Nicolai Hähnle
3c77f26ccc
amd/common: whitespace fixes
...
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
2018-12-19 12:01:12 +01:00
Rhys Perry
12dc7cb202
ac: refactor visit_load_buffer
...
This is so that we can split different types of loads more easily.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
2018-12-16 14:56:10 +00:00
Samuel Pitoiset
3fbdcd942f
amd: remove support for LLVM 6.0
...
User are encouraged to switch to LLVM 7.0 released in September 2018.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
2018-12-06 14:02:56 +01:00
Dave Airlie
ec9fe8abc7
ac: avoid casting pointers on bcsel and stores
...
For variable pointers we really don't want to case the pointers to int
without a good reason, just add a wrapper for bcsel loading and result
storing.
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-11-21 08:54:25 +10:00
Bas Nieuwenhuizen
dd0172e865
radv: Use structured intrinsics instead of indexing workaround for GFX9.
...
These force the index to be used in the instruction so we don't need the
workaround.
Totals:
SGPRS: 1321642 -> 1321802 (0.01 %)
VGPRS: 943664 -> 943788 (0.01 %)
Spilled SGPRs: 28468 -> 28480 (0.04 %)
Spilled VGPRs: 88 -> 89 (1.14 %)
Private memory VGPRs: 0 -> 0 (0.00 %)
Scratch size: 80 -> 80 (0.00 %) dwords per thread
Code Size: 52415292 -> 52338932 (-0.15 %) bytes
LDS: 400 -> 400 (0.00 %) blocks
Max Waves: 233903 -> 233803 (-0.04 %)
Wait states: 0 -> 0 (0.00 %)
Totals from affected shaders:
SGPRS: 238344 -> 238504 (0.07 %)
VGPRS: 232732 -> 232856 (0.05 %)
Spilled SGPRs: 13125 -> 13137 (0.09 %)
Spilled VGPRs: 88 -> 89 (1.14 %)
Private memory VGPRs: 0 -> 0 (0.00 %)
Scratch size: 80 -> 80 (0.00 %) dwords per thread
Code Size: 15752712 -> 15676352 (-0.48 %) bytes
LDS: 139 -> 139 (0.00 %) blocks
Max Waves: 31680 -> 31580 (-0.32 %)
Wait states: 0 -> 0 (0.00 %)
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
2018-11-19 23:36:00 +01:00
Marek Olšák
8676af12c8
ac: fix ac_build_fdiv for f64
...
trivial
Fixes: a5f35aa742
2018-10-29 17:24:21 -04:00
Connor Abbott
59535b05cf
ac: Introduce ac_build_expand()
...
And implement ac_bulid_expand_to_vec4() on top of it.
Fixes: 7e7ee82698
("ac: add support for 16bit buffer loads")
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-10-22 09:44:51 +02:00
Marek Olšák
bfc795670e
ac: add helpers for fast integer division by a constant
2018-10-16 17:23:25 -04:00
Samuel Pitoiset
416013b4f5
radv: emit the GLC bit for SSBO loads/stores when needed
...
This fixes some new memory model tests:
dEQP-VK.memory_model.message_passing.core11.u32.coherent.fence_fence.atomicwrite.device.*
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108112
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-10-12 08:42:08 +02:00
Marek Olšák
77903c8cfb
ac: add ac_build_round
2018-10-06 21:50:09 -04:00
Marek Olšák
82f5f89bf6
ac: simplify LLVM alloca helpers
2018-10-06 21:50:09 -04:00
Marek Olšák
a668c8d6ba
ac: define all address spaces properly
2018-10-06 21:50:09 -04:00
Samuel Pitoiset
cd76ce0078
ac: add 16-bit support to ac_build_bitfield_reverse()
...
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-09-17 15:18:37 +02:00
Samuel Pitoiset
fc398f4d67
ac: add 16-bit support to ac_build_bit_count()
...
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-09-17 15:18:34 +02:00
Samuel Pitoiset
94dd08eb7c
ac: add 16-bit support to ac_find_lsb()
...
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-09-17 15:18:32 +02:00
Samuel Pitoiset
5a6c8ca3e8
ac: add 16-bit support to ac_build_umsb()
...
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-09-17 15:18:30 +02:00
Samuel Pitoiset
3e7f3e2cd1
ac: add 16-bit support to ac_build_isign()
...
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-09-17 15:18:28 +02:00
Samuel Pitoiset
cfd6314cfe
ac: add 16-bit constant values for zero and one
...
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-09-17 15:18:26 +02:00
Samuel Pitoiset
074e29183c
ac: add ac_build_bifield_reverse() helper
...
Are we missing 64-bit support?
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-09-17 15:18:23 +02:00
Samuel Pitoiset
371c35e5bb
ac: add ac_build_bit_count() helper
...
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-09-17 15:18:20 +02:00
Marek Olšák
be0bd95abf
radeonsi: fix GPU hangs with bindless textures and LLVM 7.0
...
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
2018-09-10 15:19:56 -04:00
Marek Olšák
cc36ebbdc3
ac: use iN_0/1 constants
...
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
2018-09-10 15:19:56 -04:00
Marek Olšák
a5f35aa742
ac: revert new LLVM 7.0 behavior for fdiv
...
Cc: 18.2 <mesa-stable@lists.freedesktop.org>
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
2018-09-10 15:19:56 -04:00
Marek Olšák
60beac9efc
ac,radeonsi: use ac_build_fmad
...
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
2018-08-21 20:50:37 -04:00
Marek Olšák
659f2e0fcb
ac: add imad & fmad helpers
...
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
2018-08-21 20:50:37 -04:00
Marek Olšák
2276f8f064
ac: add ac_build_s_barrier
...
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
2018-08-21 20:50:37 -04:00
Marek Olšák
fd1121e839
amd: remove support for LLVM 5.0
...
Users are encouraged to switch to LLVM 6.0 released in March 2018.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
2018-08-03 18:36:11 -04:00
Daniel Schürmann
a6a21e651d
ac: add support for 16bit UBO loads
...
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-07-23 23:16:25 +02:00
Daniel Schürmann
f582367d49
ac: add 16bit conversion operations
...
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-07-23 23:16:25 +02:00
Marek Olšák
4695984dbc
ac: fold LLVMContext creation into ac_llvm_context_init
...
Reviewed-by: Dave Airlie <airlied@redhat.com>
2018-07-04 15:48:18 -04:00
Marek Olšák
e5e57c3a5e
ac: handle undefined EQAA samples in ac_apply_fmask_to_sample
...
RADV might wanna use this helper too.
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
2018-06-13 22:00:12 -04:00
Timothy Arceri
fae3b38770
ac: fix possible truncation of intrinsic name
...
Fixes the gcc warning:
snprintf’ output between 26 and 33 bytes into a destination of size 32
Fixes: d5f7ebda3e
("ac: add LLVM build functions for subgroup instrinsics")
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-06-08 09:24:15 +10:00
Bas Nieuwenhuizen
4fc2d5e141
amd/common: Fix number of coords for getlod.
...
The LLVM 6 code reduced it to a non-array call. We need to do that
with the new code too.
This fixes dEQP-VK.glsl.texture_functions.query.texturequerylod.*array* for radv.
Fixes: a9a7993441
"amd/common: use the dimension-aware image intrinsics on LLVM 7+"
Reviewed-by: Dave Airlie <airlied@redhat.com>
2018-06-07 23:59:52 +02:00
Nicolai Hähnle
a9a7993441
amd/common: use the dimension-aware image intrinsics on LLVM 7+
...
Requires LLVM trunk r329166.
Acked-by: Marek Olšák <marek.olsak@amd.com>
2018-06-04 21:34:59 +02:00
Bas Nieuwenhuizen
699e1f5aac
ac: Use DPP for build_ddxy where possible.
...
WQM is pretty reliable now on LLVM 7, so let us just use
DPP + WQM.
This gives approximately a 1.5% performance increase on the
vrcompositor built-in benchmark.
v2: Use ac_build_quad_swizzle.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
2018-05-23 21:02:45 +02:00
Marek Olšák
f9eb1ef870
amd: remove support for LLVM 4.0
...
It doesn't support GFX9.
Acked-by: Dave Airlie <airlied@redhat.com>
Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
2018-05-17 14:54:41 -04:00
Dave Airlie
eba4cf797c
ac/llvm: use amdgcn.tbuffer.store instead of SI.tbuffer.store intrinsic
...
Drop the use of the old intrinsic.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
2018-05-17 11:46:53 +10:00
Nicolai Hähnle
c0acb596f4
amd/common: use llvm.amdgcn.wqm for explicit derivatives
...
To comply with an upcoming change in LLVM, see
https://reviews.llvm.org/D46051
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-05-04 11:02:48 +02:00
Samuel Pitoiset
d136a5fad9
ac: fix the number of coordinates for ac_image_get_lod and arrays
...
This fixes crashes for the following CTS:
dEQP-VK.glsl.texture_functions.query.texturequerylod.*
Cubemaps are the same as 2D arrays.
Fixes: 625dcbbc45
("amd/common: pass address components individually to
ac_build_image_intrinsic")
Cc: 18.1 <mesa-stable@lists.freedesktop.org>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
2018-04-23 21:48:38 +02:00
Nicolai Hähnle
24fb3e6aa1
ac/nir: use ac_build_image_opcode for image intrinsics
...
So that we'll use the dimension-aware intrinsics in the future.
Acked-by: Marek Olšák <marek.olsak@amd.com>
2018-04-20 09:30:07 +02:00
Nicolai Hähnle
74063431f1
radeonsi: generate image load/store/atomic ops using ac_build_image_opcode
...
In preparation of dimension-aware LLVM image intrinsics.
Acked-by: Marek Olšák <marek.olsak@amd.com>
2018-04-20 09:29:57 +02:00
Nicolai Hähnle
625dcbbc45
amd/common: pass address components individually to ac_build_image_intrinsic
...
This is in preparation for the new image intrinsics.
Acked-by: Marek Olšák <marek.olsak@amd.com>
2018-04-20 09:23:52 +02:00
Nicolai Hähnle
f931583828
amd/common: pass new enum ac_image_dim to ac_build_image_opcode
...
This is in preparation for the new, dimension-aware LLVM image
intrinsics.
Acked-by: Marek Olšák <marek.olsak@amd.com>
2018-04-20 09:23:40 +02:00
Daniel Schürmann
d5f7ebda3e
ac: add LLVM build functions for subgroup instrinsics
...
Co-authored-by: Connor Abbott <cwabbott0@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-04-14 01:03:09 +02:00
Daniel Schürmann
d19f20e793
ac: make ballot and umsb capable of 64bit inputs
...
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-04-14 00:52:22 +02:00
Marek Olšák
dc04e4bba2
radeonsi: move FMASK shader logic to shared code
...
We'll need it for FBFETCH in both TGSI and NIR paths.
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
2018-04-02 13:55:22 -04:00
Bas Nieuwenhuizen
4503ff760c
ac/nir: Add workaround for GFX9 buffer views.
...
On GFX9 whether the buffer size is interpreted as elements or bytes
depends on whether IDXEN is enabled in the instruction. If the index
is a constant zero, LLVM optimizes IDXEN to 0.
Now the size in elements is interpreted in bytes which of course
results in out of bounds accesses.
The correct fix is most likely to disable the LLVM optimization,
but we need something to work with LLVM <= 6.0.
radeonsi does the max between stride and element count on the CPU
but that results in the size intrinsics returning the wrong size
for the buffer. This would cause CTS errors for radv.
v2: Also include the store changes.
Fixes: e38685cc62
'Revert "radv: disable support for VEGA for now."'
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
2018-03-29 00:03:03 +02:00
Samuel Pitoiset
61a91ca3f5
ac/nir: move unpack_param() to ac_llvm_build.c
...
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-03-13 14:05:06 +01:00
Samuel Pitoiset
28bb6873ec
ac/nir: move trim_vector to ac_llvm_build.c
...
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-03-13 14:05:06 +01:00
Samuel Pitoiset
895632baef
ac/nir: move cast_ptr() to ac_llvm_build.c
...
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
2018-03-13 14:05:06 +01:00