For SIMD8 half float payload, each component takes a full register, so
we can use existing LOAD_PAYLOAD infrastruture for required padding by
alternating plain 8-wide half float vector and null vector.
Also this patch removes an unwanted assertion from
opt_copy_propagation_local for LOAD_PAYLOAD.
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com>
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11766>
To support SIMD8 half float payloads, each component takes one full
32bit wide register in both SIMD8H and SIMD16H mode. So we can make use
of existing LOAD_PAYLOAD infrastructure alternating a half float vector
and a null vector, in order to handle required padding.
v2: (Francisco)
- Skip header sources
- Fix comparision units
- Don't allocate VGRF for padded source
Signed-off-by: Sagar Ghuge <sagar.ghuge@intel.com>
Suggested-by: Francisco Jerez <currojerez@riseup.net>
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11766>
This function is big and I don't think it will won't get meaningfully
constant-propagated during inlining without LTO. Move it to a .c file so
we just have one copy, saving 2.8MB from libnir.a on an amd64 release
build.
text data bss total filename
before:
18953406 7768312 687260 27408978 build-release/driver-symlinks/iris_dri.so
9734366 5542453 481692 15758511 build-release/lib/libvulkan_intel.so
28687772 13310765 1168952 43167489 (TOTALS)
after:
15478350 7767864 687260 23933474 build-release/driver-symlinks/iris_dri.so
6810366 5541685 481692 12833743 build-release/lib/libvulkan_intel.so
22288716 13309549 1168952 36767217 (TOTALS)
No statistically significant performance difference on iris shader-db, n=8.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13889>
According to the spec the hardware locks the scoreboard on the first
or last thread switch (selected via shader state) and any TLB accesses
executed before this are not synchronized by hardware.
This change updates the logic to ensure we respect this requirement
and that we don't assume that the lock is acquired automatically
on the first TLB access, which is not valid at least since V3D 4.1+.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13910>
For this each driver must :
- report its clock_id (if no particular clock just default to cpu
boottime one)
- be able to sample its clock (gpu_timestamp())
The PPSDataSource will then emit timestamp correlation events in the
trace ensuring perfetto is able to display GPU & CPU events
appropriately on its timeline.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Antonio Caggiano <antonio.caggiano@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13831>
This solves a case where a NIR geometry shader was storing the output in
a non-constant:
vec4 32 ssa_1 = load_const (0xc0800000 /* -4.000000 */, 0xc1100000 /* -9.000000 */, 0x40400000 /* 3.000000 */, 0x40e00000 /* 7.000000 */)
vec1 32 ssa_7 = load_const (0x00000000 /* 0.000000 */)
vec1 32 ssa_8 = load_const (0x00000001 /* 0.000000 */)
vec1 32 ssa_9 = iadd ssa_7, ssa_8
vec1 32 ssa_19 = mov ssa_1.x
intrinsic store_output (ssa_19, ssa_9) (1, 1, 0, 160, 288) /* base=1 */ /* wrmask=x */ /* component=0 */ /* src_type=float32 */ /* location=32 slots=2 gs_streams(x=0 y=0 z=0 w=0) */
When lowering the VPM output we check if the destination (ssa_9 in this
case) is a constant to add to the VPM offset. We run a constant folding
optimization in an earlier VS lowering, and we should do the same for
GS.
This fixes multiple dEQP-VK.pipeline.interface_matching.* failures.
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13884>
While fragment and geometry shader were handling structs as inputs, they
weren't doing for it arrays of structures.
This fixes multiple dEQP-VK.pipeline.interface_matching.* failures and
assertions.
v2:
- Fix style (Iago).
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13884>
Now that we removed the intel intrinsic and just use the generic one,
we can skip it in the intel call lowering pass and just deal with it
in the intel rt intrinsic lowering.
v2: rewrite with nir_shader_instructions_pass() (Jason)
v3: handle everything in switch (Jason)
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: 423c47de99 ("nir: drop the btd_resume_intel intrinsic")
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12113>
TLSDESC speeds up access to dynamic TLS. This is especially important
for non-glibc targets, but is also helpful for non-initial-exec TLS
variables.
The entry asm does not support TLSDESC, but it only accesses
initial-exec symbols, so it is not necessary to handle that separately.
Acked-by: Tapani Pälli <tapani.palli@intel.com>
Acked-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12722>
Unlike Linux dma-bufs, D3D12 resources are strongly typed, and
can't necessarily just reinterpret the memory arbitrarily.
Allow importing resources with no description coming from the frontend,
and populate the resource desc from the driver instead. If there was
a template, make sure that it matches the incoming resource.
Reviewed-by: Bill Kristiansen <billkris@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13054>
Topi Pohjolainen