Since v_max_f32_e64/v_max_f16_e64 can be folded if the target
instruction supports the clamp bit, we also need to maintain
modifiers when converting v_mac to v_mad.
This fixes a rendering issue with Dirt Rally because a v_mac
instruction with the clamp bit set was converted to a v_mad
but that bit was lost during the conversion.
Fixes: e184e01dd7 ("AMDGPU: Fold FP clamp as modifier bit")
Patch by Samuel Pitoiset <samuel.pitoiset@gmail.com>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@297556 91177308-0d34-0410-b5e6-96231b3b80d8
This method inverts the Reason field of a scheduling candidate.
It does right comparison between RegCritical and RegExcess, but
everything else is broken. In fact it can prefer less strong reason
such as Weak over RegCritical because Weak > -RegCritical.
The CandReason enum is properly sorted, so just remove artificial
ranking.
Differential Revision: https://reviews.llvm.org/D30557
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@297536 91177308-0d34-0410-b5e6-96231b3b80d8
If there is only one successor, and that successor only
has one predecessor the wait can obviously be delayed until
uses or the end of the next block. This avoids code quality
regressions when there are trivial fallthrough blocks inserted
for structurization.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@297251 91177308-0d34-0410-b5e6-96231b3b80d8
When doing arcp optimization with a constant denominator,
this was leaving behind rcps with constant inputs.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@297248 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
This will allow future patches to inspect the details of the LLT. The implementation is now split between
the Support and CodeGen libraries to allow TableGen to use this class without introducing layering concerns.
Thanks to Ahmed Bougacha for finding a reasonable way to avoid the layering issue and providing the version of this patch without that problem.
The problem with the previous commit appears to have been that TableGen was including CodeGen/LowLevelType.h instead of Support/LowLevelTypeImpl.h.
Reviewers: t.p.northover, qcolombet, rovka, aditya_nandakumar, ab, javed.absar
Subscribers: arsenm, nhaehnle, mgorny, dberris, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D30046
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@297241 91177308-0d34-0410-b5e6-96231b3b80d8
More module problems. This time it only showed up in the stage 2 compile of
clang-x86_64-linux-selfhost-modules-2 but not the stage 1 compile.
Somehow, this change causes the build to need Attributes.gen before it's been
generated.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@297188 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
This will allow future patches to inspect the details of the LLT. The implementation is now split between
the Support and CodeGen libraries to allow TableGen to use this class without introducing layering concerns.
Thanks to Ahmed Bougacha for finding a reasonable way to avoid the layering issue and providing the version of this patch without that problem.
Reviewers: t.p.northover, qcolombet, rovka, aditya_nandakumar, ab, javed.absar
Subscribers: arsenm, nhaehnle, mgorny, dberris, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D30046
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@297177 91177308-0d34-0410-b5e6-96231b3b80d8
It breaks line tables because the patch is not complete, working on a complete one at the moment
This reverts commit r294031.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@297118 91177308-0d34-0410-b5e6-96231b3b80d8
Added code to check constant bus restrictions for VOP formats (only one SGPR value or literal-constant may be used by the instruction).
Note that the same checks are performed by SIInstrInfo::verifyInstruction (used by lowering code).
Added LIT tests.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@296873 91177308-0d34-0410-b5e6-96231b3b80d8
This is somewhat tricky because there are two
pairs of tied operands, and it isn't allowed to be
VOP3 encoded.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@296519 91177308-0d34-0410-b5e6-96231b3b80d8
It's not clear to me if this is always better than
doing ds_write2_b64 This adds the constraint of
a 128-bit register input instead of a pair of
64-bit.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@296512 91177308-0d34-0410-b5e6-96231b3b80d8
If during scheduling we have identified that we cannot keep optimistic
occupancy increase critical register pressure limit and try scheduling
of the whole function again. In this case blocks with smaller pressure
will have a chance for better scheduling.
Differential Revision: https://reviews.llvm.org/D30442
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@296506 91177308-0d34-0410-b5e6-96231b3b80d8
This change introduces new method to estimate register pressure in
GCNScheduler. Standard RPTracker gives huge error due to the following
reasons:
1. It does not account for live-ins or live-outs if value is not used
in the region itself. That creates a huge error in a very common case
if there are a lot of live-thu registers.
2. It does not properly count subregs.
3. It assumes a register used as an input operand can be reused as an
output. This is not always possible by itself, this is not what RA
will finally do in many cases for various reasons not limited to RA's
inability to do so, and this is not so if the value is actually a
live-thu.
In addition we can now see clear separation between live-in pressure
which we cannot change with the scheduling and tentative pressure
which we can change.
Differential Revision: https://reviews.llvm.org/D30439
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@296491 91177308-0d34-0410-b5e6-96231b3b80d8
If two subregs of the same register are defined and we need to revert
schedule changing def order, we will end up with both instructions
having def,read-undef flags because adjustLaneLiveness() will only set
this flag but will not remove it.
Fix this by removing read-undef flags before calling adjustLaneLiveness.
Differential Revision: https://reviews.llvm.org/D30428
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@296484 91177308-0d34-0410-b5e6-96231b3b80d8
Summary:
This will allow future patches to inspect the details of the LLT. The implementation is now split between
the Support and CodeGen libraries to allow TableGen to use this class without introducing layering concerns.
Thanks to Ahmed Bougacha for finding a reasonable way to avoid the layering issue and providing the version of this patch without that problem.
Reviewers: t.p.northover, qcolombet, rovka, aditya_nandakumar, ab, javed.absar
Subscribers: arsenm, nhaehnle, mgorny, dberris, llvm-commits, kristof.beyls
Differential Revision: https://reviews.llvm.org/D30046
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@296474 91177308-0d34-0410-b5e6-96231b3b80d8
Add a few non-VOP3P but instructions related to packed.
Includes hack with dummy operands for the benefit of the assembler
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@296368 91177308-0d34-0410-b5e6-96231b3b80d8
- Verify that runtime metadata is actually valid runtime metadata when assembling, otherwise we could accept the following when assembling, but ocl runtime will reject it:
.amdgpu_runtime_metadata
{ amd.MDVersion: [ 2, 1 ], amd.RandomUnknownKey, amd.IsaInfo: ...
- Make IsaInfo optional, and always emit it.
Differential Revision: https://reviews.llvm.org/D30349
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@296324 91177308-0d34-0410-b5e6-96231b3b80d8
This reverts commit r296009. It broke one out of tree target and also
does not account for all partial lines added or removed when calculating
PressureDiff.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@296182 91177308-0d34-0410-b5e6-96231b3b80d8
Clang issues warning about hidden overload. That was intended, so
add "using AMDGPUGenRegisterInfo::getRegUnitWeight;" to mute it.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@296021 91177308-0d34-0410-b5e6-96231b3b80d8
If a subreg is used in an instruction it counts as a whole superreg
for the purpose of register pressure calculation. This patch corrects
improper register pressure calculation by examining operand's lane mask.
Differential Revision: https://reviews.llvm.org/D29835
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@296009 91177308-0d34-0410-b5e6-96231b3b80d8
Implement isLegalToVectorizeLoadChain for AMDGPU to avoid
producing private address spaces accesses that will need to be
split up later. This was doing the wrong thing in the case
where the queried chain was an even number of elements.
A possible <4 x i32> store was being split into
store <2 x i32>
store i32
store i32
rather than
store <2 x i32>
store <2 x i32>
when legal.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295933 91177308-0d34-0410-b5e6-96231b3b80d8
The manual is unclear on the details of this. It's not
clear to me if denormals are not allowed with clamp,
or if that is only omod. Not allowing denorms for
fp16 or fp64 isn't useful so I also question if that
is really a restriction. Same with whether this is valid
without IEEE mode enabled.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295905 91177308-0d34-0410-b5e6-96231b3b80d8
