ADC is commutable and the load could be in either operand, but we were only checking operand 0.
Ideally we'd mark X86adc_flag as commutable and tablegen would automatically do this, but the EFLAGS register mention is preventing it.
llvm-svn: 341606
The ADC instruction is commutable, but we only have RMW isel patterns with a load on the left hand side. Nothing will canonicalize loads to the LHS on these ops. So we need two patterns.
llvm-svn: 341605
This basically reverts a change made in r336217, but improves the text of the error message for not allowing IP-relative addressing in 32-bit mode.
Fixes PR38826.
Patch by Iain Sandoe.
llvm-svn: 341512
This was proposed as an IR transform in D49306, but it was not clearly justifiable as a canonicalization.
Here, we only do the transform when the target tells us that sqrt can be lowered with inline code.
This is the basic case. Some potential enhancements are in the TODO comments:
1. Generalize the transform for other exponents (allow more than 2 sqrt calcs if that's really cheaper).
2. If we have less fast-math-flags, generate code to avoid -0.0 and/or INF.
3. Allow the transform when optimizing/minimizing size (might require a target hook to get that right).
Note that by default, x86 converts single-precision sqrt calcs into sqrt reciprocal estimate with
refinement. That codegen is controlled by CPU attributes and can be manually overridden. We have plenty
of test coverage for that already, so I didn't bother to include extra testing for that here. AArch uses
its full-precision ops in all cases (not sure if that's the intended behavior or not, but that should
also be covered by existing tests).
Differential Revision: https://reviews.llvm.org/D51630
llvm-svn: 341481
Load Hardening.
Wires up the existing pass to work with a proper IR attribute rather
than just a hidden/internal flag. The internal flag continues to work
for now, but I'll likely remove it soon.
Most of the churn here is adding the IR attribute. I talked about this
Kristof Beyls and he seemed at least initially OK with this direction.
The idea of using a full attribute here is that we *do* expect at least
some forms of this for other architectures. There isn't anything
*inherently* x86-specific about this technique, just that we only have
an implementation for x86 at the moment.
While we could potentially expose this as a Clang-level attribute as
well, that seems like a good question to defer for the moment as it
isn't 100% clear whether that or some other programmer interface (or
both?) would be best. We'll defer the programmer interface side of this
for now, but at least get to the point where the feature can be enabled
without relying on implementation details.
This also allows us to do something that was really hard before: we can
enable *just* the indirect call retpolines when using SLH. For x86, we
don't have any other way to mitigate indirect calls. Other architectures
may take a different approach of course, and none of this is surfaced to
user-level flags.
Differential Revision: https://reviews.llvm.org/D51157
llvm-svn: 341363
implementing the proposed mitigation technique described in the original
design document.
The idea is to check after calls that the return address used to arrive
at that location is in fact the correct address. In the event of
a mis-predicted return which reaches a *valid* return but not the
*correct* return, this will detect the mismatch much like it would
a mispredicted conditional branch.
This is the last published attack vector that I am aware of in the
Spectre v1 space which is not mitigated by SLH+retpolines. However,
don't read *too* much into that: this is an area of ongoing research
where we expect more issues to be discovered in the future, and it also
makes no attempt to mitigate Spectre v4. Still, this is an important
completeness bar for SLH.
The change here is of course delightfully simple. It was predicated on
cutting support for post-instruction symbols into LLVM which was not at
all simple. Many thanks to Hal Finkel, Reid Kleckner, and Justin Bogner
who helped me figure out how to do a bunch of the complex changes
involved there.
Differential Revision: https://reviews.llvm.org/D50837
llvm-svn: 341358
retpolines.
This implements the core design of tracing the intended target into the
target, checking it, and using that to update the predicate state. It
takes advantage of a few interesting aspects of SLH to make it a bit
easier to implement:
- We already split critical edges with conditional branches, so we can
assume those are gone.
- We already unfolded any memory access in the indirect branch
instruction itself.
I've left hard errors in place to catch if any of these somewhat subtle
invariants get violated.
There is some code that I can factor out and share with D50837 when it
lands, but I didn't want to couple landing the two patches, so I'll do
that in a follow-up cleanup commit if alright.
Factoring out the code to handle different scenarios of materializing an
address remains frustratingly hard. In a bunch of cases you want to fold
one of the cases into an immediate operand of some other instruction,
and you also have both symbols and basic blocks being used which require
different methods on the MI builder (and different operand kinds).
Still, I'll take a stab at sharing at least some of this code in
a follow-up if I can figure out how.
Differential Revision: https://reviews.llvm.org/D51083
llvm-svn: 341356
Summary:
A follow-up for D49266 / rL337166 + D49497 / rL338044.
This is still the same pattern to check for the [lack of]
signed truncation, but in this case the constants and the predicate
are negated.
https://rise4fun.com/Alive/BDVhttps://rise4fun.com/Alive/n7Z
Reviewers: spatel, craig.topper, RKSimon, javed.absar, efriedma, dmgreen
Reviewed By: spatel
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D51532
llvm-svn: 341287
These intrinsics use the same implementation as PTEST intrinsics, but use vXi1 vectors.
New clang builtins will be accompanying them shortly.
llvm-svn: 341259
This patch recognizes shuffles that shift elements and fill with zeros. I've copied and modified the shift matching code we use for normal vector registers to do this. I'm not sure if there's a good way to share more of this code without making the existing function more complex than it already is.
This will be used to enable kshift intrinsics in clang.
Differential Revision: https://reviews.llvm.org/D51401
llvm-svn: 341227
This patch fixes the number of micro opcodes, and processor resource cycles for
the following AVX instructions:
vinsertf128rr/rm
vperm2f128rr/rm
vbroadcastf128
Tests have been regenerated using the usual scripts in the llvm/utils directory.
Differential Revision: https://reviews.llvm.org/D51492
llvm-svn: 341185
This will cover the (v2i32 (setcc v2f32)) case in replaceNodeResults. That code shouldn't be needed at all in this mode. A future patch will skip it.
llvm-svn: 341171
This assert tried to check that AND constants are only on the RHS. But its possible for both operands to be constants if one is opaque which will prevent the AND from being constant folded.
Fixes PR38771
llvm-svn: 341102
With r295105, some 'noreturn' blocks (those that don't return and have no
successors) may be merged.
If such blocks' predecessors have different outgoing offset or register, don't
report an error in CFIInstrInserter verify().
Thanks to Vlad Tsyrklevich for reporting the issue.
Differential Revision: https://reviews.llvm.org/D51161
llvm-svn: 341087
Hacker's Delight 10-17: when C is constant,
the result of X % C == 0 can be computed more cheaply
without actually calculating the remainder.
The motivation is discussed here:
https://bugs.llvm.org/show_bug.cgi?id=35479.
Patch by: hermord (Dmytro Shynkevych)!
For https://reviews.llvm.org/D50222
llvm-svn: 341047
Check that Machine CSE correctly handles during the transformation, the
debug location information for local variables.
Differential Revision: https://reviews.llvm.org/D50887
llvm-svn: 341025
We now only add +64bit to the CPU string for "generic" CPU. All other CPU names are assumed to have the feature flag already set if they support 64-bit. I've remove the implies from CMPXCHG8 so that Feature64Bit only comes in via CPUs or user passing -mattr=+64bit.
I've changed the assert to a report_fatal_error so it's not lost in Release builds.
The test updates are to fix things that tripped the new error.
Differential Revision: https://reviews.llvm.org/D51231
llvm-svn: 341022
Variables declared with the dllimport attribute are accessed via a
stub variable named __imp_<var>. In MinGW configurations, variables that
aren't declared with a dllimport attribute might still end up imported
from another DLL with runtime pseudo relocs.
For x86_64, this avoids the risk that the target is out of range
for a 32 bit PC relative reference, in case the target DLL is loaded
further than 4 GB from the reference. It also avoids having to make the
text section writable at runtime when doing the runtime fixups, which
makes it worthwhile to do for i386 as well.
Add stub variables for all dso local data references where a definition
of the variable isn't visible within the module, since the DLL data
autoimporting might make them imported even though they are marked as
dso local within LLVM.
Don't do this for variables that actually are defined within the same
module, since we then know for sure that it actually is dso local.
Don't do this for references to functions, since there's no need for
runtime pseudo relocations for autoimporting them; if a function from
a different DLL is called without the appropriate dllimport attribute,
the call just gets routed via a thunk instead.
GCC does something similar since 4.9 (when compiling with -mcmodel=medium
or large; from that version, medium is the default code model for x86_64
mingw), but only for x86_64.
Differential Revision: https://reviews.llvm.org/D51288
llvm-svn: 340942
Adjust missed test to avoid the X / X -> 1 & X % X -> 0 folds while keeping their original purposes.
Differential Revision: https://reviews.llvm.org/D50636
llvm-svn: 340917
Adjust tests to avoid the X / X -> 1 & X % X -> 0 folds while keeping their original purposes.
Differential Revision: https://reviews.llvm.org/D50636
llvm-svn: 340916
Noticed while looking at D49562 codegen - we can avoid a large constant mask load and a slow VPBLENDVB select op by using VPBLENDW+VPBLENDD instead.
TODO: As discussed on the patch, we should investigate adding VPBLENDVB handling to target shuffle combining as well, that will allow us to extend this to VPBLENDW+VPBLENDW+VPBLENDD.
Differential Revision: https://reviews.llvm.org/D50074
llvm-svn: 340913
Summary: This is split out from D41062 to cover the code in LegalVectorTypes.cpp
Reviewers: RKSimon, spatel, efriedma
Reviewed By: efriedma
Subscribers: sdardis, jvesely, nhaehnle, jrtc27, atanasyan, llvm-commits
Differential Revision: https://reviews.llvm.org/D51337
llvm-svn: 340891
These are intrinsics for supporting kadd builtins in clang. These builtins are already in gcc to implement intrinsics from icc. Though they are missing from the Intel Intrinsics Guide.
This instruction adds two mask registers together as if they were scalar rather than a vXi1. We might be able to get away with a bitcast to scalar and a normal add instruction, but that would require DAG combine smarts in the backend to recoqnize add+bitcast. For now I'd prefer to go with the easiest implementation so we can get these builtins in to clang with good codegen.
Differential Revision: https://reviews.llvm.org/D51370
llvm-svn: 340869
This patch creates the shift mask and actual shift using the vXi16 vector shift ops.
Differential Revision: https://reviews.llvm.org/D51263
llvm-svn: 340813
We're using a 256-bit PACKUS to do the truncation, but that instruction operates on 128-bit lanes. So previously we shuffled first to rearrange the lanes. But that requires 2 shuffles. Instead we can shuffle after the PACKUS using a single VPERMQ. This matches what our normal LowerTRUNCATE code does when it uses PACKUS.
Differential Revision: https://reviews.llvm.org/D51284
llvm-svn: 340757
InstCombine mucks these up a bit. So we need to do some additional pattern matching to fix it. There are a still a few special cases not handled, but this covers the general case.
Differential Revision: https://reviews.llvm.org/D50952
llvm-svn: 340756
Summary:
This commit adds the case of tail calling a sret function from a non-sret
function when both functions have the C calling convention.
llvm-svn: 340737
Summary:
Remove unnecessary lines from `sibcall.ll` and rename labels according
to @RKSimon's recommendations in the D45653 conversation.
llvm-svn: 340735
Summary:
Previously most CPUs inherited cmov support through Feature64Bit(or FeatureCMPXCHG16HB implying Feature64Bit) or FeatureSSE1.
This has the surprising side effect that -mattr=-cmov causes an assert to fire in 64-bit mode because it clears the Feature64Bit. Or in 32-bit mode, -mattr=-cmov disables any sse/avx features which seems surprising.
This patch removes the implication and instead updates hasCMOV in X86Subtarget to check SSE1 or is64Bit in addition to the regular cmov flag. This should keep most things working the way they did before. I don't believe there is a way to specific "-cmov" directly from clang so this should only effect our lower level tools.
This does stop -mattr=cx16(cmpxchg16b) from implying cmov is enabled via the 64bit flag as you can see from one of the changed tests. But that was a 32-bit test so I don't know why it enabled cx16 anyway.
For the other test I had to add -sse to override the new sse check in hasCMOV.
Reviewers: RKSimon, DavidKreitzer, spatel
Reviewed By: RKSimon
Subscribers: llvm-commits, jfb
Differential Revision: https://reviews.llvm.org/D51228
llvm-svn: 340707
Summary: This matches gcc and one cpuid dump I found online. Given that these are considered 7th generation x86 CPU it seems likely they support cmov since cmov was added by Intel in their 6th generation.
Reviewers: RKSimon, spatel
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D51264
llvm-svn: 340706
I noticed this along with the patterns in D51125, but when the index is variable,
we don't convert insertelement into a build_vector.
For x86, that means these get expanded at legalization time into the loading/spilling
code that we see in the tests. I think it's always better to avoid going to memory on
these, and we get the optimal 'broadcast' if it's available.
I suspect other targets may want to look at enabling the hook. AArch64 and AMDGPU have
regression tests that would be affected (although I did not check what would happen in
those cases). In the most basic cases shown here, AArch64 would probably do much
better with a splat.
Differential Revision: https://reviews.llvm.org/D51186
llvm-svn: 340705
Summary:
The only time vector SMUL_LOHI/UMUL_LOHI nodes are created is during division/remainder lowering. If its created before op legalization, generic DAGCombine immediately turns that SMUL_LOHI/UMUL_LOHI into a MULHS/MULHU since only the upper half is used. That node will stick around through vector op legalization and will be turned back into UMUL_LOHI/SMUL_LOHI during op legalization. It will then be custom lowered by the X86 backend. Due to this two step lowering the vector shuffles created by the custom lowering get legalized after their inputs rather than before. This prevents the shuffles from being combined with any build_vector of constants.
This patch uses changes vXi32 to use MULHS/MULHU instead. This is what the later DAG combine did anyway. But by skipping the change back to UMUL_LOHI/SMUL_LOHI we lower it before any constant BUILD_VECTORS. This allows the vector_shuffle creation to constant fold with the build_vectors. This accounts for the test changes here.
Reviewers: RKSimon, spatel
Reviewed By: RKSimon
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D51254
llvm-svn: 340690
This is a preliminary step for a preliminary step for D50992.
I noticed that x86 often misses chances to load a scalar directly
into a vector register.
So this patch is just allowing more of those cases to match a
broadcast op in lowerBuildVectorAsBroadcast(). The old code comment
said it doesn't make sense to use a broadcast when we're loading a
single element and everything else is undef, but I think that's the
best case in the improved tests in insert-loaded-scalar.ll. We avoid
scalar-to-vector-register move and/or less efficient shuffling.
Note that there are some existing types that were already producing
a broadcast, but that happens semi-accidentally. Ie, it's not
happening as part of lowerBuildVectorAsBroadcast(). The build vector
gets expanded into load + shuffle, and then shuffle lowering produces
the broadcast.
Description of the other test diffs:
1. avx-basic.ll - replacing load+shufle is a win.
2. sse3-avx-addsub-2.ll - vmovddup vs. vbroadcastss is neutral
3. sse41.ll - don't care - we convert that intrinsic to generic IR now, so this test is deprecated
4. vector-shuffle-128-v8.ll / vector-shuffle-256-v16.ll - pshufb alternatives with an extra instruction are not obviously bad
Differential Revision: https://reviews.llvm.org/D51125
llvm-svn: 340685
Summary:
When computeIntervals is looking through COPY instruction to
extend the location mapping for a debug variable it did not
handle subregisters correctly.
For example
DBG_VALUE debug-use %0.sub_8bit_hi, ...
%1:gr16 = COPY %0
was transformed into
DBG_VALUE debug-use %0.sub_8bit_hi, ...
%1:gr16 = COPY %0
DBG_VALUE debug-use %1, ...
So the subregister index was missing in the added DBG_VALUE.
As long as the subreg refered to the least significant bits
of the superreg, then I guess we could get the correct
result in a debugger even when referring to the superreg.
But as in the example above when the subreg refers to other
parts of the superreg, then debuginfo would be incorrect.
I'm not sure exactly how to fix this properly, so this patch
just avoids looking through the COPY when there is a subreg
involved (for more info, see the FIXME added in the code).
Reviewers: rnk, aprantl
Reviewed By: aprantl
Subscribers: JDevlieghere, llvm-commits
Tags: #debug-info
Differential Revision: https://reviews.llvm.org/D50788
llvm-svn: 340679
Firstly, require the symbol to be used within the module. If a
symbol is unused within a module, then by definition it cannot be
address-significant within that module. This condition is useful on all
platforms because it could make symbol tables smaller -- without this
change, emitting an address-significance table could cause otherwise
unused undefined symbols to be added to the object file.
But this change is necessary with COFF specifically in order to
preserve the property that an unreferenced undefined symbol in an IR
module does not result in a link failure. This is already the case for
ELF because ELF linkers only reject links with unresolved symbols if
there is a relocation to that symbol, but COFF linkers require all
undefined symbols to be resolved regardless of relocations. So if
a module contains an unreferenced undefined symbol, we need to make
sure not to add it to the address-significance table (and thus the
symbol table) in case it doesn't end up resolved at link time.
Secondly, do not add dllimport symbols to the table. These symbols
won't be able to be resolved because their definitions live in another
module and are accessed via the IAT, and the address-significance
table has no effect on other modules anyway. It wouldn't make sense
to add the IAT entry symbol to the address-significance table either
because the IAT entry isn't address-significant -- the generated code
never takes its address.
Differential Revision: https://reviews.llvm.org/D51199
llvm-svn: 340648
The variable index pattern is different than the constant index
cases as shown in D51125. We might want to splat regardless of
whether the scalar is loaded from memory or transferred from GPR.
llvm-svn: 340565
subtarget features for indirect calls and indirect branches.
This is in preparation for enabling *only* the call retpolines when
using speculative load hardening.
I've continued to use subtarget features for now as they continue to
seem the best fit given the lack of other retpoline like constructs so
far.
The LLVM side is pretty simple. I'd like to eventually get rid of the
old feature, but not sure what backwards compatibility issues that will
cause.
This does remove the "implies" from requesting an external thunk. This
always seemed somewhat questionable and is now clearly not desirable --
you specify a thunk the same way no matter which set of things are
getting retpolines.
I really want to keep this nicely isolated from end users and just an
LLVM implementation detail, so I've moved the `-mretpoline` flag in
Clang to no longer rely on a specific subtarget feature by that name and
instead to be directly handled. In some ways this is simpler, but in
order to preserve existing behavior I've had to add some fallback code
so that users who relied on merely passing -mretpoline-external-thunk
continue to get the same behavior. We should eventually remove this
I suspect (we have never tested that it works!) but I've not done that
in this patch.
Differential Revision: https://reviews.llvm.org/D51150
llvm-svn: 340515
Previously we asumed a vector reduction add is part of a loop and one of the input is a phi. But the code in SelectionDAGBuilder that sets vector reduction flag handles more cases than that. It just requires that the use chain ends in a horizontal reduction. And there are no other uses. This means it can handle unrolled reduction loops.
If the initial value of the reduction was 0, an unrolled loop would begin with a vector reduction add that has two sad inputs. Previously we would only transform one side of the add, but for this case we need to transform both sides.
I've created a lambda to reuse some of the code for both sides. And fixed the variables names to remove reference to "phi".
Differential Revision: https://reviews.llvm.org/D50817
llvm-svn: 340478
This solves the motivating case from:
https://bugs.llvm.org/show_bug.cgi?id=38527
If we are legalizing an FP vector op that maps to 1 of the LLVM intrinsics that mimic libm calls,
but we're going to end up with scalar libcalls for that vector type anyway, then we should unroll
the vector op into scalars before widening. This avoids libcalls because we've lost the knowledge
that some of the scalar elements are undef.
Differential Revision: https://reviews.llvm.org/D50791
llvm-svn: 340469
Inspired by what AArch64 does for shifts, this patch attempts to replace shift amounts with neg if we can.
This is done directly as part of isel so its as late as possible to avoid breaking some BZHI patterns since those patterns need an unmasked (32-n) to be correct.
To avoid manual load folding and custom instruction selection for the negate. I've inserted new nodes in the DAG above the shift node in topological order.
Differential Revision: https://reviews.llvm.org/D48789
llvm-svn: 340441
Summary:
When RegisterCoalescer::reMaterializeTrivialDef is substituting
a register use in a DBG_VALUE instruction, and the old register
is a subreg, and the new register is a physical register,
then we need to use substPhysReg in order to extract the correct
subreg.
Reviewers: wmi, aprantl
Reviewed By: wmi
Subscribers: hiraditya, MatzeB, qcolombet, tpr, llvm-commits
Differential Revision: https://reviews.llvm.org/D50844
llvm-svn: 340326
The test demonstrates over-complicated codegen for a udiv that only has one divisor that doesn't equal 1. This should have allowed the codegen to be a lot simpler (uniform shifts etc.) but only the SSE2 manages to make use of this......
llvm-svn: 340313
DAGCombiner doesn't pay attention to whether constants are opaque before doing the div by constant optimization. So BypassSlowDivision shouldn't introduce control flow that would make DAGCombiner unable to see an opaque constant. This can occur when a div and rem of the same constant are used in the same basic block. it will be hoisted, but not leave the block.
Longer term we probably need to look into the X86 immediate cost model used by constant hoisting and maybe not mark div/rem immediates for hoisting at all.
This fixes the case from PR38649.
Differential Revision: https://reviews.llvm.org/D51000
llvm-svn: 340303
During combining, ReduceLoadWdith is used to combine AND nodes that
mask loads into narrow loads. This patch allows the mask to be a
shifted constant. This results in a narrow load which is then left
shifted to compensate for the new offset.
Differential Revision: https://reviews.llvm.org/D50432
llvm-svn: 340261
This reduces most of the sdiv stages (the MULHS, shifts etc.) to just zero/identity values and use the numerator scale factor to multiply by +1/-1.
llvm-svn: 340260
Summary:
RegisterCoalescer::reMaterializeTrivialDef used to assert that
the input register was live in. But as shown by the new
coalesce-dead-lanes.mir test case that seems to be a valid
scenario. We now return false instead of the assert, simply
avoiding to remat the dead def.
Normally a COPY of an undef value is eliminated by
eliminateUndefCopy(). Although we only do that when the
destination isn't a physical register. So the situation
above should be limited to the case when we copy an undef
value to a physical register.
Reviewers: kparzysz, wmi, tpr
Reviewed By: kparzysz
Subscribers: MatzeB, qcolombet, tpr, llvm-commits
Differential Revision: https://reviews.llvm.org/D50842
llvm-svn: 340255
Due to some splat handling code in getVectorShuffle, its possible for NewV1/NewV2 to have their mask modified from what is requested. This can lead to cycles being created in the DAG.
This patch examines the returned mask and makes sure its different. Long term we may need to look closer at that splat code in getVectorShuffle, or add more splat awareness to getVectorShuffle.
Fixes PR38639
Differential Revision: https://reviews.llvm.org/D50981
llvm-svn: 340214
We can safely avoid interfering with the subus combine if both inputs are freely truncatable. Either both extends, or an extend and a constant vector.
Differential Revision: https://reviews.llvm.org/D50878
llvm-svn: 340212
Only adds support to the existing 'large element' scalar/vector to 'small element' vector bitcasts.
Handle the case where the sign bit extends to only part of the small elements.
llvm-svn: 340169
Only adds support to the existing 'large element' scalar/vector to 'small element' vector bitcasts.
The next step would be to support cases where the large elements aren't all sign bits, and determine the small element equivalent based on the demanded elements.
llvm-svn: 340143
We were basically assuming only one operand of the compare could be an ADD node and using that to swap operands. But we can have a normal add followed by a saturing add.
This rewrites the canonicalization to just be based on the condition code.
llvm-svn: 340134
The code already support 128 and 256 and even knows to split 256 for AVX1. So we really just needed to stop looking for specific VTs and subtarget features and just look for legal VTs with i8/i16 elements.
While there, add some curly braces around outer if statement bodies that contain only another if. It makes all the closing curly braces look more regular.
llvm-svn: 340128
Summary:
I believe this restores the behavior we had before r339147.
Fixes PR38622.
Reviewers: RKSimon, chandlerc, spatel
Reviewed By: chandlerc
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D50936
llvm-svn: 340120
Extending the concept introduced in D49562, this patch lowers constant vXi8 ISD::SRL/ISD::SRA by zero/sign extending to vXi16 and using PMULLW and then truncating the high 8 bits of the result.
Differential Revision: https://reviews.llvm.org/D50781
llvm-svn: 340062
* -march=x86-64 -> -mtriple=x86_64-unknown-linux to avoid _ prefixes to
symbols
* add -start-before to avoid running the whole codegen on the IR. I
assumed it is meant to be running after X86SpeculativeLoadHardening.
llvm-svn: 340034
test/CodeGen/X86/shadow-stack.ll has the following machine verifier
errors:
```
*** Bad machine code: Using a killed virtual register ***
- function: bar
- basic block: %bb.6 entry (0x7fdc81857818)
- instruction: %3:gr64 = MOV64rm killed %2:gr64, 1, $noreg, 8, $noreg
- operand 1: killed %2:gr64
*** Bad machine code: Using a killed virtual register ***
- function: bar
- basic block: %bb.6 entry (0x7fdc81857818)
- instruction: $rsp = MOV64rm killed %2:gr64, 1, $noreg, 16, $noreg
- operand 1: killed %2:gr64
*** Bad machine code: Virtual register killed in block, but needed live out. ***
- function: bar
- basic block: %bb.2 entry (0x7fdc818574f8)
Virtual register %2 is used after the block.
```
The fix here is to only copy the machine operand's register without the
kill flags for all the instructions except the very last one of the
sequence.
I had to insert dummy PHIs in the test case to force the NoPHI function
property to be set to false. More on this here: https://llvm.org/PR38439
Differential Revision: https://reviews.llvm.org/D50260
llvm-svn: 340033
Add support for cases where only some c1+c2 results exceed the max bitshift, clamping accordingly.
Differential Revision: https://reviews.llvm.org/D35722
llvm-svn: 340010
well as MIR parsing support for `MCSymbol` `MachineOperand`s.
The only real way to test pre- and post-instruction symbol support is to
use them in operands, so I ended up implementing that within the patch
as well. I can split out the operand support if folks really want but it
doesn't really seem worth it.
The functional implementation of pre- and post-instruction symbols is
now *completely trivial*. Two tiny bits of code in the (misnamed)
AsmPrinter. It should be completely target independent as well. We emit
these exactly the same way as we emit basic block labels. Most of the
code here is to give full dumping, MIR printing, and MIR parsing support
so that we can write useful tests.
The MIR parsing of MC symbol operands still isn't 100%, as it forces the
symbols to be non-temporary and non-local symbols with names. However,
those names often can encode most (if not all) of the special semantics
desired, and unnamed symbols seem especially annoying to serialize and
de-serialize. While this isn't perfect or full support, it seems plenty
to write tests that exercise usage of these kinds of operands.
The MIR support for pre-and post-instruction symbols was quite
straightforward. I chose to print them out in an as-if-operand syntax
similar to debug locations as this seemed the cleanest way and let me
use nice introducer tokens rather than inventing more magic punctuation
like we use for memoperands.
However, supporting MIR-based parsing of these symbols caused me to
change the design of the symbol support to allow setting arbitrary
symbols. Without this, I don't see any reasonable way to test things
with MIR.
Differential Revision: https://reviews.llvm.org/D50833
llvm-svn: 339962
When nodes are reassociated the vector-reduction flag gets lost.
The test case is here is what would happen if you had a sum of absolute differences loop that started with a non-zero but contant sum and that loop was unrolled. The vectorizer will generate a constant vector for the initial value. And DAGCombiner reassociate tries to move it down the addition tree erasing the vector-reduction flag. Interestingly this moves constants the opposite direction of the reassociate IR pass.
I've chosen to just punt on the reassociate, but I suppose we could maybe preserve the flag if both nodes have it set.
Differential Revision: https://reviews.llvm.org/D50827
llvm-svn: 339946
Normally the peephole pass converts EXTRACT_SUBREG to COPY instructions. But we're after peephole so we can't rely on it to clean these up.
To fix this, the eflags pass now emits a COPY with a subreg input.
I also noticed that in 32-bit mode we need to constrain the input to the copy to ensure the subreg is valid. Otherwise we'll fail verify-machineinstrs
Differential Revision: https://reviews.llvm.org/D50656
llvm-svn: 339945
There is no way in the universe, that doing a full-width division in
software will be faster than doing overflowing multiplication in
software in the first place, especially given that this same full-width
multiplication needs to be done anyway.
This patch replaces the previous implementation with a direct lowering
into an overflowing multiplication algorithm based on half-width
operations.
Correctness of the algorithm was verified by exhaustively checking the
output of this algorithm for overflowing multiplication of 16 bit
integers against an obviously correct widening multiplication. Baring
any oversights introduced by porting the algorithm to DAG, confidence in
correctness of this algorithm is extremely high.
Following table shows the change in both t = runtime and s = space. The
change is expressed as a multiplier of original, so anything under 1 is
“better” and anything above 1 is worse.
+-------+-----------+-----------+-------------+-------------+
| Arch | u64*u64 t | u64*u64 s | u128*u128 t | u128*u128 s |
+-------+-----------+-----------+-------------+-------------+
| X64 | - | - | ~0.5 | ~0.64 |
| i686 | ~0.5 | ~0.6666 | ~0.05 | ~0.9 |
| armv7 | - | ~0.75 | - | ~1.4 |
+-------+-----------+-----------+-------------+-------------+
Performance numbers have been collected by running overflowing
multiplication in a loop under `perf` on two x86_64 (one Intel Haswell,
other AMD Ryzen) based machines. Size numbers have been collected by
looking at the size of function containing an overflowing multiply in
a loop.
All in all, it can be seen that both performance and size has improved
except in the case of armv7 where code size has regressed for 128-bit
multiply. u128*u128 overflowing multiply on 32-bit platforms seem to
benefit from this change a lot, taking only 5% of the time compared to
original algorithm to calculate the same thing.
The final benefit of this change is that LLVM is now capable of lowering
the overflowing unsigned multiply for integers of any bit-width as long
as the target is capable of lowering regular multiplication for the same
bit-width. Previously, 128-bit overflowing multiply was the widest
possible.
Patch by Simonas Kazlauskas!
Differential Revision: https://reviews.llvm.org/D50310
llvm-svn: 339922
This patch refactors the existing TargetLowering::BuildSDIV base implementation to support non-uniform constant vector denominators.
This is the last patch necessary to close PR36545
Differential Revision: https://reviews.llvm.org/D50765
llvm-svn: 339908
a shorter name ('x86-slh') for the internal flags and pass name.
Without this, you can't use the -stop-after or -stop-before
infrastructure. I seem to have just missed this when originally adding
the pass.
The shorter name solves two problems. First, the flag names were ...
really long and hard to type/manage. Second, the pass name can't be the
exact same as the flag name used to enable this, and there are already
some users of that flag name so I'm avoiding changing it unnecessarily.
llvm-svn: 339836
To lower this we now create a new V1 containing the low half of both sources and a new V2 containing the upper half of both sources. Then we created a repeated lane shuffle of those new sources to create the final result.
This fixes PR35833
Differential Revison: https://reviews.llvm.org/D41794
llvm-svn: 339818
This commit adds new sibling-call test cases, so it will be possible to see
how these test cases will be changed after applying D45653.
See D45653 for details.
llvm-svn: 339760
This patch refactors the existing BuildExactSDIV implementation to support non-uniform constant vector denominators.
Differential Revision: https://reviews.llvm.org/D50392
llvm-svn: 339756
rL339686 added the case where a faux shuffle might have repeated shuffle inputs coming from either side of the OR().
This patch improves the insertion of the inputs into the source ops lists to account for this, as well as making it trivial to add support for shuffles with more than 2 inputs in the future.
llvm-svn: 339696
Summary: This revision improves previous version (rL330322) which has been reverted due to crashes.
This is the patch that lowers x86 intrinsics to native IR
in order to enable optimizations. The patch also includes folding
of previously missing saturation patterns so that IR emits the same
machine instructions as the intrinsics.
Reviewers: craig.topper, spatel, RKSimon
Reviewed By: craig.topper
Subscribers: mike.dvoretsky, DavidKreitzer, sroland, llvm-commits
Differential Revision: https://reviews.llvm.org/D46179
llvm-svn: 339650
This is another variation of PR38533. In this case, the result type of the bitcast is legal and 16-bits wide, but not a scalar integer. So we need to emit the convert to i16 and then bitcast it to the true result type. This new bitcast will be further type legalized if necessary.
llvm-svn: 339536
Previously if the result type was a vector, we emitted a FP_TO_FP16 with a vector result type which isn't valid.
This is basically the opposite case of the root cause of PR38533.
llvm-svn: 339535
Fixes PR37524.
The exception handling encodings for x86_64 in kernel code model
has been changed with r309884. Restore it to correct ones. These
encodings include PersonalityEncoding, LSDAEncoding and
TTypeEncoding.
Differential Revision: https://reviews.llvm.org/D50490
llvm-svn: 339534
Now we switch to the subregister in expandPostRAPseudos where we already switched the opcode.
This simplifies a few isel patterns that used the pseudo directly. And magically seems to have improved our ability to CSE it in the undef-label.ll test.
llvm-svn: 339496
Summary: This change provides a common optimization path for both Unsafe and FMF driven optimization for this fsub fold adding reassociation, as it the flag that most closely represents the translation
Reviewers: spatel, wristow, arsenm
Reviewed By: spatel
Subscribers: wdng
Differential Revision: https://reviews.llvm.org/D50195
llvm-svn: 339357
As discussed on D41794, we have many cases where we fail to combine shuffles as the input operands have other uses.
This patch permits these shuffles to be combined as long as they don't introduce additional variable shuffle masks, which should reduce instruction dependencies and allow the total number of shuffles to still drop without increasing the constant pool.
However, this may mean that some memory folds may no longer occur, and on pre-AVX require the occasional extra register move.
This also exposes some poor PMULDQ/PMULUDQ codegen which was doing unnecessary upper/lower calculations which will in fact fold to zero/undef - the fix will be added in a followup commit.
Differential Revision: https://reviews.llvm.org/D50328
llvm-svn: 339335
isNegatibleForFree() should not matter here (as the test diffs show)
because it's always a win to replace an fsub+fadd with fneg. The
problem in D50195 persists because either (1) we are doing these
folds in the wrong order or (2) we're missing another fold for fadd.
llvm-svn: 339299
Summary:
Currently, in line with GCC, when specifying reserved registers like sp or pc on an inline asm() clobber list, we don't always preserve the original value across the statement. And in general, overwriting reserved registers can have surprising results.
For example:
```
extern int bar(int[]);
int foo(int i) {
int a[i]; // VLA
asm volatile(
"mov r7, #1"
:
:
: "r7"
);
return 1 + bar(a);
}
```
Compiled for thumb, this gives:
```
$ clang --target=arm-arm-none-eabi -march=armv7a -c test.c -o - -S -O1 -mthumb
...
foo:
.fnstart
@ %bb.0: @ %entry
.save {r4, r5, r6, r7, lr}
push {r4, r5, r6, r7, lr}
.setfp r7, sp, #12
add r7, sp, #12
.pad #4
sub sp, #4
movs r1, #7
add.w r0, r1, r0, lsl #2
bic r0, r0, #7
sub.w r0, sp, r0
mov sp, r0
@APP
mov.w r7, #1
@NO_APP
bl bar
adds r0, #1
sub.w r4, r7, #12
mov sp, r4
pop {r4, r5, r6, r7, pc}
...
```
r7 is used as the frame pointer for thumb targets, and this function needs to restore the SP from the FP because of the variable-length stack allocation a. r7 is clobbered by the inline assembly (and r7 is included in the clobber list), but LLVM does not preserve the value of the frame pointer across the assembly block.
This type of behavior is similar to GCC's and has been discussed on the bugtracker: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=11807 . No consensus seemed to have been reached on the way forward. Clang behavior has briefly been discussed on the CFE mailing (starting here: http://lists.llvm.org/pipermail/cfe-dev/2018-July/058392.html). I've opted for following Eli Friedman's advice to print warnings when there are reserved registers on the clobber list so as not to diverge from GCC behavior for now.
The patch uses MachineRegisterInfo's target-specific knowledge of reserved registers, just before we convert the inline asm string in the AsmPrinter.
If we find a reserved register, we print a warning:
```
repro.c:6:7: warning: inline asm clobber list contains reserved registers: R7 [-Winline-asm]
"mov r7, #1"
^
```
Reviewers: eli.friedman, olista01, javed.absar, efriedma
Reviewed By: efriedma
Subscribers: efriedma, eraman, kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D49727
llvm-svn: 339257
Provide a pass-through of the numerator for divide by one cases - this is the same approach we take in DAGCombiner::visitSDIVLike.
I investigated whether we could achieve this by magic MULHU/SRL values but nothing appeared to work as we don't have a way for MULHU(x,c) -> x
llvm-svn: 339254
Making the test use urem relies on it calling udiv-like combines, but the real issue is with the udiv so we're better off using that directly.
llvm-svn: 339247
Scatter could have multiple identical indices. We need to maintain sequential order. We get this right in LegalizeVectorTypes, but not in this code.
Differential Revision: https://reviews.llvm.org/D50374
llvm-svn: 339157
This patch refactors the existing TargetLowering::BuildUDIV base implementation to support non-uniform constant vector denominators.
It also includes a fold for MULHU by pow2 constants to SRL which can now more readily occur from BuildUDIV.
Differential Revision: https://reviews.llvm.org/D49248
llvm-svn: 339121
This assert fires when attempting to extract a subregister from the
global PIC base register. This virtual register SD node is not in the
VRBaseMap, so we shouldn't call getVR to look it up there. If this is a
RegisterSDNode, we should be able to use the virtual register directly.
Fixes PR38385
llvm-svn: 339056
Summary:
Expand isFNEG so that we generate the appropriate F(N)M(ADD|SUB)
instructions in more cases. For example, the following sequence
a = _mm256_broadcast_ss(f)
d = _mm256_fnmadd_ps(a, b, c)
generates an fsub and fma without this patch and an fnma with this
change.
Reviewers: craig.topper
Subscribers: llvm-commits, davidxl, wmi
Differential Revision: https://reviews.llvm.org/D48467
llvm-svn: 339043
If the store is volatile this might be a memory mapped IO access. In that case we shouldn't generate a load that didn't exist in the source
Differential Revision: https://reviews.llvm.org/D50270
llvm-svn: 339041
for all the uses from the same def is done.
We run into a compile time problem with flex generated code combined with
`-fno-jump-tables`. The cause is that machineLICM hoists a lot of invariants
outside of a big loop, and drastically increases the compile time in global
register splitting and copy coalescing. https://reviews.llvm.org/D49353
relieves the problem in global splitting. This patch is to handle the problem
in copy coalescing.
About the situation where the problem in copy coalescing happens. After
machineLICM, we have several defs outside of a big loop with hundreds or
thousands of uses inside the loop. Rematerialization in copy coalescing
happens for each use and everytime rematerialization is done, shrinkToUses
will be called to update the huge live interval. Because we have 'n' uses
for a def, and each live interval update will have at least 'n' complexity,
the total update work is n^2.
To fix the problem, we try to do the live interval update work in a collective
way. If a def has many copylike uses larger than a threshold, each time
rematerialization is done for one of those uses, we won't do the live interval
update in time but delay that work until rematerialization for all those uses
are completed, so we only have to do the live interval update work once.
Delaying the live interval update could potentially change the copy coalescing
result, so we hope to limit that change to those defs with many
(like above a hundred) copylike uses, and the cutoff can be adjusted by the
option -mllvm -late-remat-update-threshold=xxx.
Differential Revision: https://reviews.llvm.org/D49519
llvm-svn: 339035
These tests were clearly auto-generated when they were converted to
FileCheck back in r80019 (2009), but we didn't have a fancy script to
keep them up to date then. I've reviewed the diff, and we should be
generating the exact same code sequences we used to.
After this, I plan to commit a change that changes our output slightly,
but in a way that is still correct. It will generate a large diff, and I
want it to be clearly correct, so I am regenerating these checks in
preparation for that.
llvm-svn: 338928
- Remove -asm-verbose=0 from every llc command. The tests still pass.
- Reorder the RUN lines to match CHECKs.
- Use -LABEL like update_llc_test_checks.py does.
llvm-svn: 338927
Put the LLVM IR at the bottom of the function instead of the top. In my
next patch, I will run update_llc_test_checks.py on this file, and I
want to only highlight the diffs in the CHECK lines. Hopefully by doing
this change first, the patch will be more understandable.
llvm-svn: 338926
At one point in time acquire implied mayLoad and mayStore as did release. Thus we needed separate pseudos that also carried that property. This appears to no longer be the case. I believe it was changed in 2012 with a comment saying that atomic memory accesses are marked volatile which preserves the ordering.
So from what I can tell we shouldn't need additional pseudos since they aren't carry any flags that are different from the normal instructions. The only thing I can think of is that we may consider them for load folding candidates in the peephole pass now where we didn't before. If that's important hopefully there's something in the memory operand we can check to prevent the folding without relying on pseudo instructions.
Differential Revision: https://reviews.llvm.org/D50212
llvm-svn: 338925
Clang uses "ctpop & 1" to implement __builtin_parity. If the popcnt instruction isn't supported this generates a large amount of code to calculate the population count. Instead we can bisect the data down to a single byte using xor and then check the parity flag.
Even when popcnt is supported, its still a good idea to split 64-bit data on 32-bit targets using an xor in front of a single popcnt. Otherwise we get two popcnts and an add before the and.
I've specifically targeted this at the sizes supported by clang builtins, but we could generalize this if we think that's useful.
Differential Revision: https://reviews.llvm.org/D50165
llvm-svn: 338907
Basic pattern that leaves an unnecessary select on a rotation by zero result. This variant is trivial - the more general case with a compare+branch to prevent execution of undefined shifts is more tricky.
llvm-svn: 338833
There are a lot of permutations of types here generating a lot of patterns in the isel table. It's more efficient to just ReplaceUses and RemoveDeadNode from the Select function.
The test changes are because we have a some shuffle patterns that have a bitcast as their root node. But the behavior is identical to another instruction whose pattern doesn't start with a bitcast. So this isn't a functional change.
llvm-svn: 338824
Move all the patterns to X86InstrVecCompiler.td so we can keep SSE/AVX/AVX512 all in one place.
To save some patterns we'll use an existing DAG combine to convert f128 fand/for/fxor to integer when sse2 is enabled. This allows use to reuse all the existing patterns for v2i64.
I believe this now makes SHA instructions the only case where VEX/EVEX and legacy encoded instructions could be generated simultaneously.
llvm-svn: 338821
If the producing instruction is legacy encoded it doesn't implicitly zero the upper bits. This is important for the SHA instructions which don't have a VEX encoded version. We might also be able to hit this with the incomplete f128 support that hasn't been ported to VEX.
llvm-svn: 338812
These instructions perform the same operation, but the semantic of which operand is destroyed is reversed. If the same register is used as both operands we can change the execution domain without worrying about this difference.
Unfortunately, this really only works in cases where the input register is killed by the instruction. If its not killed, the two address isntruction pass inserts a copy that will become a move instruction. This makes the instruction use different physical registers that contain the same data at the time the unpck/movhlps executes. I've considered using a unary pseudo instruction with tied operand to trick the two address instruction pass. We could then expand the pseudo post regalloc to get the same physical register on both inputs.
Differential Revision: https://reviews.llvm.org/D50157
llvm-svn: 338735
We now emit a move of -1 before the cmov and do the addition after the cmov just like the case with an extra addition.
This may be slightly worse for code size, but is more consistent with other compilers. And we might be able to hoist the mov -1 outside of loops.
llvm-svn: 338613
Summary:
D25878, which added support for !absolute_symbol for normal X86 ISel,
did not add support for materializing references to absolute symbols for
X86 FastISel. This causes build failures because FastISel generates
PC-relative relocations for absolute symbols. Fall back to normal ISel
for references to !absolute_symbol GVs. Fix for PR38200.
Reviewers: pcc, craig.topper
Reviewed By: pcc
Subscribers: hiraditya, llvm-commits, kcc
Differential Revision: https://reviews.llvm.org/D50116
llvm-svn: 338599
The bug is visible in the constant-folded x86 tests. We can't use the
negated shift amount when the type is not power-of-2:
https://rise4fun.com/Alive/US1r
...so in that case, use the regular lowering that includes a select
to guard against a shift-by-bitwidth. This path is improved by only
calculating the modulo shift amount once now.
Also, improve the rotate (with power-of-2 size) lowering to use
a negate rather than subtract from bitwidth. This improves the
codegen whether we have a rotate instruction or not (although
we can still see that we're not matching to a legal rotate in
all cases).
llvm-svn: 338592
EFLAGS copy lowering.
If you have a branch of LLVM, you may want to cherrypick this. It is
extremely unlikely to hit this case empirically, but it will likely
manifest as an "impossible" branch being taken somewhere, and will be
... very hard to debug.
Hitting this requires complex conditions living across complex control
flow combined with some interesting memory (non-stack) initialized with
the results of a comparison. Also, because you have to arrange for an
EFLAGS copy to be in *just* the right place, almost anything you do to
the code will hide the bug. I was unable to reduce anything remotely
resembling a "good" test case from the place where I hit it, and so
instead I have constructed synthetic MIR testing that directly exercises
the bug in question (as well as the good behavior for completeness).
The issue is that we would mistakenly assume any SETcc with a valid
condition and an initial operand that was a register and a virtual
register at that to be a register *defining* SETcc...
It isn't though....
This would in turn cause us to test some other bizarre register,
typically the base pointer of some memory. Now, testing this register
and using that to branch on doesn't make any sense. It even fails the
machine verifier (if you are running it) due to the wrong register
class. But it will make it through LLVM, assemble, and it *looks*
fine... But wow do you get a very unsual and surprising branch taken in
your actual code.
The fix is to actually check what kind of SETcc instruction we're
dealing with. Because there are a bunch of them, I just test the
may-store bit in the instruction. I've also added an assert for sanity
that ensure we are, in fact, *defining* the register operand. =D
llvm-svn: 338481
we aren't incorrectly generating any of it when doing SLH.
There was a bug that only occured with SLH that very much looked like it
could be caused by bad unwind info, and so this was a prime suspect.
Turns out that everything is fine, but this way we'll *see* if we end
up, for example, putting things we shouldn't inside the prolog.
llvm-svn: 338480
As was done for vector rotations, we can efficiently use ISD::MULHU for vXi8/vXi16 ISD::SRL lowering.
Shift-by-zero cases are still problematic (mainly on v32i8 due to extra AND/ANDN/OR or VPBLENDVB blend masks but v8i16/v16i16 aren't great either if PBLENDW fails) so I've limited this first patch to known non-zero cases if we can't easily use PBLENDW.
Differential Revision: https://reviews.llvm.org/D49562
llvm-svn: 338407
Summary:
Similar to D49636, but for PMADDUBSW. This instruction has the additional complexity that the addition of the two products saturates to 16-bits rather than wrapping around. And one operand is treated as signed and the other as unsigned.
A C example that triggers this pattern
```
static const int N = 128;
int8_t A[2*N];
uint8_t B[2*N];
int16_t C[N];
void foo() {
for (int i = 0; i != N; ++i)
C[i] = MIN(MAX((int16_t)A[2*i]*(int16_t)B[2*i] + (int16_t)A[2*i+1]*(int16_t)B[2*i+1], -32768), 32767);
}
```
Reviewers: RKSimon, spatel, zvi
Reviewed By: RKSimon, zvi
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D49829
llvm-svn: 338402
This commit fixes two issues with the liveness information after the
call:
1) The code always spills RCX and RDX if InProlog == true, which results
in an use of undefined phys reg.
2) FinalReg, JoinReg, RoundedReg, SizeReg are not added as live-ins to
the basic blocks that use them, therefore they are seen undefined.
https://llvm.org/PR38376
Differential Revision: https://reviews.llvm.org/D50020
llvm-svn: 338400
In one place we checked X86Subtarget.slowLEA() to decide if the pass should run. But to decide what the pass should we only check isSLM. This resulted in Goldmont going down the Bonnell path.
llvm-svn: 338342
This is exchanging a sub-of-1 with add-of-minus-1:
https://rise4fun.com/Alive/plKAH
This is another step towards improving select-of-constants codegen (see D48970).
x86 is the motivating target, and those diffs all appear to be wins. PPC and AArch64 look neutral.
I've limited this to early combining (!LegalOperations) in case a target wants to reverse it, but
I think canonicalizing to 'add' is more likely to produce further transforms because we have more
folds for 'add'.
Differential Revision: https://reviews.llvm.org/D49924
llvm-svn: 338317
Summary:
Attempt to extract a shrl from a udiv or a shl from a mul if this allows a rotate to be formed. This targets cases where the input to a rotate pattern was a mul or udiv by a constant and InstCombine merged one of the shifts with the op.
Patch by: sameconrad (Sam Conrad)
Reviewers: RKSimon, craig.topper, spatel, lebedev.ri, javed.absar
Reviewed By: lebedev.ri
Subscribers: efriedma, kparzysz, llvm-commits
Differential Revision: https://reviews.llvm.org/D47681
llvm-svn: 338270
The machine verifier asserts with:
Assertion failed: (isMBB() && "Wrong MachineOperand accessor"), function getMBB, file ../include/llvm/CodeGen/MachineOperand.h, line 542.
It calls analyzeBranch which tries to call getMBB if the opcode is
JMP_1, but in this case we do:
JMP_1 @OUTLINED_FUNCTION
I believe we have to use TAILJMPd64 instead of JMP_1 since JMP_1 is used
with brtarget8.
Differential Revision: https://reviews.llvm.org/D49299
llvm-svn: 338237
The tests with a constant sub operand were added with rL338143,
but the potential transform doesn't have that requirement, so
adding more tests with variable operands.
llvm-svn: 338150
This is a follow-up suggested in D48970.
Alive proofs:
https://rise4fun.com/Alive/sII
We can eliminate an instruction in the usual select-of-constants
to bit hack transform by adjusting the add/sub with constant.
This is always a win.
There are more transforms that are likely wins, but they may need
target hooks in case some targets do not benefit.
This is another step towards making up for canonicalizing to
select-of-constants in rL331486.
llvm-svn: 338132
Not sure why they were being explicitly excluded, but I believe all the math inside the if works. I changed the absolute value to be uint64_t instead of int64_t so INT64_MIN+1 wouldn't be signed wrap.
llvm-svn: 338101
Summary:
This is the pattern you get from the loop vectorizer for something like this
int16_t A[1024];
int16_t B[1024];
int32_t C[512];
void pmaddwd() {
for (int i = 0; i != 512; ++i)
C[i] = (A[2*i]*B[2*i]) + (A[2*i+1]*B[2*i+1]);
}
In this case we will have (add (mul (build_vector), (build_vector)), (mul (build_vector), (build_vector))). This is different than the pattern we currently match which has the build_vectors between an add and a single multiply. I'm not sure what C code would get you that pattern.
Reviewers: RKSimon, spatel, zvi
Reviewed By: zvi
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D49636
llvm-svn: 338097
If this happens the operands aren't updated and the existing node is returned. Make sure we pass this existing node up to the DAG combiner so that a proper replacement happens. Otherwise we get stuck in an infinite loop with an unoptimized node.
llvm-svn: 338090
Masked loads are calling DAG.getRoot rather than calling SelectionDAGBuilder::getRoot, which means the PendingLoads weren't emptied to update the root and create any needed TokenFactor. So it would be incorrect to call setRoot for the masked load.
This patch instead adds the masked load to PendingLoads so that the root doesn't get update until a store or scatter or something happens.. Alternatively, we could call SelectionDAGBuilder::getRoot before it, but that would create unnecessary serialization.
llvm-svn: 338085
Summary:
A follow-up for D49266 / rL337166.
At least one of these cases is more canonical,
so we really do have to handle it.
https://godbolt.org/g/pkzP3Xhttps://rise4fun.com/Alive/pQyhZZ
We won't get to these cases with I1 being -1,
as that will be constant-folded to true or false.
I'm also not sure we actually hit the 'ule' case,
but i think the worst think that could happen is that being dead code.
Reviewers: spatel, craig.topper, RKSimon, javed.absar, efriedma
Reviewed By: spatel
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D49497
llvm-svn: 338044
This reverts commit r337951.
While that kind of shared constant generally works fine in a MinGW
setting, it broke some cases of inline assembly that worked before:
$ cat const-asm.c
int MULH(int a, int b) {
int rt, dummy;
__asm__ (
"imull %3"
:"=d"(rt), "=a"(dummy)
:"a"(a), "rm"(b)
);
return rt;
}
int func(int a) {
return MULH(a, 1);
}
$ clang -target x86_64-win32-gnu -c const-asm.c -O2
const-asm.c:4:9: error: invalid variant '00000001'
"imull %3"
^
<inline asm>:1:15: note: instantiated into assembly here
imull __real@00000001(%rip)
^
A similar error is produced for i686 as well. The same test with a
target of x86_64-win32-msvc or i686-win32-msvc works fine.
llvm-svn: 338018
I'm not sure if this was trying to avoid optimizing the new nodes further or what. Or maybe to prevent a cycle if something tried to reform the multiply? But I don't think its a reliable way to do that. If the user of the expanded multiply is visited by the DAGCombiner after this conversion happens, the DAGCombiner will check its operands, see that they haven't been visited by the DAGCombiner before and it will then add the first node to the worklist. This process will repeat until all the new nodes are visited.
So this seems like an unreliable prevention at best. So this patch just returns the new nodes like any other combine. If this starts causing problems we can try to add target specific nodes or something to more directly prevent optimizations.
Now that we handle the combine normally, we can combine any negates the mul expansion creates into their users since those will be visited now.
llvm-svn: 338007
If the DAGCombiner's rotate matching was working as expected,
I don't think we'd see any test diffs here.
This sidesteps the issue of custom lowering for rotates raised in PR38243:
https://bugs.llvm.org/show_bug.cgi?id=38243
...by only dealing with legal operations.
llvm-svn: 337966
GNU binutils tools have no problems with this kind of shared constants,
provided that we actually hook it up completely in AsmPrinter and
produce a global symbol.
This effectively reverts SVN r335918 by hooking the rest of it up
properly.
This feature was implemented originally in SVN r213006, with no reason
for why it can't be used for MinGW other than the fact that GCC doesn't
do it while MSVC does.
Differential Revision: https://reviews.llvm.org/D49646
llvm-svn: 337951
When VectorLegalizer::LegalizeOp creates a new SDValue after iterating
over its arguments, we need to refer to the same result number of the
new node that the original value used.
Reviewed by: cameron.mcinally
Differential Revision: https://reviews.llvm.org/D49805
llvm-svn: 337939
against v1.2 BCBS attacks directly.
Attacks using spectre v1.2 (a subset of BCBS) are described in the paper
here:
https://people.csail.mit.edu/vlk/spectre11.pdf
The core idea is to speculatively store over the address in a vtable,
jumptable, or other target of indirect control flow that will be
subsequently loaded. Speculative execution after such a store can
forward the stored value to subsequent loads, and if called or jumped
to, the speculative execution will be steered to this potentially
attacker controlled address.
Up until now, this could be mitigated by enableing retpolines. However,
that is a relatively expensive technique to mitigate this particular
flavor. Especially because in most cases SLH will have already mitigated
this. To fully mitigate this with SLH, we need to do two core things:
1) Unfold loads from calls and jumps, allowing the loads to be post-load
hardened.
2) Force hardening of incoming registers even if we didn't end up
needing to harden the load itself.
The reason we need to do these two things is because hardening calls and
jumps from this particular variant is importantly different from
hardening against leak of secret data. Because the "bad" data here isn't
a secret, but in fact speculatively stored by the attacker, it may be
loaded from any address, regardless of whether it is read-only memory,
mapped memory, or a "hardened" address. The only 100% effective way to
harden these instructions is to harden the their operand itself. But to
the extent possible, we'd like to take advantage of all the other
hardening going on, we just need a fallback in case none of that
happened to cover the particular input to the control transfer
instruction.
For users of SLH, currently they are paing 2% to 6% performance overhead
for retpolines, but this mechanism is expected to be substantially
cheaper. However, it is worth reminding folks that this does not
mitigate all of the things retpolines do -- most notably, variant #2 is
not in *any way* mitigated by this technique. So users of SLH may still
want to enable retpolines, and the implementation is carefuly designed to
gracefully leverage retpolines to avoid the need for further hardening
here when they are enabled.
Differential Revision: https://reviews.llvm.org/D49663
llvm-svn: 337878
We generated a subtract for the power of 2 minus one then negated the result. The negate can be optimized away by swapping the subtract operands, but DAG combine doesn't know how to do that and we don't add any of the new nodes to the worklist anyway.
This patch makes use explicitly emit the swapped subtract.
llvm-svn: 337858
Use a left shift and 2 subtracts like we do for 30. Move this out from behind the slow lea check since it doesn't even use an LEA.
Use this for multiply by 14 as well.
llvm-svn: 337856
Mul by constant can expand to a sequence that ends with a negate. If the next instruction is an add or sub we might be able to fold the negate away.
We currently fail to do this because we explicitly don't add anything to the DAG combine worklist when we expand multiplies. This is primarily to keep the multipy from being reformed, but we should consider adding the users to worklist.
llvm-svn: 337843
This test was already checking microscopic behavior of tail call under
specific conditions. This just makes the CHECK lines much more
consistent, clear, and easily updated when intentional changes are made.
I've also switched the test to consistently name the entry block and to
order the helper declarations and comments for specific tests in the
more usual locations.
llvm-svn: 337806
Since SVN r335286, the .xdata sections are produced without an attached
symbol, which requires using a different syntax when printing assembly
output.
Instead of the usual syntax of '.section <name>,"dr",discard,<symbol>',
use '.section <name>,"dr"' + '.linkonce discard' (which is what GCC
uses for all assembly output).
This fixes PR38254.
Differential Revision: https://reviews.llvm.org/D49651
llvm-svn: 337756
Don't try to generate large PIC code for non-ELF targets. Neither COFF
nor MachO have relocations for large position independent code, and
users have been using "large PIC" code models to JIT 64-bit code for a
while now. With this change, if they are generating ELF code, their
JITed code will truly be PIC, but if they target MachO or COFF, it will
contain 64-bit immediates that directly reference external symbols. For
a JIT, that's perfectly fine.
llvm-svn: 337740
a call, and then again as a return.
Also added a comment to try and explain better why we would be doing
what we're doing when hardening the (non-call) returns.
llvm-svn: 337673
This specifically covers different ways of making indirect calls and
jumps. There are some bugs in SLH that I will be fixing in subsequent
patches where the diff in the generated instructions makes the bug fix
much more clear, so just checking in a baseline of this test to start.
I'm also going to be adding direct mitigation for variant 1.2 which this
file very specifically tests in the various forms it can arise on x86.
Again, the diff to the generated instructions should make the change for
that much more clear, so having the test as a baseline seems useful.
llvm-svn: 337672
This seems to be a net improvement. There's still an issue under avx512f where we have a 512-bit vpaddd, but not vpmaddwd so we end up doing two 256-bit vpmaddwds and inserting the results before a 512-bit vpaddd. It might be better to do two 512-bits paddds with zeros in the upper half. Same number of instructions, but breaks a dependency.
llvm-svn: 337656
This reapplies commit r337489 reverted by r337541
Additionally, this commit contains a speculative fix to the issue reported in r337541
(the report does not contain an actionable reproducer, just a stack trace)
llvm-svn: 337606
Ideally our ISD node types going into the isel table would have types consistent with their instruction domain. This prevents us having to duplicate patterns with different types for the same instruction.
Unfortunately, it seems our shuffle combining is currently relying on this a little remove some bitcasts. This seems to enable some switching between shufps and shufd. Hopefully there's some way we can address this in the combining.
Differential Revision: https://reviews.llvm.org/D49280
llvm-svn: 337590
We can safely use getConstant here as we're still lowering, which allows constant folding to kick in and simplify the vector shift codegen.
Noticed while working on D49562.
llvm-svn: 337578
When merging through a TokenFactor we need to check that the
load may be ordered such that no other aliasing memory operations may
happen. It is not sufficient to just check that the load is a member
of the chain token factor as it there may be a indirect chain. Require
the load's chain has only one use.
This fixes PR37826.
Reviewers: spatel, davide, efriedma, craig.topper, RKSimon
Subscribers: hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D49388
llvm-svn: 337560
We have a number of cases where we fail to reduce vector op widths, performing the op in a larger vector and then extracting a subvector. This is often because by default it would create illegal types.
This peephole patch attempts to handle a few common cases detailed in PR36761, which typically involved extension+conversion to vX2f64 types.
Differential Revision: https://reviews.llvm.org/D49556
llvm-svn: 337500
This is mostly a preparation work for adding a limited support for
select instructions. It proved to be difficult to do due to size and
irregularity of Vectorizer::isConsecutiveAccess, this is fixed here I
believe.
It also turned out that these changes make it simpler to finish one of
the TODOs and fix a number of other small issues, namely:
1. Looking through bitcasts to a type of a different size (requires
careful tracking of the original load/store size and some math
converting sizes in bytes to expected differences in indices of GEPs).
2. Reusing partial analysis of pointers done by first attempt in proving
them consecutive instead of starting from scratch. This added limited
support for nested GEPs co-existing with difficult sext/zext
instructions. This also required a careful handling of negative
differences between constant parts of offsets.
3. Handing a case where the first pointer index is not an add, but
something else (a function parameter for instance).
I observe an increased number of successful vectorizations on a large
set of shader programs. Only few shaders are affected, but those that
are affected sport >5% less loads and stores than before the patch.
Reviewed By: rampitec
Differential-Revision: https://reviews.llvm.org/D49342
llvm-svn: 337489
This patch fixes the latency/throughput of LEA instructions in the BtVer2
scheduling model.
On Jaguar, A 3-operands LEA has a latency of 2cy, and a reciprocal throughput of
1. That is because it uses one cycle of SAGU followed by 1cy of ALU1. An LEA
with a "Scale" operand is also slow, and it has the same latency profile as the
3-operands LEA. An LEA16r has a latency of 3cy, and a throughput of 0.5 (i.e.
RThrouhgput of 2.0).
This patch adds a new TIIPredicate named IsThreeOperandsLEAFn to X86Schedule.td.
The tablegen backend (for instruction-info) expands that definition into this
(file X86GenInstrInfo.inc):
```
static bool isThreeOperandsLEA(const MachineInstr &MI) {
return (
(
MI.getOpcode() == X86::LEA32r
|| MI.getOpcode() == X86::LEA64r
|| MI.getOpcode() == X86::LEA64_32r
|| MI.getOpcode() == X86::LEA16r
)
&& MI.getOperand(1).isReg()
&& MI.getOperand(1).getReg() != 0
&& MI.getOperand(3).isReg()
&& MI.getOperand(3).getReg() != 0
&& (
(
MI.getOperand(4).isImm()
&& MI.getOperand(4).getImm() != 0
)
|| (MI.getOperand(4).isGlobal())
)
);
}
```
A similar method is generated in the X86_MC namespace, and included into
X86MCTargetDesc.cpp (the declaration lives in X86MCTargetDesc.h).
Back to the BtVer2 scheduling model:
A new scheduling predicate named JSlowLEAPredicate now checks if either the
instruction is a three-operands LEA, or it is an LEA with a Scale value
different than 1.
A variant scheduling class uses that new predicate to correctly select the
appropriate latency profile.
Differential Revision: https://reviews.llvm.org/D49436
llvm-svn: 337469
As discussed on PR38197, this canonicalizes MOVS*(N0, OP(N0, N1)) --> MOVS*(N0, SCALAR_TO_VECTOR(OP(N0[0], N1[0])))
This returns the scalar-fp codegen lost by rL336971.
Additionally it handles the OP(N1, N0)) case for commutable (FADD/FMUL) ops.
Differential Revision: https://reviews.llvm.org/D49474
llvm-svn: 337419
Summary:
If unfolding an SUnit results in both load or the operation using it which
already exist in the DAG, abort the unfold if they are already scheduled.
If not, make sure we don't add duplicate dependencies.
This fixes PR37916.
Reviewers: davide, eli.friedman, fhahn, bogner
Subscribers: MatzeB, hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D48666
llvm-svn: 337409
While working on PR38197, I noticed that we don't make use of FADD/FMUL being able to commute the inputs to support the addps+movss -> addss style combine
llvm-svn: 337375
I'm trying to restrict the MOVLHPS/MOVHLPS ISD nodes to SSE1 only. With SSE2 we can use unpcks. I believe this will allow some patterns to be cleaned up to require fewer bitcasts.
I've put in an odd isel hack to still select MOVHLPS instruction from the unpckh node to avoid changing tests and because movhlps is a shorter encoding. Ideally we'd do execution domain switching on this, but the operands are in the wrong order and are tied. We might be able to try a commute in the domain switching using custom code.
We already support domain switching for UNPCKLPD and MOVLHPS.
llvm-svn: 337348
The presence of these symbols in the symbol table can cause symbol type
mismatch errors (or undefined symbol errors on emulated TLS targets)
and they can't be ICF'd anyway.
llvm-svn: 337338
Summary:
The only thing he suggested that I've skipped here is the double-wide
multiply instructions. Multiply is an area I'm nervous about there being
some hidden data-dependent behavior, and it doesn't seem important for
any benchmarks I have, so skipping it and sticking with the minimal
multiply support that matches what I know is widely used in existing
crypto libraries. We can always add double-wide multiply when we have
clarity from vendors about its behavior and guarantees.
I've tried to at least cover the fundamentals here with tests, although
I've not tried to cover every width or permutation. I can add more tests
where folks think it would be helpful.
Reviewers: craig.topper
Subscribers: sanjoy, mcrosier, hiraditya, llvm-commits
Differential Revision: https://reviews.llvm.org/D49413
llvm-svn: 337308
If we are only extracting vector elements via EXTRACT_VECTOR_ELT(s) we may be able to use SimplifyDemandedVectorElts to avoid unnecessary vector ops.
Differential Revision: https://reviews.llvm.org/D49262
llvm-svn: 337258
This amounts to pretty ridiculous number of patterns. Ideally we'd canonicalize the X86ISD::VRNDSCALE earlier to reuse those patterns. I briefly looked into doing that, but some strict FP operations could still get converted to rint and nearbyint during isel. It's probably still worthwhile to look into. This patch is meant as a starting point to work from.
llvm-svn: 337234
This allows us to use 231 form to fold an insertelement on the add input to the fma. There is technically no software intrinsic that can use this until AVX512F, but it can be manually built up from other intrinsics.
llvm-svn: 337223
As discussed here:
http://lists.llvm.org/pipermail/llvm-dev/2018-May/123292.htmlhttp://lists.llvm.org/pipermail/llvm-dev/2018-July/124400.html
We want to add rotate intrinsics because the IR expansion of that pattern is 4+ instructions,
and we can lose pieces of the pattern before it gets to the backend. Generalizing the operation
by allowing 2 different input values (plus the 3rd shift/rotate amount) gives us a "funnel shift"
operation which may also be a single hardware instruction.
Initially, I thought we needed to define new DAG nodes for these ops, and I spent time working
on that (much larger patch), but then I concluded that we don't need it. At least as a first
step, we have all of the backend support necessary to match these ops...because it was required.
And shepherding these through the IR optimizer is the primary concern, so the IR intrinsics are
likely all that we'll ever need.
There was also a question about converting the intrinsics to the existing ROTL/ROTR DAG nodes
(along with improving the oversized shift documentation). Again, I don't think that's strictly
necessary (as the test results here prove). That can be an efficiency improvement as a small
follow-up patch.
So all we're left with is documentation, definition of the IR intrinsics, and DAG builder support.
Differential Revision: https://reviews.llvm.org/D49242
llvm-svn: 337221
trivially rematerializable.
We run into a case where machineLICM hoists a large number of live ranges
outside of a big loop because it thinks those live ranges are trivially
rematerializable. In regalloc, global splitting is tried out first for those
live ranges before they are spilled and rematerialized. Because the global
splitting algorithm is quadratic, increasing a lot of global splitting
candidates causes huge compile time increase (50s to 1400s on my local
machine when compiling a module).
However, we think for live ranges which are very large and are trivially
rematerialiable, it is better to just skip global splitting so as to save
compile time with little chance of sacrificing performance. We uses the
segment size of live range to indirectly evaluate whether the global
splitting of the live range can introduce high cost, and use an option
as a knob to adjust the size limit threshold.
Differential Revision: https://reviews.llvm.org/D49353
llvm-svn: 337186
invariant instructions to be both more correct and much more powerful.
While testing, I continued to find issues with sinking post-load
hardening. Unfortunately, it was amazingly hard to create any useful
tests of this because we were mostly sinking across copies and other
loading instructions. The fact that we couldn't sink past normal
arithmetic was really a big oversight.
So first, I've ported roughly the same set of instructions from the data
invariant loads to also have their non-loading varieties understood to
be data invariant. I've also added a few instructions that came up so
often it again made testing complicated: inc, dec, and lea.
With this, I was able to shake out a few nasty bugs in the validity
checking. We need to restrict to hardening single-def instructions with
defined registers that match a particular form: GPRs that don't have
a NOREX constraint directly attached to their register class.
The (tiny!) test case included catches all of the issues I was seeing
(once we can sink the hardening at all) except for the NOREX issue. The
only test I have there is horrible. It is large, inexplicable, and
doesn't even produce an error unless you try to emit encodings. I can
keep looking for a way to test it, but I'm out of ideas really.
Thanks to Ben for giving me at least a sanity-check review. I'll follow
up with Craig to go over this more thoroughly post-commit, but without
it SLH crashes everywhere so landing it for now.
Differential Revision: https://reviews.llvm.org/D49378
llvm-svn: 337177
Summary:
[[ https://bugs.llvm.org/show_bug.cgi?id=38149 | PR38149 ]]
As discussed in https://reviews.llvm.org/D49179#1158957 and later,
the IR for 'check for [no] signed truncation' pattern can be improved:
https://rise4fun.com/Alive/gBf
^ that pattern will be produced by Implicit Integer Truncation sanitizer,
https://reviews.llvm.org/D48958https://bugs.llvm.org/show_bug.cgi?id=21530
in signed case, therefore it is probably a good idea to improve it.
But the IR-optimal patter does not lower efficiently, so we want to undo it..
This handles the simple pattern.
There is a second pattern with predicate and constants inverted.
NOTE: we do not check uses here. we always do the transform.
Reviewers: spatel, craig.topper, RKSimon, javed.absar
Reviewed By: spatel
Subscribers: kristof.beyls, llvm-commits
Differential Revision: https://reviews.llvm.org/D49266
llvm-svn: 337166
Found cases that hit the assert I added. This patch factors the validity
checking into a nice helper routine and calls it when deciding to harden
post-load, and asserts it when doing so later.
I've added tests for the various ways of loading a floating point type,
as well as loading all vector permutations. Even though many of these go
to identical instructions, it seems good to somewhat comprehensively
test them.
I'm confident there will be more fixes needed here, I'll try to add
tests each time as I get this predicate adjusted.
llvm-svn: 337160
This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid.
The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well.
llvm-svn: 337147
indices used by AVX2 and AVX-512 gather instructions.
The index vector is hardened by broadcasting the predicate state
into a vector register and then or-ing. We don't even have to worry
about EFLAGS here.
I've added a test for all of the gather intrinsics to make sure that we
don't miss one. A particularly interesting creation is the gather
prefetch, which needs to be marked as potentially "loading" to get the
correct behavior. It's a memory access in many ways, and is actually
relevant for SLH. Based on discussion with Craig in review, I've moved
it to be `mayLoad` and `mayStore` rather than generic side effects. This
matches how we model other prefetch instructions.
Many thanks to Craig for the review here.
Differential Revision: https://reviews.llvm.org/D49336
llvm-svn: 337144
AVX512F only has integer domain logic instructions. AVX512DQ added FP domain logic instructions.
Execution domain fixing runs before EVEX->VEX. So if we have AVX512F and not AVX512DQ we fail to do execution domain switching of the logic operations. This leads to mismatches in execution domain and more test differences.
This patch adds custom domain fixing that switches EVEX integer logic operations to VEX fp logic operations if XMM16-31 are not used.
llvm-svn: 337137
128-bit ops implicitly zero the upper bits. This should address the comment about domain crossing for the integer version without AVX2 since we can use a 128-bit VBLENDW without AVX2.
The only bad thing I see here is that we failed to reuse an vxorps in some of the tests, but I think that's already known issue.
llvm-svn: 337134
This is almost the same as an existing IR canonicalization in instcombine,
so I'm assuming this is a good early generic DAG combine too.
The motivation comes from reduced bit-hacking for select-of-constants in IR
after rL331486. We want to restore that functionality in the DAG as noted in
the commit comments for that change and the llvm-dev discussion here:
http://lists.llvm.org/pipermail/llvm-dev/2018-July/124433.html
The PPC and AArch tests show that those targets are already doing something
similar. x86 will be neutral in the minimal case and generally better when
this pattern is extended with other ops as shown in the signbit-shift.ll tests.
Note the asymmetry: we don't include the (extend (ifneg X)) transform because
it already exists in SimplifySelectCC(), and that is verified in the later
unchanged tests in the signbit-shift.ll files. Without the 'not' op, the
general transform to use a shift is always a win because that's a single
instruction.
Alive proofs:
https://rise4fun.com/Alive/ysli
Name: if pos, get -1
%c = icmp sgt i16 %x, -1
%r = sext i1 %c to i16
=>
%n = xor i16 %x, -1
%r = ashr i16 %n, 15
Name: if pos, get 1
%c = icmp sgt i16 %x, -1
%r = zext i1 %c to i16
=>
%n = xor i16 %x, -1
%r = lshr i16 %n, 15
Differential Revision: https://reviews.llvm.org/D48970
llvm-svn: 337130
The MachineOutliner was doing an std::for_each from the call (inserted
before the outlined sequence) to the iterator at the end of the
sequence.
std::for_each needs the iterator past the end, so the last instruction
was not taken into account when propagating the liveness information.
This fixes the machine verifier issue in machine-outliner-disubprogram.ll.
Differential Revision: https://reviews.llvm.org/D49295
llvm-svn: 337090
no conditions.
This is only valid to do if we're hardening calls and rets with LFENCE
which results in an LFENCE guarding the entire entry block for us.
llvm-svn: 337089
The code tried to find the immediate by using getNumOperands() on the MachineInstr, but there might be implicit-defs after the immediate that get counted.
Instead use getNumOperands() from the instruction description which will only count the operands that are defined in the td file.
llvm-svn: 337088
AVX512 doesn't have an immediate controlled blend instruction. But blend throughput is still better than movss/sd on SKX.
This commit changes AVX512 to use the AVX blend instructions instead of MOVSS/MOVSD. This constrains the register allocation since it won't be able to use XMM16-31, but hopefully the increased throughput and reduced port 5 pressure makes up for that.
llvm-svn: 337083
Summary:
By looking at the callers of getUse(), we can see that even though
IVUsers may offer uses, but they may not be interesting to
LSR. It's possible that none of them is interesting.
Reviewers: sanjoy
Subscribers: jlebar, hiraditya, bixia, llvm-commits
Differential Revision: https://reviews.llvm.org/D49049
llvm-svn: 337072
See D49247, D49266
I'm only adding the sane negative tests, and not
adding the one-use tests yet. Also, not adding
negative tests for the second pattern with inverted operands yet,
since it's handling will be added in later differential.
llvm-svn: 337014
Spectre variant #1 for x86.
There is a lengthy, detailed RFC thread on llvm-dev which discusses the
high level issues. High level discussion is probably best there.
I've split the design document out of this patch and will land it
separately once I update it to reflect the latest edits and updates to
the Google doc used in the RFC thread.
This patch is really just an initial step. It isn't quite ready for
prime time and is only exposed via debugging flags. It has two major
limitations currently:
1) It only supports x86-64, and only certain ABIs. Many assumptions are
currently hard-coded and need to be factored out of the code here.
2) It doesn't include any options for more fine-grained control, either
of which control flow edges are significant or which loads are
important to be hardened.
3) The code is still quite rough and the testing lighter than I'd like.
However, this is enough for people to begin using. I have had numerous
requests from people to be able to experiment with this patch to
understand the trade-offs it presents and how to use it. We would also
like to encourage work to similar effect in other toolchains.
The ARM folks are actively developing a system based on this for
AArch64. We hope to merge this with their efforts when both are far
enough along. But we also don't want to block making this available on
that effort.
Many thanks to the *numerous* people who helped along the way here. For
this patch in particular, both Eric and Craig did a ton of review to
even have confidence in it as an early, rough cut at this functionality.
Differential Revision: https://reviews.llvm.org/D44824
llvm-svn: 336990
flow patterns including forks, merges, and even cyles.
This tries to cover a reasonably comprehensive set of patterns that
still don't require PHIs or PHI placement. The coverage was inspired by
the amazing variety of patterns produced when copy EFLAGS and restoring
it to implement Speculative Load Hardening. Without this patch, we
simply cannot make such complex and invasive changes to x86 instruction
sequences due to EFLAGS.
I've added "just" one test, but this test covers many different
complexities and corner cases of this approach. It is actually more
comprehensive, as far as I can tell, than anything that I have
encountered in the wild on SLH.
Because the test is so complex, I've tried to give somewhat thorough
comments and an ASCII-art diagram of the control flows to make it a bit
easier to read and maintain long-term.
Differential Revision: https://reviews.llvm.org/D49220
llvm-svn: 336985
This is not an optimization we should be doing in isel. This is more suitable for a DAG combine.
My main concern is a future time when we support more FPENV. Changing a packed op to a scalar op could cause us to miss some exceptions that should have occured if we had done a packed op. A DAG combine would be better able to manage this.
llvm-svn: 336971
The one I noticed is sqrtsss/sd, but there could be others.
I had to add a couple new tests that don't have insertelement in there to catch this on the fast-isel path. Otherwise we trigger an abort and use SelectionDAG.
llvm-svn: 336938
canWidenShuffleElements can do a better job if given a mask with ZeroableElements info. Apparently, ZeroableElements was being only used to identify AllZero candidates, but possibly we could plug it into more shuffle matchers.
Original Patch by Zvi Rackover @zvi
Differential Revision: https://reviews.llvm.org/D42044
llvm-svn: 336903
Noticed while updating D42044, lowerV2X128VectorShuffle can improve the shuffle mask with the zeroable data to create a target shuffle mask to recognise more 'zero upper 128' patterns.
NOTE: lowerV4X128VectorShuffle could benefit as well but the code needs refactoring first to discriminate between SM_SentinelUndef and SM_SentinelZero for negative shuffle indices.
Differential Revision: https://reviews.llvm.org/D49092
llvm-svn: 336900
there for a long time.
The boolean tracking whether we saw a kill of the flags was supposed to
be per-block we are scanning and instead was outside that loop and never
cleared. It requires a quite contrived test case to hit this as you have
to have multiple levels of successors and interleave them with kills.
I've included such a test case here.
This is another bug found testing SLH and extracted to its own focused
patch.
llvm-svn: 336876
multiple successors where some of the uses end up killing the EFLAGS
register.
There was a bug where rather than skipping to the next basic block
queued up with uses once we saw a kill, we stopped processing the blocks
entirely. =/
Test case produces completely nonsensical code w/o this tiny fix.
This was found testing Speculative Load Hardening and split out of that
work.
Differential Revision: https://reviews.llvm.org/D49211
llvm-svn: 336874
This converts them to what clang is now using for codegen. Unfortunately, there seem to be a few kinks to work out still. I'll try to address with follow up patches.
llvm-svn: 336871
This is marginally helpful for removing redundant extensions, and the
code is easier to read, so it seems like an all-around win. In the new
test i8-phi-ext.ll, we used to emit an AssertSext i8; now we emit an
AssertZext i2, which allows the extension of the return value to be
eliminated.
Differential Revision: https://reviews.llvm.org/D49004
llvm-svn: 336868
See https://reviews.llvm.org/D47106 for details.
Reviewed By: probinson
Differential Revision: https://reviews.llvm.org/D47171
This commit drops that patch's changes to:
llvm/test/CodeGen/NVPTX/f16x2-instructions.ll
llvm/test/CodeGen/NVPTX/param-load-store.ll
For some reason, the dos line endings there prevent me from commiting
via the monorepo. A follow-up commit (not via the monorepo) will
finish the patch.
llvm-svn: 336843
We can instead block the load folding isProfitableToFold. Then isel will emit a register->register move for the zeroing part and a separate load. The PostProcessISelDAG should be able to remove the register->register move.
This saves us patterns and fixes the fact that we only had unaligned load patterns. The test changes show places where we should have been using an aligned load.
llvm-svn: 336828
First stage in PR38057 - support non-uniform constant vectors in the combine to reuse the division-by-constant logic.
We can definitely do better for srem pow2 remainders (and avoid that extra multiply....) but this at least helps keep everything on the vector unit.
Differential Revision: https://reviews.llvm.org/D48975
llvm-svn: 336774
Summary:
These changes cover the PR#31399.
Now the ffs(x) function is lowered to (x != 0) ? llvm.cttz(x) + 1 : 0
and it corresponds to the following llvm code:
%cnt = tail call i32 @llvm.cttz.i32(i32 %v, i1 true)
%tobool = icmp eq i32 %v, 0
%.op = add nuw nsw i32 %cnt, 1
%add = select i1 %tobool, i32 0, i32 %.op
and x86 asm code:
bsfl %edi, %ecx
addl $1, %ecx
testl %edi, %edi
movl $0, %eax
cmovnel %ecx, %eax
In this case the 'test' instruction can't be eliminated because
the 'add' instruction modifies the EFLAGS, namely, ZF flag
that is set by the 'bsf' instruction when 'x' is zero.
We now produce the following code:
bsfl %edi, %ecx
movl $-1, %eax
cmovnel %ecx, %eax
addl $1, %eax
Patch by Ivan Kulagin
Reviewers: davide, craig.topper, spatel, RKSimon
Reviewed By: craig.topper
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D48765
llvm-svn: 336768
These patterns looked for a MOVSS/SD followed by a scalar_to_vector. Or a scalar_to_vector followed by a load.
In both cases we emitted a MOVSS/SD for the MOVSS/SD part, a REG_CLASS for the scalar_to_vector, and a MOVSS/SD for the load.
But we have patterns that do each of those 3 things individually so there's no reason to build large patterns.
Most of the test changes are just reorderings. The one test that had a meaningful change is pr30430.ll and it appears to be a regression. But its doing -O0 so I think it missed a lot of opportunities and was just getting lucky before.
llvm-svn: 336762
Isel currently emits movss/movsd a lot of the time and an accidental double commute turns it into a blend.
Ideally we'd select blend directly in isel under optspeed and not rely on the double commute to create blend.
llvm-svn: 336731
This patch adds fast-isel tests for the IR patterns produced for truncation
intrinsics in rC336643.
Differential Revision: https://reviews.llvm.org/D48822
llvm-svn: 336645
Now that rL336250 has landed, we should prefer 2 immediate shifts + a shuffle blend over performing a multiply. Despite the increase in instructions, this is quicker (especially for slow v4i32 multiplies), avoid loads and constant pool usage. It does mean however that we increase register pressure. The code size will go up a little but by less than what we save on the constant pool data.
This patch also adds support for v16i16 to the BLEND(SHIFT(v,c1),SHIFT(v,c2)) combine, and also prevents blending on pre-SSE41 shifts if it would introduce extra blend masks/constant pool usage.
Differential Revision: https://reviews.llvm.org/D48936
llvm-svn: 336642
Summary:
This adds a reverse transform for the instcombine canonicalizations
that were added in D47980, D47981.
As discussed later, that was worse at least for the code size,
and potentially for the performance, too.
https://rise4fun.com/Alive/Zmpl
Reviewers: craig.topper, RKSimon, spatel
Reviewed By: spatel
Subscribers: reames, llvm-commits
Differential Revision: https://reviews.llvm.org/D48768
llvm-svn: 336585
Pre-AVX512 (which can perform a quick extend/shift/truncate), extending to 2 v8i16 for the PMULLW and then truncating is more performant than relying on the generic PBLENDVB vXi8 shift path and uses a similar amount of mask constant pool data.
Differential Revision: https://reviews.llvm.org/D48963
llvm-svn: 336513
This allows us to handle masking in a very similar way to the default rounding version that uses llvm.fma.
I had to add new rounding mode CodeGenOnly instructions to support isel when we can't find a movss to grab the upper bits from to use the b_Int instruction.
Fast-isel tests have been updated to match new clang codegen.
We are currently having trouble folding fneg into the new intrinsic. I'm going to correct that in a follow up patch to keep the size of this one down.
A future patch will also remove the old intrinsics.
llvm-svn: 336506
As discussed on PR37989, this patch adds EXTRACT_SUBVECTOR handling to TargetLowering::SimplifyDemandedVectorElts and calls it from DAGCombiner::visitEXTRACT_SUBVECTOR.
Differential Revision: https://reviews.llvm.org/D48825
llvm-svn: 336490
D48278
Allow to reduce redundant shift masks.
For example:
x1 = x & 0xAB00
x2 = (x >> 8) & 0xAB
can be reduced to:
x1 = x & 0xAB00
x2 = x1 >> 8
It only allows folding when the masks and shift values are constants.
llvm-svn: 336426
The intrinsics can be implemented with a f32/f64 llvm.fma intrinsic and an insert into a zero vector.
There are a couple regressions here due to SelectionDAG not being able to pull an fneg through an extract_vector_elt. I'm not super worried about this though as InstCombine should be able to do it before we get to SelectionDAG.
llvm-svn: 336416
This upgrades all of the intrinsics to use fneg instructions to convert fma into fmsub/fnmsub/fnmadd/fmsubadd. And uses a select instruction for masking.
This matches how clang uses the intrinsics these days.
llvm-svn: 336409
-Split cases that call 2 intrinsics in the same case.
-Remove testing mask3 and maskz intrinsics with an all ones mask. These won't be interesting after the upgrade.
-Restore test cases for some intrinsics that are marked for deletion, but haven't been deleted yet.
llvm-svn: 336408
Previously we could only negate the FMADD opcodes. This used to be mostly ok when we lowered FMA intrinsics during lowering. But with the move to llvm.fma from target specific intrinsics, we can combine (fneg (fma)) to (fmsub) earlier. So if we start with (fneg (fma (fneg))) we would get stuck at (fmsub (fneg)).
This patch fixes that so we can also combine things like (fmsub (fneg)).
llvm-svn: 336304
There's a regression in here due to inability to combine fneg inputs of X86ISD::FMSUB/FNMSUB/FNMADD nodes.
More removals to come, but I wanted to stop and fix the regression that showed up in this first.
llvm-svn: 336303
We were only doing this for basic blends, despite shuffle lowering now being good enough to handle more complex blends. This means that the two v8i16 splat shifts are performed in parallel instead of serially as the general shift case.
Reapplied with a fixed (extra null tests) version of rL336113 after reversion in rL336189 - extra test case added at rL336247.
llvm-svn: 336250
The following code pattern:
mov %rax, %rcx
test %rax, %rax
%rax = ....
je throw_npe
mov(%rcx), %r9
mov(%rax), %r10
gets transformed into the following incorrect code after implicit null check pass:
mov %rax, %rcx
%rax = ....
faulting_load_op("movl (%rax), %r10", throw_npe)
mov(%rcx), %r9
For implicit null check pass, if the register that is checked for null value (ie, the register used in the 'test' instruction) is written into before the condition jump, we should avoid doing the optimization.
Patch by Surya Kumari Jangala!
Differential Revision: https://reviews.llvm.org/D48627
Reviewed By: skatkov
llvm-svn: 336241
D48768 may turn some of these into shifts.
Reviewers: spatel
Reviewed By: spatel
Subscribers: spatel, RKSimon, llvm-commits, craig.topper
Differential Revision: https://reviews.llvm.org/D48767
llvm-svn: 336224
This might make the error message added in r335668 unneeded, but I'm not sure yet.
The check for RIP is technically unnecessary since RIP is in GR64, but that fact is kind of surprising so be explicit.
llvm-svn: 336217
Add registers still missing after r328016 (D43353):
- for bits 15-8 of SI, DI, BP, SP (*H), and R8-R15 (*BH),
- for bits 31-16 of R8-R15 (*WH).
Thanks to Craig Topper for pointing it out.
llvm-svn: 336134
Similarily, don't fold fp128 loads into SSE instructions if the load isn't aligned. Unless we're targeting an AMD CPU that doesn't check alignment on arithmetic instructions.
Should fix PR38001
llvm-svn: 336121
We were only doing this for basic blends, despite shuffle lowering now being good enough to handle more complex blends. This means that the two v8i16 splat shifts are performed in parallel instead of serially as the general shift case.
llvm-svn: 336113
We have special case support for 2 shift values for basic blends, but irregular shift patterns end up using the generic lowering, despite shuffle lowering being good enough to handle more complex blends.
llvm-svn: 336112
The combine added in commit 329525 overlooked the case where one, but not all, of the divisor elements is -1, -1 is the only power of two value for which the sdiv expansion recipe breaks.
Thanks to @zvi for the original patch.
Differential Revision: https://reviews.llvm.org/D45806
llvm-svn: 336048
Especially of note was the test_mm_mask_set1_epi64 and other set1 tests that were truncating the element to be broadcasted to i8 and broadcasting that instead of a whole 64 bit value.
Some of the others were just correcting mask sizes on parameters due to bugs in the clang test case they were generated from that have now been fixed.
Some were converting i8 to <4 x i1>/<2 x i1> by truncating to i4/i2 and then bitcasting. But the clang codegen is bitcast to <8 x i1>, then extract to <4 x i1>/<2 x i1>. This is likely to incur less trouble from the integer type legalizer in the backend.
llvm-svn: 336045
The important part is the creation of the SHLD/SHRD nodes. The compare and the conditional move can use target independent nodes that can be legalized on their own. This gives some opportunities to trigger the optimizations present in the lowering for those things. And its just better to limit the number of places we emit target specific nodes.
The changed test cases still aren't optimal.
Differential Revision: https://reviews.llvm.org/D48619
llvm-svn: 335998
This uses the same technique as for shifts - split the rotation into 4/2/1-bit partial rotations and select those partials based on the amount bit, making use of PBLENDVB if available. This halves the use of PBLENDVB compared to expanding to shifts, which can be a slow op.
Unfortunately I haven't found a decent way to share much of this code with the shift equivalent.
Differential Revision: https://reviews.llvm.org/D48655
llvm-svn: 335957
This fixes a regression since SVN r334523, where the object files
built targeting MinGW were rejected by GNU binutils tools. Prior to
that commit, we only put constants in comdat for MSVC configurations.
Differential Revision: https://reviews.llvm.org/D48567
llvm-svn: 335918
This is a follow up to r335753. At the time I forgot about isProfitableToFold which makes this pretty easy.
Differential Revision: https://reviews.llvm.org/D48706
llvm-svn: 335895
Reverting because this is causing failures in the LLDB test suite on
GreenDragon.
LLVM ERROR: unsupported relocation with subtraction expression, symbol
'__GLOBAL_OFFSET_TABLE_' can not be undefined in a subtraction
expression
llvm-svn: 335894
We could get away with it for constant folded cases, but not for rL335719.
Thanks to Krzysztof Parzyszek for noticing.
Reapply original commit rL335821 which was reverted at rL335871 due to a WebAssembly bug that was fixed at rL335884.
llvm-svn: 335886
Add NoTrapAfterNoreturn target option which skips emission of traps
behind noreturn calls even if TrapUnreachable is enabled.
Enable the feature on Mach-O to save code size; Comments suggest it is
not possible to enable it for the other users of TrapUnreachable.
rdar://41530228
DifferentialRevision: https://reviews.llvm.org/D48674
llvm-svn: 335877
As noted in the D44909 review, the transform from (fptosi+sitofp) to ftrunc
can produce -0.0 where the original code does not:
#include <stdio.h>
int main(int argc) {
float x;
x = -0.8 * argc;
printf("%f\n", (float)((int)x));
return 0;
}
$ clang -O0 -mavx fp.c ; ./a.out
0.000000
$ clang -O1 -mavx fp.c ; ./a.out
-0.000000
Ideally, we'd use IR/node flags to predicate the transform, but the IR parser
doesn't currently allow fast-math-flags on the cast instructions. So for now,
just use the function attribute that corresponds to clang's "-fno-signed-zeros"
option.
Differential Revision: https://reviews.llvm.org/D48085
llvm-svn: 335761
If we are just modifying a single bit at a variable bit position we can use the BT* instructions to make the change instead of shifting a 1(or rotating a -1) and doing a binop. These instruction also ignore the upper bits of their index input so we can also remove an and if one is present on the index.
Fixes PR37938.
llvm-svn: 335754
Simon Pilgrim