| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| |
|
|
|
|
|
|
|
|
| |
See bug 39332: https://bugs.llvm.org/show_bug.cgi?id=39332
Reviewers: artem.tamazov, arsenm
Differential Revision: https://reviews.llvm.org/D56794
llvm-svn: 351555
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This replaces most argument uses with loads, but for
now not all.
The code in SelectionDAG for calling convention lowering
is actively harmful for amdgpu_kernel. It attempts to
split the argument types into register legal types, which
results in low quality code for arbitary types. Since
all kernel arguments are passed in memory, we just want the
raw types.
I've tried a couple of methods of mitigating this in SelectionDAG,
but it's easier to just bypass this problem alltogether. It's
possible to hack around the problem in the initial lowering,
but the real problem is the DAG then expects to be able to use
CopyToReg/CopyFromReg for uses of the arguments outside the block.
Exposing the argument loads in the IR also has the advantage
that the LoadStoreVectorizer can merge them.
I'm not sure the best approach to dealing with the IR
argument list is. The patch as-is just leaves the IR arguments
in place, so all the existing code will still compute the same
kernarg size and pointlessly lowers the arguments.
Arguably the frontend should emit kernels with an empty argument
list in the first place. Alternatively a dummy array could be
inserted as a single argument just to reserve space.
This does have some disadvantages. Local pointer kernel arguments can
no longer have AssertZext placed on them as the equivalent !range
metadata is not valid on pointer typed loads. This is mostly bad
for SI which needs to know about the known bits in order to use the
DS instruction offset, so in this case this is not done.
More importantly, this skips noalias arguments since this pass
does not yet convert this to the equivalent !alias.scope and !noalias
metadata. Producing this metadata correctly seems to be tricky,
although this logically is the same as inlining into a function which
doesn't exist. Additionally, exposing these loads to the vectorizer
may result in degraded aliasing information if a pointer load is
merged with another argument load.
I'm also not entirely sure this is preserving the current clover
ABI, although I would greatly prefer if it would stop widening
arguments and match the HSA ABI. As-is I think it is extending
< 4-byte arguments to 4-bytes but doesn't align them to 4-bytes.
llvm-svn: 335650
|
| |
|
|
|
|
|
|
| |
We propagate the existing NaN value when possible.
Differential Revision: https://reviews.llvm.org/D44521
llvm-svn: 328140
|
| |
|
|
|
|
|
|
| |
As suggested in D44521 - bitcast to integer for the math,
so we preserve the intent of these tests when NaN math
gets folded away.
llvm-svn: 327890
|
| |
|
|
| |
llvm-svn: 318004
|
| |
|
|
|
|
| |
Differential revision: https://reviews.llvm.org/D34407
llvm-svn: 307097
|
| |
|
|
|
|
|
|
|
| |
It broke a testcase.
Failing Tests (1):
LLVM :: CodeGen/AMDGPU/alignbit-pat.ll
llvm-svn: 307054
|
| |
|
|
|
|
| |
Differential revision: https://reviews.llvm.org/D34407
llvm-svn: 307026
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Currently the default C calling convention functions are treated
the same as compute kernels. Make this explicit so the default
calling convention can be changed to a non-kernel.
Converted with perl -pi -e 's/define void/define amdgpu_kernel void/'
on the relevant test directories (and undoing in one place that actually
wanted a non-kernel).
llvm-svn: 298444
|
| |
|
|
|
|
| |
Merge some of the old, smaller tests into more complete versions.
llvm-svn: 295792
|
| |
|
|
|
|
|
|
|
|
|
| |
This switches to the workaround that HSA defaults to
for the mesa path.
This should be applied to the 4.0 branch.
Patch by Vedran Miletić <vedran@miletic.net>
llvm-svn: 292982
|
| |
|
|
| |
llvm-svn: 286912
|
| |
|
|
|
|
| |
I'm guessing at how it is supposed to be printed
llvm-svn: 285490
|
| |
|
|
| |
llvm-svn: 285449
|
| |
|
|
| |
llvm-svn: 280970
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Now that unaligned access expansion should not attempt
to produce i64 accesses, we can remove the hack in
PreprocessISelDAG where this is done.
This allows splitting i64 private accesses while
allowing the new add nodes indexing the vector components
can be folded with the base pointer arithmetic.
llvm-svn: 268293
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
PeepholeOptimizer cleans up redundant copies, which makes
the operand folding more effective.
shader-db stats:
Totals:
SGPRS: 34200 -> 34336 (0.40 %)
VGPRS: 22118 -> 21655 (-2.09 %)
Code Size: 632144 -> 633460 (0.21 %) bytes
LDS: 11 -> 11 (0.00 %) blocks
Scratch: 10240 -> 11264 (10.00 %) bytes per wave
Max Waves: 8822 -> 8918 (1.09 %)
Wait states: 0 -> 0 (0.00 %)
Totals from affected shaders:
SGPRS: 7704 -> 7840 (1.77 %)
VGPRS: 5169 -> 4706 (-8.96 %)
Code Size: 234444 -> 235760 (0.56 %) bytes
LDS: 2 -> 2 (0.00 %) blocks
Scratch: 0 -> 1024 (0.00 %) bytes per wave
Max Waves: 1188 -> 1284 (8.08 %)
Wait states: 0 -> 0 (0.00 %)
Increases:
SGPRS: 35 (0.01 %)
VGPRS: 1 (0.00 %)
Code Size: 59 (0.02 %)
LDS: 0 (0.00 %)
Scratch: 1 (0.00 %)
Max Waves: 48 (0.02 %)
Wait states: 0 (0.00 %)
Decreases:
SGPRS: 26 (0.01 %)
VGPRS: 54 (0.02 %)
Code Size: 68 (0.03 %)
LDS: 0 (0.00 %)
Scratch: 0 (0.00 %)
Max Waves: 4 (0.00 %)
Wait states: 0 (0.00 %)
llvm-svn: 266378
|
| |
|
|
|
|
|
| |
If a constant is the same as the reverse of an inline immediate,
this is 4 bytes smaller than having to embed a 32-bit literal.
llvm-svn: 263201
|
| |
|
|
|
|
|
| |
Make the REG_SEQUENCE be a VGPR, and do the register class
copy first.
llvm-svn: 251855
|
|
|
llvm-svn: 239657
|
