9 Commits

Author SHA1 Message Date
Diana Picus
bc6955f18c
[AMDGPU] Don't fix the scavenge slot at offset 0 (#79136)
At the moment, the emergency spill slot is a fixed object for entry
functions and chain functions, and a regular stack object otherwise.
This patch adopts the latter behaviour for entry/chain functions too. It
seems this was always the intention [1] and it will also save us a bit
of stack space in cases where the first stack object has a large
alignment.

[1]
34c8b835b1
2024-02-09 09:20:25 +01:00
Jay Foad
42b9ea841e
[AMDGPU] Increase max scratch allocation for GFX12 (#77625) 2024-01-17 10:25:28 +00:00
Jay Foad
e2e5d59236 [AMDGPU] Add GFX10/GFX11 wave64 test coverage in huge-private-buffer.ll 2023-01-10 14:17:09 +00:00
Nikita Popov
bdf2fbba9c [AMDGPU] Convert some tests to opaque pointers (NFC) 2022-12-19 12:41:13 +01:00
Jay Foad
898b18844c [AMDGPU] Add GFX11 to some tests with manual checks
Differential Revision: https://reviews.llvm.org/D138138
2022-11-17 09:42:28 +00:00
Stanislav Mekhanoshin
0846c125f9 [AMDGPU] gfx1010 core wave32 changes
Differential Revision: https://reviews.llvm.org/D63204

llvm-svn: 363934
2019-06-20 15:08:34 +00:00
Matt Arsenault
5c714cbdd8 AMDGPU: Correct maximum possible private allocation size
We were assuming a much larger possible per-wave visible stack
allocation than is possible:

faa3ae5138/src/core/runtime/amd_gpu_agent.cpp (L70)

Based on this, we can assume the high 15 bits of a frame index or sret
are 0. The frame index value is the per-lane offset, so the maximum
frame index value is MAX_WAVE_SCRATCH / wavesize.

Remove the corresponding subtarget feature and option that made
this configurable.

llvm-svn: 361541
2019-05-23 19:38:14 +00:00
Yaxun Liu
2a22c5deff [AMDGPU] Switch to the new addr space mapping by default
This requires corresponding clang change.

Differential Revision: https://reviews.llvm.org/D40955

llvm-svn: 324101
2018-02-02 16:07:16 +00:00
Matt Arsenault
45b98189bd AMDGPU: Don't use MUBUF vaddr if address may overflow
Effectively revert r263964. Before we would not
allow this if vaddr was not known to be positive.

llvm-svn: 318240
2017-11-15 00:45:43 +00:00