into bloated code:
shlq $42, %rdi ## encoding: [0x48,0xc1,0xe7,0x2a]
movabsq $4398046511104, %rax ## encoding: [0x48,0xb8,0x00,0x00,0x00,0x00,0x00,0x04,0x00,0x00]
andq %rdi, %rax ## encoding: [0x48,0x21,0xf8]
ret ## encoding: [0xc3]
with this patch we can fold the immediate into the and:
andq $1, %rdi ## encoding: [0x48,0x83,0xe7,0x01]
movq %rdi, %rax ## encoding: [0x48,0x89,0xf8]
shlq $42, %rax ## encoding: [0x48,0xc1,0xe0,0x2a]
ret ## encoding: [0xc3]
It's possible to save another byte by using 'andl' instead of 'andq' but I currently see no way of doing
that without making this code even more complicated. See the TODOs in the code.
llvm-svn: 129990
add <rd>, sp, #<imm8>
ldr <rd>, [sp, #<imm8>]
When the offset from sp is multiple of 4 and in range of 0-1020.
This saves code size by utilizing 16-bit instructions.
rdar://9321541
llvm-svn: 129971
This patch depends on the prior fix r129908 that changes to use std::find,
rather than std::binary_search, on unordered array.
Patch by Dan Bailey
llvm-svn: 129909
used by Clang. To help Clang integration, the PTX target has been split
into two targets: ptx32 and ptx64, depending on the desired pointer size.
- Add GCCBuiltin class to all intrinsics
- Split PTX target into ptx32 and ptx64
llvm-svn: 129851
manually and pass all (now) 4 arguments to the mul libcall. Add a new
ExpandLibCall for just this (copied gratuitously from type legalization).
Fixes rdar://9292577
llvm-svn: 129842
- As before, there is a minor semantic change here (evidenced by the test
change) for Darwin triples that have no version component. I debated changing
the default behavior of isOSVersionLT, but decided it made more sense for
triples to be explicit.
llvm-svn: 129805
- There is a minor semantic change here (evidenced by the test change) for
Darwin triples that have no version component. I debated changing the default
behavior of isOSVersionLT, but decided it made more sense for triples to be
explicit.
llvm-svn: 129802
Making use of VFP / NEON floating point multiply-accumulate / subtraction is
difficult on current ARM implementations for a few reasons.
1. Even though a single vmla has latency that is one cycle shorter than a pair
of vmul + vadd, a RAW hazard during the first (4? on Cortex-a8) can cause
additional pipeline stall. So it's frequently better to single codegen
vmul + vadd.
2. A vmla folowed by a vmul, vmadd, or vsub causes the second fp instruction to
stall for 4 cycles. We need to schedule them apart.
3. A vmla followed vmla is a special case. Obvious issuing back to back RAW
vmla + vmla is very bad. But this isn't ideal either:
vmul
vadd
vmla
Instead, we want to expand the second vmla:
vmla
vmul
vadd
Even with the 4 cycle vmul stall, the second sequence is still 2 cycles
faster.
Up to now, isel simply avoid codegen'ing fp vmla / vmls. This works well enough
but it isn't the optimial solution. This patch attempts to make it possible to
use vmla / vmls in cases where it is profitable.
A. Add missing isel predicates which cause vmla to be codegen'ed.
B. Make sure the fmul in (fadd (fmul)) has a single use. We don't want to
compute a fmul and a fmla.
C. Add additional isel checks for vmla, avoid cases where vmla is feeding into
fp instructions (except for the #3 exceptional case).
D. Add ARM hazard recognizer to model the vmla / vmls hazards.
E. Add a special pre-regalloc case to expand vmla / vmls when it's likely the
vmla / vmls will trigger one of the special hazards.
Enable these fp vmlx codegen changes for Cortex-A9.
llvm-svn: 129775
Add a avoidWriteAfterWrite() target hook to identify register classes that
suffer from write-after-write hazards. For those register classes, try to avoid
writing the same register in two consecutive instructions.
This is currently disabled by default. We should not spill to avoid hazards!
The command line flag -avoid-waw-hazard can be used to enable waw avoidance.
llvm-svn: 129772
when they are a truncate from something else. This eliminates fully half of all the
fastisel rejections on a test c++ file I'm working with, which should make a substantial
improvement for -O0 compile of c++ code.
This fixed rdar://9297003 - fast isel bails out on all functions taking bools
llvm-svn: 129752
Before we would bail out on i1 arguments all together, now we just bail on
non-constant ones. Also, we used to emit extraneous code. e.g. test12 was:
movb $0, %al
movzbl %al, %edi
callq _test12
and test13 was:
movb $0, %al
xorl %edi, %edi
movb %al, 7(%rsp)
callq _test13f
Now we get:
movl $0, %edi
callq _test12
and:
movl $0, %edi
callq _test13f
llvm-svn: 129751
registers for fast allocation a different way. This has us updating
used registers only when we're using that exact register.
Fixes rdar://9207598
llvm-svn: 129711
value constraints on them (when defined as ImmLeaf's). This is particularly important
for X86-64, where almost all reg/imm instructions take a i64immSExt32 immediate operand,
which has a value constraint. Before this patch we ended up iseling the examples into
such amazing code as:
movabsq $7, %rax
imulq %rax, %rdi
movq %rdi, %rax
ret
now we produce:
imulq $7, %rdi, %rax
ret
This dramatically shrinks the generated code at -O0 on x86-64.
llvm-svn: 129691
2. implement rdar://9289501 - fast isel should fold trivial multiplies to shifts
3. teach tblgen to handle shift immediates that are different sizes than the
shifted operands, eliminating some code from the X86 fast isel backend.
4. Have FastISel::SelectBinaryOp use (the poorly named) FastEmit_ri_ function
instead of FastEmit_ri to simplify code.
llvm-svn: 129666
when we have a global variable base an an index. Instead, just give up on
folding the global variable.
Before we'd geenrate:
_test: ## @test
## BB#0:
movq _rtx_length@GOTPCREL(%rip), %rax
leaq (%rax), %rax
addq %rdi, %rax
movzbl (%rax), %eax
ret
now we generate:
_test: ## @test
## BB#0:
movq _rtx_length@GOTPCREL(%rip), %rax
movzbl (%rax,%rdi), %eax
ret
The difference is even more significant when there is a scale
involved.
This fixes rdar://9289558 - total fail with addr mode formation at -O0/x86-64
llvm-svn: 129664
less trivial things) into a dummy lea. Before we generated:
_test: ## @test
movq _G@GOTPCREL(%rip), %rax
leaq (%rax), %rax
ret
now we produce:
_test: ## @test
movq _G@GOTPCREL(%rip), %rax
ret
This is part of rdar://9289558
llvm-svn: 129662
The basic issue here is that bottom-up isel is matching the branch
and compare, and was failing to fold the load into the branch/compare
combo. Fixing this (by allowing folding into any instruction of a
sequence that is selected) allows us to produce things like:
cmpb $0, 52(%rax)
je LBB4_2
instead of:
movb 52(%rax), %cl
cmpb $0, %cl
je LBB4_2
This makes the generated -O0 code run a bit faster, but also speeds up
compile time by putting less pressure on the register allocator and
generating less code.
This was one of the biggest classes of missing load folding. Implementing
this shrinks 176.gcc's c-decl.s (as a random example) by about 4% in (verbose-asm)
line count.
llvm-svn: 129656
Change ELF systems to use CFI for producing the EH tables. This reduces the
size of the clang binary in Debug builds from 690MB to 679MB.
llvm-svn: 129571
This is done by pushing physical register definitions close to their
use, which happens to handle flag definitions if they're not glued to
the branch. This seems to be generally a good thing though, so I
didn't need to add a target hook yet.
The primary motivation is to generate code closer to what people
expect and rule out missed opportunity from enabling macro-op
fusion. As a side benefit, we get several 2-5% gains on x86
benchmarks. There is one regression:
SingleSource/Benchmarks/Shootout/lists slows down be -10%. But this is
an independent scheduler bug that will be tracked separately.
See rdar://problem/9283108.
Incidentally, pre-RA scheduling is only half the solution. Fixing the
later passes is tracked by:
<rdar://problem/8932804> [pre-RA-sched] on x86, attempt to schedule CMP/TEST adjacent with condition jump
Fixes:
<rdar://problem/9262453> Scheduler unnecessary break of cmp/jump fusion
llvm-svn: 129508
the same allocation size but different primitive sizes(e.g., <3xi32> and
<4xi32>). When ScalarRepl promotes them, it can't use a bit cast but
should use a shuffle vector instead.
llvm-svn: 129472
ignored. There was a test to catch this, but it was just blindly updated in
a large change. This fixes another part of <rdar://problem/9275290>.
llvm-svn: 129466
the max itself, so it is not easy to write a test case for this, but I added a
test case that would fail if the code in AsmPrinter were removed.
llvm-svn: 129432
Additional fixes:
Do something reasonable for subtargets with generic
itineraries by handle node latency the same as for an empty
itinerary. Now nodes default to unit latency unless an itinerary
explicitly specifies a zero cycle stage or it is a TokenFactor chain.
Original fixes:
UnitsSharePred was a source of randomness in the scheduler: node
priority depended on the queue data structure. I rewrote the recent
VRegCycle heuristics to completely replace the old heuristic without
any randomness. To make the ndoe latency adjustments work, I also
needed to do something a little more reasonable with TokenFactor. I
gave it zero latency to its consumers and always schedule it as low as
possible.
llvm-svn: 129421
Now that we have a first-class way to represent unaligned loads, the unaligned
load intrinsics are superfluous.
First part of <rdar://problem/8460511>.
llvm-svn: 129401
UnitsSharePred was a source of randomness in the scheduler: node
priority depended on the queue data structure. I rewrote the recent
VRegCycle heuristics to completely replace the old heuristic without
any randomness. To make these heuristic adjustments to node latency work,
I also needed to do something a little more reasonable with TokenFactor. I
gave it zero latency to its consumers and always schedule it as low as
possible.
llvm-svn: 129383
reassociation opportunities are exposed. This fixes a bug where
the nested reassociation expects to be the IR to be consistent,
but it isn't, because the outer reassociation has disconnected
some of the operands. rdar://9167457
llvm-svn: 129324
--- Reverse-merging r129235 into '.':
D test/Feature/bb_attrs.ll
U include/llvm/BasicBlock.h
U include/llvm/Bitcode/LLVMBitCodes.h
U lib/VMCore/AsmWriter.cpp
U lib/VMCore/BasicBlock.cpp
U lib/AsmParser/LLParser.cpp
U lib/AsmParser/LLLexer.cpp
U lib/AsmParser/LLToken.h
U lib/Bitcode/Reader/BitcodeReader.cpp
U lib/Bitcode/Writer/BitcodeWriter.cpp
llvm-svn: 129259
Stuart Hastings