b3119a3 introduced a strict LLVM requirement for r300 on all
architectures and thus configure fails on architectures where LLVM is
not available or buggy.
r300 doesn't strictly require LLVM, but for performance reasons we
highly recommend LLVM usage. So require it at least on x86 and x86_64
architectures as we have done before b3119a3.
Fixes: b3119a3 ("configure.ac: Check gallium LLVM version in gallium_require_llvm")
Cc: 17.0 <mesa-stable@lists.freedesktop.org>
Signed-off-by: Andreas Boll <andreas.boll.dev@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
All of these have had support for the TGSI opcodes since before most of
the glsl compiler work landed.
Also update the docs accordingly, including the missing note about i965.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
v2: add conversion opcodes.
v3 (idr): Rebase on replacemtn of TGSI_OPCODE_I2U64 with
TGSI_OPCODE_I2I64.
v4 (idr): "cut them down later" => Remove ir_unop_b2u64 and
ir_unop_u642b. Handle these with extra i2u or u2i casts just like
uint(bool) and bool(uint) conversion is done.
v5 (nha): add clarifying comment about a subtle assumption
Signed-off-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
v1.1: move to using a normal CAP. (Marek)
v2: fill in the cap everywhere
Signed-off-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
which is not applicable for "all slices at each lod". Current
logic makes one to believe it has some purpose. When miptree
layout is calculated brw_miptree_layout_texture_array() sets
the qpitch unconditionally but later on ignores it altogether
for ALL_SLICES_AT_EACH_LOD.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Such as comment states for intel_miptree_hiz_buffer::mt, hiz_mt
only exists for gen6. In addition, intel_hiz_miptree_buf_create()
uses MIPTREE_LAYOUT_FORCE_ALL_SLICE_AT_LOD unconditionally.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
In intel_hiz_miptree_buf_create() intel_miptree_aux_buffer::bo
is unconditionally initialised to point to the same buffer
object as hiz_mt does. The same goes for
intel_miptree_aux_buffer::pitch/qpitch.
This will make following patches simpler to read.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
In intel_hiz_miptree_buf_create() intel_miptree_aux_buffer::bo
is unconditionally initialised to point to the same buffer
object as hiz_mt does. Also intel_miptree_aux_buffer::offset
is initialised to zero (calloc()).
This will make following patches significantly simpler to read.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Only caller, brw_workaround_depthstencil_alignment(), returns
early for gen6+.
While at it, reduce scope for brw_get_depthstencil_tile_masks() as
well.
Reviewed-by: Samuel Iglesias Gons\341lvez <siglesias@igalia.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
There exact same check earlier in brw_miptree_layout() which
intel_miptree_create_layout() in turn calls unconditionally.
Reviewed-by: Samuel Iglesias Gons\341lvez <siglesias@igalia.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
In addition, let intel_miptree_create_layout() release the
miptree - it is the allocator.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
We had a lot of memcpy call overhead because gpu_stride wasn't being
inlined. But if you split out the stride==8 and stride==16 cases like
this code does while still using memcpy, you'd no longer have glibc's
NEON memcpy applied at which point we'd be doing 16 uncached reads
instead of 64/(NEON memcpy granularity), for about a 30% performance
hit. By hand writing the assembly, we can get a whole cacheline
loaded at a time.
Unfortunately, NEON intrinsics turned out to be unusable -- they
didn't have the vldm instruction available.
Note that, for now, the NEON code is only enabled when building for ARMv7
(Pi 2+). We may want to do runtime detection for the Raspbian case, in
the future.
Improves 1024x1024 GetTexImage by 208.256% +/- 7.07029% (n=10).
Saves a measly 20 bytes on IA32 and nothing on x64. Depending on
exactly when this is applied, a lot of variation is possible due to
function alignment.
text data bss dec hex filename
6670131 228340 22552 6921023 699b3f lib/i965_dri.so before
6670111 228340 22552 6921003 699b2b lib/i965_dri.so after
6342932 293872 29880 6666684 65b9bc lib64/i965_dri.so before
6342932 293872 29880 6666684 65b9bc lib64/i965_dri.so after
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
By putting the parameters first that match the parameters to the call
site, 4 (of 14) instructions are saved at _mesa_Uniform4fv on x64. On
IA32, the details of the instructions change, but it is the same count
and mix of instructions.
Before:
0000000000000830 <_mesa_Uniform4fv>:
830: 48 83 ec 10 sub $0x10,%rsp
834: 49 89 d0 mov %rdx,%r8
837: 48 8b 15 00 00 00 00 mov 0x0(%rip),%rdx # 83e <_mesa_Uniform4fv+0xe>
83e: 89 f8 mov %edi,%eax
840: 89 f1 mov %esi,%ecx
842: 41 b9 02 00 00 00 mov $0x2,%r9d
848: 64 48 8b 3a mov %fs:(%rdx),%rdi
84c: 48 8b 97 c8 01 02 00 mov 0x201c8(%rdi),%rdx
853: 48 8b 72 70 mov 0x70(%rdx),%rsi
857: 6a 04 pushq $0x4
859: 89 c2 mov %eax,%edx
85b: e8 00 00 00 00 callq 860 <_mesa_Uniform4fv+0x30>
860: 48 83 c4 18 add $0x18,%rsp
864: c3 retq
After:
00000000000007f0 <_mesa_Uniform4fv>:
7f0: 48 83 ec 10 sub $0x10,%rsp
7f4: 48 8b 05 00 00 00 00 mov 0x0(%rip),%rax # 7fb <_mesa_Uniform4fv+0xb>
7fb: 41 b9 02 00 00 00 mov $0x2,%r9d
801: 64 48 8b 08 mov %fs:(%rax),%rcx
805: 48 8b 81 c8 01 02 00 mov 0x201c8(%rcx),%rax
80c: 6a 04 pushq $0x4
80e: 4c 8b 40 70 mov 0x70(%rax),%r8
812: e8 00 00 00 00 callq 817 <_mesa_Uniform4fv+0x27>
817: 48 83 c4 18 add $0x18,%rsp
81b: c3 retq
Saves a measly 416 bytes of text on x64. Depending on exactly when this
is applied, a lot of variation is possible due to function alignment.
text data bss dec hex filename
6670131 228340 22552 6921023 699b3f lib/i965_dri.so before
6670131 228340 22552 6921023 699b3f lib/i965_dri.so after
6343348 293872 29880 6667100 65bb5c lib64/i965_dri.so before
6342932 293872 29880 6666684 65b9bc lib64/i965_dri.so after
There is likely to be no performance change with just this patch.
_mesa_uniform immediately calls validate_uniform_parameters with
parameters in the "wrong" (different from the call site) order.
v2: Rebase on GL_ARB_gpu_shader_fp64.
v3: Rebase on GL_ARB_gpu_shader_int64.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Emil Velikov