intrinsic call. This prevents it from being reordered so that it appears
*before* the setjmp intrinsic (thus making it completely useless).
<rdar://problem/9409683>
llvm-svn: 131174
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
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
It needed to be moved closer to the setjmp statement, because the code directly
after the setjmp needs to know about values that are on the stack. Also, the
'bitcast' of the function context was causing a dead load. This wouldn't be too
horrible, except that at -O0 it wasn't optimized out, and because it wasn't
using the correct base pointer (if there is a VLA), it would try to access a
value from a garbage address.
<rdar://problem/9130540>
llvm-svn: 128873
registers that arise from argument shuffling with the soft float ABI. These
instructions are particularly slow on Cortex A8. This fixes one half of
<rdar://problem/8674845>.
llvm-svn: 128759
was lowering them to sext / uxt + mul instructions. Unfortunately the
optimization passes may hoist the extensions out of the loop and separate them.
When that happens, the long multiplication instructions can be broken into
several scalar instructions, causing significant performance issue.
Note the vmla and vmls intrinsics are not added back. Frontend will codegen them
as intrinsics vmull* + add / sub. Also note the isel optimizations for catching
mul + sext / zext are not changed either.
First part of rdar://8832507, rdar://9203134
llvm-svn: 128502
isel lowering to fold the zero-extend's and take advantage of no-stall
back to back vmul + vmla:
vmull q0, d4, d6
vmlal q0, d5, d6
is faster than
vaddl q0, d4, d5
vmovl q1, d6
vmul q0, q0, q1
This allows us to vmull + vmlal for:
f = vmull_u8( vget_high_u8(s), c);
f = vmlal_u8(f, vget_low_u8(s), c);
rdar://9197392
llvm-svn: 128444
masks to match inversely for the code as is to work. For the example given
we actually want:
bfi r0, r2, #1, #1
not #0, however, given the way the pattern is written it's not possible
at the moment.
Fixes rdar://9177502
llvm-svn: 128320
to have single return block (at least getting there) for optimizations. This
is general goodness but it would prevent some tailcall optimizations.
One specific case is code like this:
int f1(void);
int f2(void);
int f3(void);
int f4(void);
int f5(void);
int f6(void);
int foo(int x) {
switch(x) {
case 1: return f1();
case 2: return f2();
case 3: return f3();
case 4: return f4();
case 5: return f5();
case 6: return f6();
}
}
=>
LBB0_2: ## %sw.bb
callq _f1
popq %rbp
ret
LBB0_3: ## %sw.bb1
callq _f2
popq %rbp
ret
LBB0_4: ## %sw.bb3
callq _f3
popq %rbp
ret
This patch teaches codegenprep to duplicate returns when the return value
is a phi and where the phi operands are produced by tail calls followed by
an unconditional branch:
sw.bb7: ; preds = %entry
%call8 = tail call i32 @f5() nounwind
br label %return
sw.bb9: ; preds = %entry
%call10 = tail call i32 @f6() nounwind
br label %return
return:
%retval.0 = phi i32 [ %call10, %sw.bb9 ], [ %call8, %sw.bb7 ], ... [ 0, %entry ]
ret i32 %retval.0
This allows codegen to generate better code like this:
LBB0_2: ## %sw.bb
jmp _f1 ## TAILCALL
LBB0_3: ## %sw.bb1
jmp _f2 ## TAILCALL
LBB0_4: ## %sw.bb3
jmp _f3 ## TAILCALL
rdar://9147433
llvm-svn: 127953
The previous codegen for the slow path (when values are in VFP / NEON
registers) was incorrect if the source is NaN.
The new codegen uses NEON vbsl instruction to copy the sign bit. e.g.
vmov.i32 d1, #0x80000000
vbsl d1, d2, d0
If NEON is not available, it uses integer instructions to copy the sign bit.
rdar://9034702
llvm-svn: 126295
In other words, do not keep track of argument's location. The debugger (gdb) is not prepared to see line table entries for arguments. For the debugger, "second" line table entry marks beginning of function body.
This requires some coordination with debugger to get this working.
- The debugger needs to be aware of prolog_end attribute attached with line table entries.
- The compiler needs to accurately mark prolog_end in line table entries (at -O0 and at -O1+)
llvm-svn: 126155
This
define float @foo(float %x, float %y) nounwind readnone {
entry:
%0 = tail call float @copysignf(float %x, float %y) nounwind readnone
ret float %0
}
Was compiled to:
vmov s0, r1
bic r0, r0, #-2147483648
vmov s1, r0
vcmpe.f32 s0, #0
vmrs apsr_nzcv, fpscr
it lt
vneglt.f32 s1, s1
vmov r0, s1
bx lr
This fails to copy the sign of -0.0f because it's lost during the float to int
conversion. Also, it's sub-optimal when the inputs are in GPR registers.
Now it uses integer and + or operations when it's profitable. And it's correct!
lsrs r1, r1, #31
bfi r0, r1, #31, #1
bx lr
rdar://8984306
llvm-svn: 125357
The vld1-lane, vld1-dup and vst1-lane instructions do not yet support using
post-increment versions, but all the rest of the NEON load/store instructions
should be handled now.
llvm-svn: 125014
the load, then it may be legal to transform the load and store to integer
load and store of the same width.
This is done if the target specified the transformation as profitable. e.g.
On arm, this can transform:
vldr.32 s0, []
vstr.32 s0, []
to
ldr r12, []
str r12, []
rdar://8944252
llvm-svn: 124708
1. Fixed ARM pc adjustment.
2. Fixed dynamic-no-pic codegen
3. CSE of pc-relative load of global addresses.
It's now enabled by default for Darwin.
llvm-svn: 123991
TargetInstrInfo:
Change produceSameValue() to take MachineRegisterInfo as an optional argument.
When in SSA form, targets can use it to make more aggressive equality analysis.
Machine LICM:
1. Eliminate isLoadFromConstantMemory, use MI.isInvariantLoad instead.
2. Fix a bug which prevent CSE of instructions which are not re-materializable.
3. Use improved form of produceSameValue.
ARM:
1. Teach ARM produceSameValue to look pass some PIC labels.
2. Look for operands from different loads of different constant pool entries
which have same values.
3. Re-implement PIC GA materialization using movw + movt. Combine the pair with
a "add pc" or "ldr [pc]" to form pseudo instructions. This makes it possible
to re-materialize the instruction, allow machine LICM to hoist the set of
instructions out of the loop and make it possible to CSE them. It's a bit
hacky, but it significantly improve code quality.
4. Some minor bug fixes as well.
With the fixes, using movw + movt to materialize GAs significantly outperform the
load from constantpool method. 186.crafty and 255.vortex improved > 20%, 254.gap
and 176.gcc ~10%.
llvm-svn: 123905
of the floating point types less than 64-bits. It's somewhat of a temporary
hack but forces more accurate modeling of register pressure and results
in fewer spills.
llvm-svn: 123811
movw r0, :lower16:(L_foo$non_lazy_ptr-(LPC0_0+4))
movt r0, :upper16:(L_foo$non_lazy_ptr-(LPC0_0+4))
LPC0_0:
add r0, pc, r0
It's not yet enabled by default as some tests are failing. I suspect bugs in
down stream tools.
llvm-svn: 123619
Also fix an off-by-one in SelectionDAGBuilder that was preventing shuffle
vectors from being translated to EXTRACT_SUBVECTOR.
Patch by Tim Northover.
The test changes are needed to keep those spill-q tests from testing aligned
spills and restores. If the only aligned stack objects are spill slots, we
no longer realign the stack frame. Prior to this patch, an EXTRACT_SUBVECTOR
was legalized by loading from the stack, which created an aligned frame index.
Now, however, there is nothing except the spill slot in the stack frame, so
I added an aligned alloca.
llvm-svn: 122995
If the basic block containing the BCCi64 (or BCCZi64) instruction ends with
an unconditional branch, that branch needs to be deleted before appending
the expansion of the BCCi64 to the end of the block.
llvm-svn: 122521
Type legalization splits up i64 values into pairs of i32 values, which leads
to poor quality code when inserting or extracting i64 vector elements.
If the vector element is loaded or stored, it can be treated as an f64 value
and loaded or stored directly from a VPR register. Use the pre-legalization
DAG combiner to cast those vector elements to f64 types so that the type
legalizer won't mess them up. Radar 8755338.
llvm-svn: 122319
zextOrTrunc(), and APSInt methods extend(), extOrTrunc() and new method
trunc(), to be const and to return a new value instead of modifying the
object in place.
llvm-svn: 121120
legalization time. Since at legalization time there is no mapping from
SDNode back to the corresponding LLVM instruction and the return
SDNode is target specific, this requires a target hook to check for
eligibility. Only x86 and ARM support this form of sibcall optimization
right now.
rdar://8707777
llvm-svn: 120501
We need to check if the individual vector elements are sign/zero-extended
values. For now this only handles constants values. Radar 8687140.
llvm-svn: 120034
This function was being called from two different places for completely
unrelated reasons. During type legalization, it was called to expand 64-bit
shift operations. During operation legalization, it was called to handle
Neon vector shifts. The vector shift code was not written to check for
illegal types, since it was assumed to be only called after type legalization.
Fixed this by splitting off the 64-bit shift expansion into a separate
function. I don't have a particular testcase for this; I just noticed it
by inspection.
llvm-svn: 119738
It is only supported for ARM code. Normally Thumb2 code would use DMB instead,
but depending on how the compiler is invoked (e.g., -mattr=-db) that might be
disabled. This prevents a "cannot select MEMBARRIER_MCR" error in that
situation. Radar 8644195
llvm-svn: 118642
There were a number of issues to fix up here:
* The "device" argument of the llvm.memory.barrier intrinsic should be
used to distinguish the "Full System" domain from the "Inner Shareable"
domain. It has nothing to do with using DMB vs. DSB instructions.
* The compiler should never need to emit DSB instructions. Remove the
ARMISD::SYNCBARRIER node and also remove the instruction patterns for DSB.
* Merge the separate DMB/DSB instructions for options only used for the
disassembler with the default DMB/DSB instructions. Add the default
"full system" option ARM_MB::SY to the ARM_MB::MemBOpt enum.
* Add a separate ARMISD::MEMBARRIER_MCR node for subtargets that implement
a data memory barrier using the MCR instruction.
* Fix up encodings for these instructions (except MCR).
I also updated the tests and added a few new ones to check for DMB options
that were not currently being exercised.
llvm-svn: 117756
elements than the result vector type. So, when an instruction like:
%8 = shufflevector <2 x float> %4, <2 x float> %7, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
is translated to a DAG, each operand is changed to a concat_vectors node that appends 2 undef elements. That is:
shuffle [a,b], [c,d] is changed to:
shuffle [a,b,u,u], [c,d,u,u]
That's probably the right thing for x86 but for NEON, we'd much rather have:
shuffle [a,b,c,d], undef
Teach the DAG combiner how to do that transformation for ARM. Radar 8597007.
llvm-svn: 117482
new VariantKind to the MCSymbolExpr seems like overkill, but I'm not sure
there's a more straightforward way to get the printing difference captured.
(i.e., x86 uses @PLT, ARM uses (PLT)).
llvm-svn: 114613
CombineTo to avoid putting the result on the worklist. I don't think it makes
much difference for now, but it might help someday as we add more DAG
combine optimizations.
llvm-svn: 114595
of those. Refactor to share code for handling BUILD_VECTOR(VMOVRRD).
I don't have a testcase that exercises this, but it seems like an obvious
good thing to do.
llvm-svn: 114589
value should be in GPRs when it's going to be used as a scalar, and we use
VMOVRRD to make that happen, but if the value is converted back to a vector
we need to fold to a simple bit_convert. Radar 8407927.
llvm-svn: 114233
take multiple cycles to decode.
For the current if-converter clients (actually only ARM), the instructions that
are predicated on false are not nops. They would still take machine cycles to
decode. Micro-coded instructions such as LDM / STM can potentially take multiple
cycles to decode. If-converter should take treat them as non-micro-coded
simple instructions.
llvm-svn: 113570
vabd intrinsic and add and/or zext operations. In the case of vaba, this
also avoids the need for a DAG combine pattern to combine vabd with add.
Update tests. Auto-upgrade the old intrinsics.
llvm-svn: 112941
add, and subtract operations with zero-extended or sign-extended vectors.
Update tests. Add auto-upgrade support for the old intrinsics.
llvm-svn: 112773
comparison that would overflow.
- The other under/overflow cases can't actually happen because the immediates
which would trigger them are legal (so we don't enter this code), but
adjusted the style to make it clear the transform is always valid.
llvm-svn: 112053
float t1(int argc) {
return (argc == 1123) ? 1.234f : 2.38213f;
}
We would generate truly awful code on ARM (those with a weak stomach should look
away):
_t1:
movw r1, #1123
movs r2, #1
movs r3, #0
cmp r0, r1
mov.w r0, #0
it eq
moveq r0, r2
movs r1, #4
cmp r0, #0
it ne
movne r3, r1
adr r0, #LCPI1_0
ldr r0, [r0, r3]
bx lr
The problem was that legalization was creating a cascade of SELECT_CC nodes, for
for the comparison of "argc == 1123" which was fed into a SELECT node for the ?:
statement which was itself converted to a SELECT_CC node. This is because the
ARM back-end doesn't have custom lowering for SELECT nodes, so it used the
default "Expand".
I added a fairly simple "LowerSELECT" to the ARM back-end. It takes care of this
testcase, but can obviously be expanded to include more cases.
Now we generate this, which looks optimal to me:
_t1:
movw r1, #1123
movs r2, #0
cmp r0, r1
adr r0, #LCPI0_0
it eq
moveq r2, #4
ldr r0, [r0, r2]
bx lr
.align 2
LCPI0_0:
.long 1075344593 @ float 2.382130e+00
.long 1067316150 @ float 1.234000e+00
llvm-svn: 110799
memory and synchronization barrier dmb and dsb instructions.
- Change instruction names to something more sensible (matching name of actual
instructions).
- Added tests for memory barrier codegen.
llvm-svn: 110785
Also added a test case to check for the added benefit of this patch: it's optimizing away the unnecessary restore of sp from fp for some non-leaf functions.
llvm-svn: 110707
reserved, not available for general allocation. This eliminates all the
extra checks for Darwin.
This change also fixes the use of FP to access frame indices in leaf
functions and cleaned up some confusing code in epilogue emission.
llvm-svn: 110655
Add support for using the FPSCR in conjunction with the vcvtr instruction, for controlling fp to int rounding.
Add support for the FLT_ROUNDS_ node now that the FPSCR is exposed.
llvm-svn: 110152
integers with mov + vdup. 8003375. This is
currently disabled by default because LICM will
not hoist a VDUP, so it pessimizes the code if
the construct occurs inside a loop (8248029).
llvm-svn: 109799
it's too late to start backing off aggressive latency scheduling when most
of the registers are in use so the threshold should be a bit tighter.
- Correctly handle live out's and extract_subreg etc.
- Enable register pressure aware scheduling by default for hybrid scheduler.
For ARM, this is almost always a win on # of instructions. It's runtime
neutral for most of the tests. But for some kernels with high register
pressure it can be a huge win. e.g. 464.h264ref reduced number of spills by
54 and sped up by 20%.
llvm-svn: 109279
it should set the jump table encloding the EK_Inline. This prevents
a second, unused, copy of the table from being emitted after the function
body. PR6581.
llvm-svn: 108730
it should set the jump table encloding the EK_Inline. This prevents
a second, unused, copy of the table from being emitted after the function
body. PR7499.
llvm-svn: 108722
-enable-no-nans-fp-math and -enable-no-infs-fp-math. All of the current codegen fp math optimizations only care whether the fp arithmetics arguments and results can never be NaN.
llvm-svn: 108465
instructions already have implicit defs of LR. The comment suggests that
this is intended to fix something like pr6111, but it doesn't really do
that either.
llvm-svn: 108186
correct alignment information, which simplifies ExpandRes_VAARG a bit.
The patch introduces a new alignment information to TargetLoweringInfo. This is
needed since the two natural candidates cannot be used:
* The 's' in target data: If this is set to the minimal alignment of any
argument, getCallFrameTypeAlignment would return 4 for doubles on ARM for
example.
* The getTransientStackAlignment method. It is possible for an architecture to
have argument less aligned than what we maintain the stack pointer.
llvm-svn: 108072
1. The arguments are f32.
2. The arguments are loads and they have no uses other than the comparison.
3. The comparison code is EQ or NE.
e.g.
vldr.32 s0, [r1]
vldr.32 s1, [r0]
vcmpe.f32 s1, s0
vmrs apsr_nzcv, fpscr
beq LBB0_2
=>
ldr r1, [r1]
ldr r0, [r0]
cmp r0, r1
beq LBB0_2
More complicated cases will be implemented in subsequent patches.
llvm-svn: 107852
Add explicit testcases for tail calls within the same module.
Duplicate some code to humor those who think .w doesn't apply on ARM.
Leave this disabled on Thumb1, and add some comments explaining why it's hard
and won't gain much.
llvm-svn: 107851
getFunctionAlignment and the corresponding use of that value in the ARM
asm printer, but now we're using the standard asm printer. The result of
this was that function alignments were dropped completely for Thumb functions.
Radar 8143571.
llvm-svn: 107435
for an "i" constraint should get lowered; PR 6309. While
this argument was passed around a lot, this is the only
place it was used, so it goes away from a lot of other
places.
llvm-svn: 106893
Evan Cheng