This can result in increased opportunities for store narrowing in code generation. Update a number of
tests for this change. This fixes <rdar://problem/8285027>.
Additionally, because this inverts the order of ors and ands, some patterns for optimizing or-of-and-of-or
no longer fire in instances where they did originally. Add a simple transform which recaptures most of these
opportunities: if we have an or-of-constant-or and have failed to fold away the inner or, commute the order
of the two ors, to give the non-constant or a chance for simplification instead.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113679 91177308-0d34-0410-b5e6-96231b3b80d8
to use AddrMode4, there was a count of the registers stored in one of the
operands. I changed that to just count the operands but forgot to adjust for
the size of D registers. This was noticed by Evan as a performance problem
but it is a potential correctness bug as well, since it is possible that this
could merge a base update with a non-matching immediate.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113576 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113570 91177308-0d34-0410-b5e6-96231b3b80d8
- This is annoying, because we have to scatter this check everywhere that could emit real data, but I see no better solution.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113552 91177308-0d34-0410-b5e6-96231b3b80d8
- Output format and some of the code stolen from macho-dump.
- Somewhat incomplete and probably buggy.
- Comes with a very basic test.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113488 91177308-0d34-0410-b5e6-96231b3b80d8
of checking for either 4 or 8 is not very satisfactory, but
it would catch the original problem (an alignment of 1).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113485 91177308-0d34-0410-b5e6-96231b3b80d8
removed. Not that the XTARGET wasn't doing anything since it
does nothing without an accompanying XFAIL.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113484 91177308-0d34-0410-b5e6-96231b3b80d8
the VST pseudos. The VLD/VST scheduling still needs work (see pr6722), but
at least we shouldn't confuse the loads with the stores.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113473 91177308-0d34-0410-b5e6-96231b3b80d8
unrolling threshold to the optimize-for-size threshold. Basically, for loops containing calls, unrolling
can still be profitable as long as the loop is REALLY small.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113439 91177308-0d34-0410-b5e6-96231b3b80d8
turning (fptrunc (sqrt (fpext x))) -> (sqrtf x) is great, but we have
to delete the original sqrt as well. Not doing so causes us to do
two sqrt's when building with -fmath-errno (the default on linux).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113260 91177308-0d34-0410-b5e6-96231b3b80d8
always be disambiguated as sldtw. sldtw and sldtq with
a mem operands have the same effect, but sldtw is more
compact. Force it to sldtw, resolving rdar://8017530
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113186 91177308-0d34-0410-b5e6-96231b3b80d8
in the duplicated block instead of duplicating them.
Duplicating them into the end of the loop and the preheader
means that we got a phi node in the header of the loop,
which prevented LICM from hoisting them. GVN would
usually come around later and merge the duplicated
instructions so we'd get reasonable output... except that
anything dependent on the shoulda-been-hoisted value can't
be hoisted. In PR5319 (which this fixes), a memory value
didn't get promoted.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113134 91177308-0d34-0410-b5e6-96231b3b80d8
Since mem2reg isn't run at -O0, we get a ton of reloads from the stack,
for example, before, this code:
int foo(int x, int y, int z) {
return x+y+z;
}
used to compile into:
_foo: ## @foo
subq $12, %rsp
movl %edi, 8(%rsp)
movl %esi, 4(%rsp)
movl %edx, (%rsp)
movl 8(%rsp), %edx
movl 4(%rsp), %esi
addl %edx, %esi
movl (%rsp), %edx
addl %esi, %edx
movl %edx, %eax
addq $12, %rsp
ret
Now we produce:
_foo: ## @foo
subq $12, %rsp
movl %edi, 8(%rsp)
movl %esi, 4(%rsp)
movl %edx, (%rsp)
movl 8(%rsp), %edx
addl 4(%rsp), %edx ## Folded load
addl (%rsp), %edx ## Folded load
movl %edx, %eax
addq $12, %rsp
ret
Fewer instructions and less register use = faster compiles.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113102 91177308-0d34-0410-b5e6-96231b3b80d8
location is being re-stored to the memory location. We would get
a dangling pointer from the SSAUpdate data structure and miss a
use. This fixes PR8068
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113042 91177308-0d34-0410-b5e6-96231b3b80d8
"For ARM stack frames that utilize variable sized objects and have either
large local stack areas or require dynamic stack realignment, allocate a
base register via which to access the local frame. This allows efficient
access to frame indices not accessible via the FP (either due to being out
of range or due to dynamic realignment) or the SP (due to variable sized
object allocation). In particular, this greatly improves efficiency of access
to spill slots in Thumb functions which contain VLAs."
r112986 fixed a latent bug exposed by the above.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112989 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112941 91177308-0d34-0410-b5e6-96231b3b80d8
large local stack areas or require dynamic stack realignment, allocate a
base register via which to access the local frame. This allows efficient
access to frame indices not accessible via the FP (either due to being out
of range or due to dynamic realignment) or the SP (due to variable sized
object allocation). In particular, this greatly improves efficiency of access
to spill slots in Thumb functions which contain VLAs.
rdar://7352504
rdar://8374540
rdar://8355680
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112883 91177308-0d34-0410-b5e6-96231b3b80d8
there are clearly no stores between the load and the store. This fixes
this miscompile reported as PR7833.
This breaks the test/CodeGen/X86/narrow_op-2.ll optimization, which is
safe, but awkward to prove safe. Move it to X86's README.txt.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112861 91177308-0d34-0410-b5e6-96231b3b80d8
add, and subtract operations with zero-extended or sign-extended vectors.
Update tests. Add auto-upgrade support for the old intrinsics.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112773 91177308-0d34-0410-b5e6-96231b3b80d8
check more strict, breaking some cases not checked in the
testsuite, but also exposes some foldings not done before,
as this example:
movaps (%rdi), %xmm0
movaps (%rax), %xmm1
movaps %xmm0, %xmm2
movss %xmm1, %xmm2
shufps $36, %xmm2, %xmm0
now is generated as:
movaps (%rdi), %xmm0
movaps %xmm0, %xmm1
movlps (%rax), %xmm1
shufps $36, %xmm1, %xmm0
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112753 91177308-0d34-0410-b5e6-96231b3b80d8
This caused a miscompilation in WebKit where %RAX had conflicting defs when
RemoveCopyByCommutingDef was commuting a %EAX use.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112751 91177308-0d34-0410-b5e6-96231b3b80d8
on llvmdev: SRoA is introducing MMX datatypes like <1 x i64>,
which then cause random problems because the X86 backend is
producing mmx stuff without inserting proper emms calls.
In the short term, force off MMX datatypes. In the long term,
the X86 backend should not select generic vector types to MMX
registers. This is being worked on, but won't be done in time
for 2.8. rdar://8380055
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112696 91177308-0d34-0410-b5e6-96231b3b80d8
int x(int t) {
if (t & 256)
return -26;
return 0;
}
We generate this:
tst.w r0, #256
mvn r0, #25
it eq
moveq r0, #0
while gcc generates this:
ands r0, r0, #256
it ne
mvnne r0, #25
bx lr
Scandalous really!
During ISel time, we can look for this particular pattern. One where we have a
"MOVCC" that uses the flag off of a CMPZ that itself is comparing an AND
instruction to 0. Something like this (greatly simplified):
%r0 = ISD::AND ...
ARMISD::CMPZ %r0, 0 @ sets [CPSR]
%r0 = ARMISD::MOVCC 0, -26 @ reads [CPSR]
All we have to do is convert the "ISD::AND" into an "ARM::ANDS" that sets [CPSR]
when it's zero. The zero value will all ready be in the %r0 register and we only
need to change it if the AND wasn't zero. Easy!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112664 91177308-0d34-0410-b5e6-96231b3b80d8
I have not been able to find a way to test each in isolation, for a few reasons:
1) The ability to look-through non-i1 BinaryOperator's requires the ability to look through non-constant
ICmps in order for it to ever trigger.
2) The ability to do LVI-powered PHI value determination only matters in cases that ProcessBranchOnPHI
can't handle. Since it already handles all the cases without other instructions in the def-use chain
between the PHI and the branch, it requires the ability to look through ICmps and/or BinaryOperators
as well.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112611 91177308-0d34-0410-b5e6-96231b3b80d8
This actually exposed an infinite recursion bug in ComputeValueKnownInPredecessors which theoretically already existed (in JumpThreading's
handling of and/or of i1's), but never manifested before. This patch adds a tracking set to prevent this case.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112589 91177308-0d34-0410-b5e6-96231b3b80d8
1) nuke ConstDataCoalSection, which is dead.
2) revise my previous patch for rdar://8018335,
which was completely wrong. Specifically, it doesn't
make sense to mark __TEXT,__const_coal as PURE_INSTRUCTIONS,
because it is for readonly data. templates (it turns out)
go to const_coal_nt. The real fix for rdar://8018335 was
to give ConstTextCoalSection a section kind of ReadOnly
instead of Text.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112496 91177308-0d34-0410-b5e6-96231b3b80d8
IR add/sub operations with one or both operands sign- or zero-extended.
Auto-upgrade the old intrinsics.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112416 91177308-0d34-0410-b5e6-96231b3b80d8
when the top elements of a vector are undefined. This happens all
the time for X86-64 ABI stuff because only the low 2 elements of
a 4 element vector are defined. For example, on:
_Complex float f32(_Complex float A, _Complex float B) {
return A+B;
}
We used to produce (with SSE2, SSE4.1+ uses insertps):
_f32: ## @f32
movdqa %xmm0, %xmm2
addss %xmm1, %xmm2
pshufd $16, %xmm2, %xmm2
pshufd $1, %xmm1, %xmm1
pshufd $1, %xmm0, %xmm0
addss %xmm1, %xmm0
pshufd $16, %xmm0, %xmm1
movdqa %xmm2, %xmm0
unpcklps %xmm1, %xmm0
ret
We now produce:
_f32: ## @f32
movdqa %xmm0, %xmm2
addss %xmm1, %xmm2
pshufd $1, %xmm1, %xmm1
pshufd $1, %xmm0, %xmm3
addss %xmm1, %xmm3
movaps %xmm2, %xmm0
unpcklps %xmm3, %xmm0
ret
This implements rdar://8368414
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112378 91177308-0d34-0410-b5e6-96231b3b80d8
all the other LDM/STM instructions. This fixes asm printer crashes when
compiling with -O0. I've changed one of the NEON tests (vst3.ll) to run
with -O0 to check this in the future.
Prior to this change VLDM/VSTM used addressing mode #5, but not really.
The offset field was used to hold a count of the number of registers being
loaded or stored, and the AM5 opcode field was expanded to specify the IA
or DB mode, instead of the standard ADD/SUB specifier. Much of the backend
was not aware of these special cases. The crashes occured when rewriting
a frameindex caused the AM5 offset field to be changed so that it did not
have a valid submode. I don't know exactly what changed to expose this now.
Maybe we've never done much with -O0 and NEON. Regardless, there's no longer
any reason to keep a count of the VLDM/VSTM registers, so we can use
addressing mode #4 and clean things up in a lot of places.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112322 91177308-0d34-0410-b5e6-96231b3b80d8
A = shl x, 42
...
B = lshr ..., 38
which can be transformed into:
A = shl x, 4
...
iff we can prove that the would-be-shifted-in bits
are already zero. This eliminates two shifts in the testcase
and allows eliminate of the whole i128 chain in the real example.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112314 91177308-0d34-0410-b5e6-96231b3b80d8
framework, which is good at ripping through bitfield
operations. This generalize a bunch of the existing
xforms that instcombine does, such as
(x << c) >> c -> and
to handle intermediate logical nodes. This is useful for
ripping up the "promote to large integer" code produced by
SRoA.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112304 91177308-0d34-0410-b5e6-96231b3b80d8
computation can be truncated if it is fed by a sext/zext that doesn't
have to be exactly equal to the truncation result type.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112285 91177308-0d34-0410-b5e6-96231b3b80d8
by the SRoA "promote to large integer" code, eliminating
some type conversions like this:
%94 = zext i16 %93 to i32 ; <i32> [#uses=2]
%96 = lshr i32 %94, 8 ; <i32> [#uses=1]
%101 = trunc i32 %96 to i8 ; <i8> [#uses=1]
This also unblocks other xforms from happening, now clang is able to compile:
struct S { float A, B, C, D; };
float foo(struct S A) { return A.A + A.B+A.C+A.D; }
into:
_foo: ## @foo
## BB#0: ## %entry
pshufd $1, %xmm0, %xmm2
addss %xmm0, %xmm2
movdqa %xmm1, %xmm3
addss %xmm2, %xmm3
pshufd $1, %xmm1, %xmm0
addss %xmm3, %xmm0
ret
on x86-64, instead of:
_foo: ## @foo
## BB#0: ## %entry
movd %xmm0, %rax
shrq $32, %rax
movd %eax, %xmm2
addss %xmm0, %xmm2
movapd %xmm1, %xmm3
addss %xmm2, %xmm3
movd %xmm1, %rax
shrq $32, %rax
movd %eax, %xmm0
addss %xmm3, %xmm0
ret
This seems pretty close to optimal to me, at least without
using horizontal adds. This also triggers in lots of other
code, including SPEC.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112278 91177308-0d34-0410-b5e6-96231b3b80d8
Update all the tests using those intrinsics and add support for
auto-upgrading bitcode files with the old versions of the intrinsics.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112271 91177308-0d34-0410-b5e6-96231b3b80d8
fix: add a flag to MapValue and friends which indicates whether
any module-level mappings are being made. In the common case of
inlining, no module-level mappings are needed, so MapValue doesn't
need to examine non-function-local metadata, which can be very
expensive in the case of a large module with really deep metadata
(e.g. a large C++ program compiled with -g).
This flag is a little awkward; perhaps eventually it can be moved
into the ClonedCodeInfo class.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112190 91177308-0d34-0410-b5e6-96231b3b80d8
expanding: e.g. <2 x float> -> <4 x float> instead of -> 2 floats. This
affects two places in the code: handling cross block values and handling
function return and arguments. Since vectors are already widened by
legalizetypes, this gives us much better code and unblocks x86-64 abi
and SPU abi work.
For example, this (which is a silly example of a cross-block value):
define <4 x float> @test2(<4 x float> %A) nounwind {
%B = shufflevector <4 x float> %A, <4 x float> undef, <2 x i32> <i32 0, i32 1>
%C = fadd <2 x float> %B, %B
br label %BB
BB:
%D = fadd <2 x float> %C, %C
%E = shufflevector <2 x float> %D, <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
ret <4 x float> %E
}
Now compiles into:
_test2: ## @test2
## BB#0:
addps %xmm0, %xmm0
addps %xmm0, %xmm0
ret
previously it compiled into:
_test2: ## @test2
## BB#0:
addps %xmm0, %xmm0
pshufd $1, %xmm0, %xmm1
## kill: XMM0<def> XMM0<kill> XMM0<def>
insertps $0, %xmm0, %xmm0
insertps $16, %xmm1, %xmm0
addps %xmm0, %xmm0
ret
This implements rdar://8230384
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112101 91177308-0d34-0410-b5e6-96231b3b80d8
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.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112053 91177308-0d34-0410-b5e6-96231b3b80d8
any load in the default address space that completes implies that the base value that it GEP'd from
was not null.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112015 91177308-0d34-0410-b5e6-96231b3b80d8
- Implemented by manually splicing the tokens. If this turns out to be
problematically platform specific, a more elegant solution would be to
implement some context dependent lexing support.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@111934 91177308-0d34-0410-b5e6-96231b3b80d8
comparison is in a different basic block from the branch. In such
cases, the comparison's operands may not have initialized virtual
registers available.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@111709 91177308-0d34-0410-b5e6-96231b3b80d8
It's similar to "linker_private_weak", but it's known that the address of the
object is not taken. For instance, functions that had an inline definition, but
the compiler decided not to inline it. Note, unlike linker_private and
linker_private_weak, linker_private_weak_def_auto may have only default
visibility. The symbols are removed by the linker from the final linked image
(executable or dynamic library).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@111684 91177308-0d34-0410-b5e6-96231b3b80d8