Commit Graph

61 Commits

Author SHA1 Message Date
Stanislav Mekhanoshin d4b500cb08 [AMDGPU] Track occupancy in MFI
Keep track of achieved occupancy in SIMachineFunctionInfo.
At the moment we have a lot of duplicated or even missed code to
query and maintain occupancy info. Record it in the MFI and
query in a single call. Interfaces:

- getOccupancy() - returns current recorded achieved occupancy.
- getMinAllowedOccupancy() - returns lesser of the achieved occupancy
and the lowest occupancy we are ready to tolerate. For example if
a kernel is memory bound we are ready to tolerate 4 waves.
- limitOccupancy() - record occupancy level if we have to lower it.
- increaseOccupancy() - record occupancy if scheduler managed to
increase the occupancy.

MFI takes care of integrating different checks affecting occupancy,
including LDS use and waves-per-eu attribute. Note that scheduler
starts with not yet known register pressure, so has to record either
limit or increase in occupancy after it is done. Later passes can
just query a resulting value.

New interface is used in the active scheduler and NFC wrt its work.
Changes are also made to experimental schedulers to use it and record
an occupancy after they are done. Before the change waves-per-eu was
ignored by experimental schedulers and tolerance window for memory
bound kernels was not used.

Differential Revision: https://reviews.llvm.org/D47509

llvm-svn: 333629
2018-05-31 05:36:04 +00:00
Tom Stellard 44b30b4537 AMDGPU: Remove #include "MCTargetDesc/AMDGPUMCTargetDesc.h" from common headers
Summary:
MCTargetDesc/AMDGPUMCTargetDesc.h contains enums for all the instuction
and register defintions, which are huge so we only want to include
them where needed.

This will also make it easier if we want to split the R600 and GCN
definitions into separate tablegenerated files.

I was unable to remove AMDGPUMCTargetDesc.h from SIMachineFunctionInfo.h
because it uses some enums from the header to initialize default values
for the SIMachineFunction class, so I ended up having to remove includes of
SIMachineFunctionInfo.h from headers too.

Reviewers: arsenm, nhaehnle

Reviewed By: nhaehnle

Subscribers: MatzeB, kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, javed.absar, llvm-commits

Differential Revision: https://reviews.llvm.org/D46272

llvm-svn: 332930
2018-05-22 02:03:23 +00:00
Adrian Prantl 5f8f34e459 Remove \brief commands from doxygen comments.
We've been running doxygen with the autobrief option for a couple of
years now. This makes the \brief markers into our comments
redundant. Since they are a visual distraction and we don't want to
encourage more \brief markers in new code either, this patch removes
them all.

Patch produced by

  for i in $(git grep -l '\\brief'); do perl -pi -e 's/\\brief //g' $i & done

Differential Revision: https://reviews.llvm.org/D46290

llvm-svn: 331272
2018-05-01 15:54:18 +00:00
Matt Arsenault 03ae399d50 AMDGPU: Support realigning stack
While the stack access instructions don't care about
alignment > 4, some transformations on the pointer calculation
do make assumptions based on knowing the low bits of a pointer
are 0. If a stack object ends up being accessed through its
absolute address (relative to the kernel scratch wave offset),
the addressing expression may depend on the stack frame being
properly aligned. This was breaking in a testcase due to the
add->or combine.

I think some of the SP/FP handling logic is still backwards,
and overly simplistic to support all of the stack features.
Code which tries to modify the SP with inline asm for example
or variable sized objects will probably require redoing this.

llvm-svn: 328831
2018-03-29 21:30:06 +00:00
Tim Renouf 8234b4893a [AMDGPU] stop buffer_store being moved illegally
Summary:
The machine instruction scheduler was illegally moving a buffer store
past a buffer load with the same descriptor and offset. Fixed by marking
buffer ops as mayAlias and isAliased. This may be overly conservative,
and we may need to revisit.

Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, t-tye, llvm-commits

Differential Revision: https://reviews.llvm.org/D43332

Change-Id: Iff3173d9e0653e830474546276ab9d30318b8ef7
llvm-svn: 325567
2018-02-20 10:03:38 +00:00
Matt Arsenault 923712b6b5 Reapply "AMDGPU: Add 32-bit constant address space"
This reverts r324494 and reapplies r324487.

llvm-svn: 324747
2018-02-09 16:57:57 +00:00
Rafael Espindola f4e3f3e31c Revert "AMDGPU: Add 32-bit constant address space"
This reverts commit r324487.

It broke clang tests.

llvm-svn: 324494
2018-02-07 18:09:35 +00:00
Marek Olsak 871c30e540 AMDGPU: Add 32-bit constant address space
Note: This is a candidate for LLVM 6.0, because it was planned to be
      in that release but was delayed due to a long review period.

Merge conflict in release_60 - resolution:
    Add "-p6:32:32" into the second (non-amdgiz) string.

Only scalar loads support 32-bit pointers. An address in a VGPR will
fail to compile. That's OK because the results of loads will only be used
in places where VGPRs are forbidden.

Updated AMDGPUAliasAnalysis and used SReg_64_XEXEC.
The tests cover all uses cases we need for Mesa.

Reviewers: arsenm, nhaehnle

Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits

Differential Revision: https://reviews.llvm.org/D41651

llvm-svn: 324487
2018-02-07 16:01:00 +00:00
Tim Renouf 75ced9d5b8 [AMDGPU] stop image_store being moved illegally
Summary:
A recent change
321556: AMDGPU: Remove mayLoad/hasSideEffects from MIMG stores
can allow the machine instruction scheduler to move an image store past
an image load using the same descriptor.

V2: Fixed by marking image ops as mayAlias and isAliased. This may be
overly conservative, and we may need to revisit.
V3: Reverted test change done on 321556.

Reviewers: arsenm, nhaehnle, dstuttard

Subscribers: llvm-commits, t-tye, yaxunl, wdng, kzhuravl

Differential Revision: https://reviews.llvm.org/D41969

llvm-svn: 322419
2018-01-12 22:57:24 +00:00
Matt Arsenault e19bc2ee0f AMDGPU: Use unique PSVs for buffer resources
Also fixes using the wrong memory type for some
intrinsics when custom lowering them.

llvm-svn: 321557
2017-12-29 17:18:21 +00:00
Matt Arsenault 905f3518ba AMDGPU: Implement getTgtMemIntrinsic for images
Currently all images are lowered to have a single
image PseudoSourceValue. Image stores happen to have
overly strict mayLoad/mayStore/hasSideEffects flags
set on them, so this happens to work. When these
are fixed to be correct, the scheduler breaks
this because the identical PSVs are assumed to
be the same address. These need to be unique
to the image resource value.

llvm-svn: 321555
2017-12-29 17:18:14 +00:00
David Blaikie 3f833edc7c Target/TargetInstrInfo.h -> CodeGen/TargetInstrInfo.h to match layering
This header includes CodeGen headers, and is not, itself, included by
any Target headers, so move it into CodeGen to match the layering of its
implementation.

llvm-svn: 317647
2017-11-08 01:01:31 +00:00
Konstantin Zhuravlyov 275a4f76c4 AMDGPU: Fix warning discovered by r317266 [-Wunused-private-field]
llvm-svn: 317280
2017-11-02 22:35:22 +00:00
Konstantin Zhuravlyov b695cd41b3 AMDGPU: Remove outdated fixme (it was already fixed)
llvm-svn: 317266
2017-11-02 20:48:06 +00:00
Tim Renouf 132291589f [AMDGPU] AMDPAL scratch buffer support
Summary:
Added support for scratch (including spilling) for OS type amdpal:
generates code to set up the scratch descriptor if it is needed.

With amdpal, the scratch resource descriptor is loaded from offset 0 of
the global information table. The low 32 bits of the address of the
global information table is passed in s0.

Added amdgpu-git-ptr-high function attribute to hard-wire the high 32
bits of the address of the global information table. If the function
attribute is not specified, or is 0xffffffff, then the backend generates
code to use the high 32 bits of pc.

The documentation for the AMDPAL ABI will be added in a later commit.

Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, t-tye

Differential Revision: https://reviews.llvm.org/D37483

llvm-svn: 314501
2017-09-29 09:49:35 +00:00
Jan Sjodin 312ccf761c Add AddresSpace to PseudoSourceValue.
Differential Revision: https://reviews.llvm.org/D35089

llvm-svn: 313297
2017-09-14 20:53:51 +00:00
Matt Arsenault 71bcbd451f AMDGPU: Start adding tail call support
Handle the sibling call cases.

llvm-svn: 310753
2017-08-11 20:42:08 +00:00
Eugene Zelenko 59e128266c [AMDGPU] Fix some Clang-tidy modernize-use-using and Include What You Use warnings; other minor fixes (NFC).
llvm-svn: 310328
2017-08-08 00:47:13 +00:00
Matt Arsenault 8623e8d864 AMDGPU: Pass special input registers to functions
llvm-svn: 309998
2017-08-03 23:00:29 +00:00
Matt Arsenault 8e8f8f43b0 AMDGPU: Fix clobbering CSR VGPRs when spilling SGPR to it
llvm-svn: 309783
2017-08-02 01:52:45 +00:00
Matt Arsenault 9166ce86e8 AMDGPU: Annotate implicitarg.ptr usage
We need to pass something to functions for this to work.
It isn't derivable just from the kernarg segment pointer
because the implicit arguments are placed after the
kernel arguments.

Also fixes missing test for the intrinsic.

llvm-svn: 309398
2017-07-28 15:52:08 +00:00
Matt Arsenault 1cc47f8413 AMDGPU: Figure out private memory regs after lowering
Introduce pseudo-registers for registers needed for stack
access, which are replaced during finalizeLowering.
Note these pseudo-registers are currently only used for the
used register location, and not for determining their
input argument register.

This is better because it avoids the need to try to predict
whether a call will be emitted from the IR, and also
detects stack objects introduced by legalization.

Test changes are from the HasStackObjects check being more
accurate since stack objects introduced during legalization
are now known.

llvm-svn: 308325
2017-07-18 16:44:56 +00:00
Matt Arsenault e15855d9e3 AMDGPU: Annotate features from x work item/group IDs.
This wasn't necessary before since they are always enabled
for kernels, but this is necessary if they need to be
forwarded to a callable function.

llvm-svn: 308226
2017-07-17 22:35:50 +00:00
Matt Arsenault 10fc062b2b AMDGPU: Partially fix implicit.buffer.ptr intrinsic handling
This should not be treated as a different version of
private_segment_buffer. These are distinct things with
different uses and register classes, and requires the
function argument info to have more context about the
function's type and environment.

Also add missing test coverage for the intrinsic, and
emit an error for HSA. This also encovers that the intrinsic
is broken unless there happen to be stack objects.

llvm-svn: 306264
2017-06-26 03:01:31 +00:00
Chandler Carruth 6bda14b313 Sort the remaining #include lines in include/... and lib/....
I did this a long time ago with a janky python script, but now
clang-format has built-in support for this. I fed clang-format every
line with a #include and let it re-sort things according to the precise
LLVM rules for include ordering baked into clang-format these days.

I've reverted a number of files where the results of sorting includes
isn't healthy. Either places where we have legacy code relying on
particular include ordering (where possible, I'll fix these separately)
or where we have particular formatting around #include lines that
I didn't want to disturb in this patch.

This patch is *entirely* mechanical. If you get merge conflicts or
anything, just ignore the changes in this patch and run clang-format
over your #include lines in the files.

Sorry for any noise here, but it is important to keep these things
stable. I was seeing an increasing number of patches with irrelevant
re-ordering of #include lines because clang-format was used. This patch
at least isolates that churn, makes it easy to skip when resolving
conflicts, and gets us to a clean baseline (again).

llvm-svn: 304787
2017-06-06 11:49:48 +00:00
Matt Arsenault 2b1f9aa577 AMDGPU: Start defining a calling convention
Partially implement callee-side for arguments and return values.
byval doesn't work properly, and most likely sret or other on-stack
return values most as well.

llvm-svn: 303308
2017-05-17 21:56:25 +00:00
Matt Arsenault 1c0ae3972f AMDGPU: Add StackPtr and FramePtr registers to MFI
These will be necessary for setting up call sequences.

llvm-svn: 301208
2017-04-24 18:05:16 +00:00
Matt Arsenault 161e2b4223 AMDGPU: Make MFI fields private
llvm-svn: 300596
2017-04-18 20:59:40 +00:00
Matt Arsenault e622dc3803 AMDGPU: Refactor argument lowering
Split into smaller functions and prepare for handling
non-entry functions.

llvm-svn: 299998
2017-04-11 22:29:24 +00:00
Matt Arsenault 678e111e11 AMDGPU: Fix crash when disassembling VOP3 mac
The unused dummy src2_modifiers is missing, so it crashes
when trying to print it.

I tried to fully remove src2_modifiers, but there are some
irritations in the places where it is converted to mad since
it starts to require modifying use lists while iterating over
them.

llvm-svn: 299861
2017-04-10 17:58:06 +00:00
Matt Arsenault e0bf7d02f0 AMDGPU: Don't use stack space for SGPR->VGPR spills
Before frame offsets are calculated, try to eliminate the
frame indexes used by SGPR spills. Then we can delete them
after.

I think for now we can be sure that no other instruction
will be re-using the same frame indexes. It should be easy
to notice if this assumption ever breaks since everything
asserts if it tries to use a dead frame index later.

The unused emergency stack slot seems to still be left behind,
so an additional 4 bytes is still wasted.

llvm-svn: 295753
2017-02-21 19:12:08 +00:00
Tom Stellard 2f3f9855f0 AMDGPU add support for spilling to a user sgpr pointed buffers
Summary:
This lets you select which sort of spilling you want, either s[0:1] or 64-bit loads from s[0:1].

Patch By: Dave Airlie

Reviewers: nhaehnle, arsenm, tstellarAMD

Reviewed By: arsenm

Subscribers: mareko, llvm-commits, kzhuravl, wdng, yaxunl, tony-tye

Differential Revision: https://reviews.llvm.org/D25428

llvm-svn: 293000
2017-01-25 01:25:13 +00:00
Eugene Zelenko 6620376da7 [AMDGPU] Fix some Clang-tidy modernize and Include What You Use warnings; other minor fixes (NFC).
llvm-svn: 292688
2017-01-21 00:53:49 +00:00
Tom Stellard bb1388862b AMDGPU/SI: Make a function const
llvm-svn: 290185
2016-12-20 17:26:34 +00:00
Tom Stellard 6f9ef14b9d AMDGPU/SI: Add a MachineMemOperand when lowering llvm.amdgcn.buffer.load.*
Reviewers: arsenm, nhaehnle, mareko

Subscribers: kzhuravl, wdng, yaxunl, llvm-commits, tony-tye

Differential Revision: https://reviews.llvm.org/D27834

llvm-svn: 290184
2016-12-20 17:19:44 +00:00
Tom Stellard 244891d129 AMDGPU/SI: Add a MachineMemOperand to MIMG instructions
Summary:
Without a MachineMemOperand, the scheduler was assuming MIMG instructions
were ordered memory references, so no loads or stores could be reordered
across them.

Reviewers: arsenm

Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, tony-tye

Differential Revision: https://reviews.llvm.org/D27536

llvm-svn: 290179
2016-12-20 15:52:17 +00:00
Konstantin Zhuravlyov 1d65026ca6 [AMDGPU] Wave and register controls
- Implemented amdgpu-flat-work-group-size attribute
- Implemented amdgpu-num-active-waves-per-eu attribute
- Implemented amdgpu-num-sgpr attribute
- Implemented amdgpu-num-vgpr attribute
- Dynamic LDS constraints are in a separate patch

Patch by Tom Stellard and Konstantin Zhuravlyov

Differential Revision: https://reviews.llvm.org/D21562

llvm-svn: 280747
2016-09-06 20:22:28 +00:00
Saleem Abdulrasool 43e5fe3fac AMDGPU: fix mismatch tags, NFC
llvm-svn: 280006
2016-08-29 20:42:07 +00:00
Matt Arsenault 69fd2c1179 AMDGPU: Remove unused tracking of flat instructions
llvm-svn: 278361
2016-08-11 17:15:28 +00:00
Matt Arsenault 52ef4019fd AMDGPU: Make AMDGPUMachineFunction fields private
ABIArgOffset is a problem because properly fsetting the
KernArgSize requires that the reserved area before the
real kernel arguments be correctly aligned, which requires
fixing clover.

llvm-svn: 276766
2016-07-26 16:45:58 +00:00
Matt Arsenault 8d718dcfda AMDGPU: Add HSA dispatch id intrinsic
llvm-svn: 276437
2016-07-22 17:01:30 +00:00
Marek Olsak 0532c190f7 AMDGPU/SI: Emit the number of SGPR and VGPR spills
Summary:
v2: don't count SGPRs spilled to scratch twice

I think this is sufficient. It doesn't count private memory usage, which
happens often and uses scratch but isn't technically a spill. The private
memory usage can be computed by:
  [scratch_per_thread - vgpr_spills - a random multiple of SGPR spills].

The fact SGPR spills add very high numbers to the scratch size make that
computation a guessing game, but I don't have a solution to that.

Reviewers: tstellarAMD

Subscribers: arsenm, kzhuravl

Differential Revision: http://reviews.llvm.org/D22197

llvm-svn: 275288
2016-07-13 17:35:15 +00:00
NAKAMURA Takumi 5cbd41e0a8 SIMachineFunctionInfo.cpp: Appease msc18 to use std::array.
llvm-svn: 273860
2016-06-27 10:26:43 +00:00
NAKAMURA Takumi d377ad806e Reformat blank lines.
llvm-svn: 273858
2016-06-27 10:26:25 +00:00
Konstantin Zhuravlyov f2f3d14774 [AMDGPU] Emit debugger prologue and emit the rest of the debugger fields in the kernel code header
Debugger prologue is emitted if -mattr=+amdgpu-debugger-emit-prologue.

Debugger prologue writes work group IDs and work item IDs to scratch memory at fixed location in the following format:
  - offset 0: work group ID x
  - offset 4: work group ID y
  - offset 8: work group ID z
  - offset 16: work item ID x
  - offset 20: work item ID y
  - offset 24: work item ID z

Set
  - amd_kernel_code_t::debug_wavefront_private_segment_offset_sgpr to scratch wave offset reg
  - amd_kernel_code_t::debug_private_segment_buffer_sgpr to scratch rsrc reg
  - amd_kernel_code_t::is_debug_supported to true if all debugger features are enabled

Differential Revision: http://reviews.llvm.org/D20335

llvm-svn: 273769
2016-06-25 03:11:28 +00:00
Konstantin Zhuravlyov 29ddd2b2f2 [AMDGPU][NFC] Rename ReserveTrapVGPRs -> ReserveRegs
Differential Revision: http://reviews.llvm.org/D20081

llvm-svn: 270594
2016-05-24 18:37:18 +00:00
Konstantin Zhuravlyov 71515e57f9 [AMDGPU] Move reserved vgpr count for trap handler usage to SIMachineFunctionInfo + minor commenting changes
Differential Revision: http://reviews.llvm.org/D19537

llvm-svn: 267573
2016-04-26 17:24:40 +00:00
Matt Arsenault 99c14524ec AMDGPU: Implement addrspacecast
llvm-svn: 267452
2016-04-25 19:27:24 +00:00
Tom Stellard 79a1fd718c AMDGPU: allow specifying a workgroup size that needs to fit in a compute unit
Summary:
For GL_ARB_compute_shader we need to support workgroup sizes of at least 1024. However, if we want to allow large workgroup sizes, we may need to use less registers, as we have to run more waves per SIMD.

This patch adds an attribute to specify the maximum work group size the compiled program needs to support. It defaults, to 256, as that has no wave restrictions.

Reducing the number of registers available is done similarly to how the registers were reserved for chips with the sgpr init bug.

Reviewers: mareko, arsenm, tstellarAMD, nhaehnle

Subscribers: FireBurn, kerberizer, llvm-commits, arsenm

Differential Revision: http://reviews.llvm.org/D18340

Patch By: Bas Nieuwenhuizen

llvm-svn: 266337
2016-04-14 16:27:07 +00:00
Tom Stellard f110f8f9f7 AMDGPU/SI: Use the correct scratch wave offset register for shaders.
Summary:
The code previously always used s1 as it was using the user + system SGPR
information for compute kernels. This is incorrect for Mesa shaders though,

The register should be the next SGPR after all user and system SGPR's.
We use that Mesa adds arguments for all input and system SGPR's and
take the next available SGPR for the scratch wave offset register.

Signed-off-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>

Reviewers: mareko, arsenm, nhaehnle, tstellarAMD

Subscribers: qcolombet, arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D18941

Patch By: Bas Nieuwenhuizen

llvm-svn: 266336
2016-04-14 16:27:03 +00:00