8 Commits

Author SHA1 Message Date
Jon Chesterfield
d77ae7f251 [amdgpu] Reimplement LDS lowering
Renames the current lowering scheme to "module" and introduces two new
ones, "kernel" and "table", plus a "hybrid" that chooses between those three
on a per-variable basis.

Unit tests are set up to pass with the default lowering of "module" or "hybrid"
with this patch defaulting to "module", which will be a less dramatic codegen
change relative to the current. This reflects the sparsity of test coverage for
the table lowering method. Hybrid is better than module in every respect and
will be default in a subsequent patch.

Reviewed By: arsenm

Differential Revision: https://reviews.llvm.org/D139433
2022-12-07 22:02:54 +00:00
Nico Weber
a862d09a92 Revert "[amdgpu] Reimplement LDS lowering"
This reverts commit 982017240d7f25a8a6969b8b73dc51f9ac5b93ed.
Breaks check-llvm, see https://reviews.llvm.org/D139433#3974862
2022-12-06 12:01:36 -05:00
Jon Chesterfield
982017240d [amdgpu] Reimplement LDS lowering
Renames the current lowering scheme to "module" and introduces two new
ones, "kernel" and "table", plus a "hybrid" that chooses between those three
on a per-variable basis.

Unit tests are set up to pass with the default lowering of "module" or "hybrid"
with this patch defaulting to "module", which will be a less dramatic codegen
change relative to the current. This reflects the sparsity of test coverage for
the table lowering method. Hybrid is better than module in every respect and
will be default in a subsequent patch.

Reviewed By: arsenm

Differential Revision: https://reviews.llvm.org/D139433
2022-12-06 16:28:15 +00:00
Jon Chesterfield
35f2584ef9 [amdgpu] Error, instead of miscompile, anonymous kernels using lds
The association between kernel and struct is done by symbol name.
This doesn't work robustly for anonymous kernels as shown by the modified
test case.

An alternative association between function and struct can be constructed
if necessary, probably though metadata, but on the basis that we currently
miscompile anonymous kernels and that they are difficult to construct from
application code and difficult to call from the runtime, this patch makes
it a fatal error for now.

Reviewed By: arsenm

Differential Revision: https://reviews.llvm.org/D134741
2022-09-28 16:30:04 +01:00
Jon Chesterfield
bc78c09952 [amdgpu] Elide module lds allocation in kernels with no callees
Introduces a string attribute, amdgpu-requires-module-lds, to allow
eliding the module.lds block from kernels. Will allocate the block as before
if the attribute is missing or has its default value of true.

Patch uses the new attribute to detect the simplest possible instance of this,
where a kernel makes no calls and thus cannot call any functions that use LDS.

Tests updated to match, coverage was already good. Interesting cases is in
lower-module-lds-offsets where annotating the kernel allows the backend to pick
a different (in this case better) variable ordering than previously. A later
patch will avoid moving kernel variables into module.lds when the kernel can
have this attribute, allowing optimal ordering and locally unused variable
elimination.

Reviewed By: arsenm

Differential Revision: https://reviews.llvm.org/D122091
2022-05-04 22:42:07 +01:00
Johannes Doerfert
a81fff8afd Reapply "[Intrinsics] Add nocallback to the default intrinsic attributes"
This reverts commit c5f789050daab25aad6770790987e2b7c0395936 and
reapplies 7aea3ea8c3b33c9bb338d5d6c0e4832be1d09ac3 with additional test
changes.
2022-03-25 09:36:50 -05:00
Stanislav Mekhanoshin
2b43209ee3 [AMDGPU] Propagate LDS align into to instructions
Differential Revision: https://reviews.llvm.org/D104316
2021-06-23 00:57:16 -07:00
Stanislav Mekhanoshin
8de4db697f [AMDGPU] Lower kernel LDS into a sorted structure
Differential Revision: https://reviews.llvm.org/D102954
2021-05-25 11:29:29 -07:00