| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
brw_link.cpp:76:44: warning: unused parameter ‘shader_type’ [-Wunused-parameter]
gl_shader_stage shader_type,
^
brw_nir.c: In function ‘brw_nir_lower_vs_inputs’:
brw_nir.c:194:55: warning: unused parameter ‘devinfo’ [-Wunused-parameter]
const struct gen_device_info *devinfo,
^
brw_vec4_visitor.cpp:914:37: warning: unused parameter ‘sampler’ [-Wunused-parameter]
uint32_t sampler,
^
brw_vec4_visitor.cpp:1146:34: warning: unused parameter ‘stream_id’ [-Wunused-parameter]
vec4_visitor::gs_emit_vertex(int stream_id)
^
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
|
|
|
|
|
| |
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
|
|
|
|
|
|
|
| |
This will make it easier to add more operations.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
in bytes.
The previous regs_written field can be recovered by rewriting each
rvalue reference of regs_written like 'x = i.regs_written' to 'x =
DIV_ROUND_UP(i.size_written, reg_unit)', and each lvalue reference
like 'i.regs_written = x' to 'i.size_written = x * reg_unit'.
For the same reason as in the previous patches, this doesn't attempt
to be particularly clever about simplifying the result in the interest
of keeping the rather lengthy patch as obvious as possible. I'll come
back later to clean up any ugliness introduced here.
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
expressed in bytes.
The dst/src_reg::offset field in byte units introduced in the previous
patch is a more straightforward alternative to an offset
representation split between ::reg_offset and ::subreg_offset fields.
The split representation makes it too easy to forget about one of the
offsets while dealing with the other, which has led to multiple FS
back-end bugs in the past. To make the matter worse the unit
reg_offset was expressed in was rather inconsistent, for uniforms it
would be expressed in either 4B or 16B units depending on the
back-end, and for most other things it would be expressed in 32B
units.
This encodes reg_offset as a new offset field expressed consistently
in byte units. Each rvalue reference of reg_offset in existing code
like 'x = r.reg_offset' is rewritten to 'x = r.offset / reg_unit', and
each lvalue reference like 'r.reg_offset = x' is rewritten to
'r.offset = r.offset % reg_unit + x * reg_unit'.
Because the change affects a lot of places and is rather non-trivial
to verify due to the inconsistent value of reg_unit, I've tried to
avoid making any additional changes other than applying the rewrite
rule above in order to keep the patch as simple as possible, sometimes
at the cost of introducing obvious stupidity (e.g. algebraic
expressions that could be simplified given some knowledge of the
context) -- I'll clean those up later on in a second pass.
v2: Fix division by the wrong reg_unit in the UNIFORM case of
convert_to_hw_regs(). (Iago)
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
|
|
|
|
|
|
|
|
|
|
|
| |
Here we create a new output_generic_reg array with the ability to
store the dst_reg for each component of user defined varyings.
This is needed as the previous code only stored the dst_reg based
on the varying location which meant packed varyings would overwrite
each other.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
|
|
|
|
|
| |
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
From the Sky Lake PRM:
"For SURFTYPE_CUBE: For Sampling Engine Surfaces and Typed Data Port
Surfaces, the range of this field is [0,340], indicating the number of
cube array elements (equal to the number of underlying 2D array elements
divided by 6). For other surfaces, this field must be zero."
In other words, the depth field for cube maps is in number of cubes not
number of 2-D slices so we need to divide by 6. ISL will do this correctly
for us assuming that we provide it with the correct array bounds which it
expects to be in 2-D slices. It appears as if we've been doing this wrong
ever since we first added cube map arrays for Sandy Bridge and the change
to ISL made things slightly worse. While we're at it, we now need to remoe
the shader hacks we've always done since they were only needed because we
were setting the depth field six times too large.
v2: Fix the vec4 backend as well (not sure how I missed this).
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Reviewed-by: Chris Forbes <chrisforbes@google.com>
|
|
|
|
|
|
|
| |
v2: Rebase on changes to previous two patches.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
|
|
|
|
|
|
|
|
|
| |
v2: Retype LZD source as UD to avoid potential problems with 0x80000000.
Suggested by Matt. Also update comment about problem values with
LZD(abs(x)). Suggested by Curro.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
|
|
|
|
|
|
|
|
|
|
| |
This uses one less instruction.
v2: Move emit_find_msb_using_lzd out of the visitor classes. Suggested
by Curro.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
|
|
|
|
|
|
|
|
|
|
| |
Cuts 6K of .text.
text data bss dec hex filename
5772372 264648 29320 6066340 5c90a4 lib/i965_dri.so before
5766074 264648 29320 6060042 5c780a lib/i965_dri.so after
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
|
|
|
|
|
|
|
|
|
|
|
|
| |
The only place that actually used the type parameter was the GS visitor,
and it was always passed glsl_type::int. Just remove the parameter.
brw_vec4_vs_visitor.cpp:38:61: warning: unused parameter ‘type’ [-Wunused-parameter]
const glsl_type *type)
^
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Timothy Arceri <timothy.arceri@collabora.com>
|
|
|
|
|
|
|
|
|
| |
This matches the "foreach x in container" pattern found in many other
programming languages. Generated by the following regular expression:
s/nir_foreach_function(\([^,]*\),\s*\([^,]*\))/nir_foreach_function(\2, \1)/
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
|
|
|
|
|
|
|
|
|
|
|
| |
This matches the "foreach x in container" pattern found in many other
programming languages. Generated by the following regular expression:
s/nir_foreach_instr(\([^,]*\),\s*\([^,]*\))/nir_foreach_instr(\2, \1)/
and similar expressions for nir_foreach_instr_safe etc.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
|
|
|
|
| |
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
|
|
|
|
| |
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
|
|
|
|
|
|
|
|
|
| |
This was actually caught by Ken in review the first time around but somehow
didn't get fixed before the patches were pushed. :-(
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94998
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=95001
|
|
|
|
|
|
|
|
| |
We shouldn't be reading the const_index directly
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94998
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=95001
|
|
|
|
|
|
|
|
|
| |
Up until now, we have been able to assume that all push constants are
vec4-aligned because this is what the GL driver gives us. In Vulkan, we
need to be able to support full std140 because we get the layout from the
client.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
|
|
|
|
|
| |
Reviewed-by: Kristian Høgsberg <krh@bitplanet.net>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This commit moves us to an instruction based model rather than a
register-based model for indirects. This is more accurate anyway as we
have to emit instructions to resolve the reladdr. It's also a lot simpler
because it gets rid of the recursive reladdr problem by design.
One side-effect of this is that we need a whole new algorithm in
move_uniform_array_access_to_pull_constants. This new algorithm is much
more straightforward than the old one and is fairly similar to what we're
already doing in the FS backend.
Reviewed-by: Kristian Høgsberg <krh@bitplanet.net>
Acked-by: Kenneth Graunke <kenneth@whitecape.org>
|
|
|
|
| |
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
|
|
|
|
| |
Reviewed-by: Matt Turner <mattst88@gmail.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This makes the extra multiply visible to NIR's algebraic optimizations
(for constant reassociation) as well as constant folding. This means
that when the result of sin/cos are multiplied by an constant, we can
eliminate the extra multiply altogether, reducing the cost of the
workaround.
It also means we only have to implement it one place, rather than in
both backends.
This makes INTEL_PRECISE_TRIG=1 cost nothing on GPUTest/Volplosion,
which has a ton of sin() calls, but always multiplies them by an
immediate constant. The extra multiply gets folded away.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eduardo Lima Mitev <elima@igalia.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Matt Turner <mattst88@gmail.com>
|
|
|
|
|
|
|
|
|
| |
Our hardware requires an LOD for all texelFetch commands even if they are
on buffer textures. GLSL IR gives us an LOD of 0 in that case, but the LOD
is really rather meaningless. This commit allows other NIR producers to be
more lazy and not provide one at all.
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The SIN and COS instructions on Intel hardware can produce values
slightly outside of the [-1.0, 1.0] range for a small set of values.
Obviously, this can break everyone's expectations about trig functions.
According to an internal presentation, the COS instruction can produce
a value up to 1.000027 for inputs in the range (0.08296, 0.09888). One
suggested workaround is to multiply by 0.99997, scaling down the
amplitude slightly. Apparently this also minimizes the error function,
reducing the maximum error from 0.00006 to about 0.00003.
When enabled, fixes 16 dEQP precision tests
dEQP-GLES31.functional.shaders.builtin_functions.precision.
{cos,sin}.{highp,mediump}_compute.{scalar,vec2,vec4,vec4}.
at the cost of making every sin and cos call more expensive (about
twice the number of cycles on recent hardware). Enabling this
option has been shown to reduce GPUTest Volplosion performance by
about 10%.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
|
|
|
|
| |
Reviewed-by: Matt Turner <mattst88@gmail.com>
|
|
|
|
|
| |
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
|
|
|
|
|
|
|
| |
Now that brw_vec4_visitor::emit_untyped_atomic was removed, there is no need
to explicitly set it.
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
brw_vec4_visitor
surface_access emit_untyped_read and emit_untyped_atomic provides the same
functionality.
v2: surface parameter of emit_untyped_atomic is a const, no need to
specify default predicate on emit_untyped_atomic, use retype
(Francisco Jerez).
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
(This is commit 4a1c8a3037cd29938b2a6e2c680c341e9903cfbe for vec4 mode.)
Using the push model for inputs is much more efficient than pulling
inputs - the hardware can simply copy a large chunk into URB registers
at thread creation time, rather than having the thread send messages to
request data from the L3 cache. Unfortunately, it's possible to have
more TES inputs than fit in registers, so we have to fall back to the
pull model in some cases.
However, it turns out that most tessellation evaluation shaders are
fairly simple, and don't use many inputs. An arbitrary cut-off of
24 vec4 slots (12 registers) should suffice. (I chose this instead of
the 32 vec4 slots used in the scalar backend to avoid regressing a few
Piglit tests due to the vec4 register allocator being too stupid to
figure out what to do. We probably ought to fix that, but it's a
separate issue.)
Improves performance in GPUTest's tessmark_x64 microbenchmark by
41.5394% +/- 0.288519% (n = 115) at 1024x768 on my Clevo W740SU
(with Iris Pro 5200).
Improves performance in Synmark's Gl40TerrainFlyTess microbenchmark by
38.3576% +/- 0.759748% (n = 42).
v2: Simplify abs/negate handling, as requested by Matt.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Matt Turner <mattst88@gmail.com>
|
|
|
|
|
|
|
|
|
|
|
| |
When NIR was originally drafted, there was no easy way to determine if
something was constant or not. The result was that we had lots of
special-casing for constant values such as this. Now that load_const
instructions are SSA-only, it's really easy to find constants and this
isn't really needed anymore.
Reviewed-by: Connor Abbott <cwabbott0@gmail.com>
Reviewed-by: Rob Clark <robclark@gmail.com>
|
|
|
|
| |
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This commit adds the capability to NIR to support separate textures and
samplers. As it currently stands, glsl_to_nir only sets the texture deref
and leaves the sampler deref alone as it did before and nir_lower_samplers
assumes this. Backends can still assume that they are combined and only
look at only at the texture index. Or, if they wish, they can assume that
they are separate because nir_lower_samplers, tgsi_to_nir, and prog_to_nir
all set both texture and sampler index whenever a sampler is required (the
two indices are the same in this case).
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
|
|
|
|
|
|
|
|
|
| |
We're about to separate the two concepts. When we do, the sampler will
become optional. Doing a rename first makes the separation a bit more
safe because drivers that depend on GLSL or TGSI behaviour will be fine to
just use the texture index all the time.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
|
|
|
|
|
|
|
| |
And mark nir_op_pack_uvec4_to_uint unreachable, since it's only produced
by lowering pack[SU]norm4x8 which the vec4 backend does not need.
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
|
| |
|
|
|
|
|
|
|
|
| |
BDW adds the following restriction: "When multiplying DW x DW, the dst
cannot be accumulator."
Cc: "11.1,11.0" <mesa-stable@lists.freedesktop.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The OpenGL specifications for bitfieldExtract() says:
The result will be undefined if <offset> or <bits> is negative, or if
the sum of <offset> and <bits> is greater than the number of bits
used to store the operand.
Therefore passing bits=32, offset=0 is legal and defined in GLSL.
But the earlier SM5 ubfe/ibfe opcodes are specified to accept a bitfield width
ranging from 0-31. As such, Intel and AMD instructions read only the low 5 bits
of the width operand, making them not able to implement the GLSL-specified
behavior directly.
This commit adds ubfe/ibfe operations from SM5 and a lowering pass for
bitfield_extract to to handle the trivial case of <bits> = 32 as
bitfieldExtract:
bits > 31 ? value : bfe(value, offset, bits)
Fixes:
ES31-CTS.shader_bitfield_operation.bitfieldExtract.uvec3_0
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=92595
Reviewed-by: Connor Abbott <cwabbott0@gmail.com>
Tested-by: Marta Lofstedt <marta.lofstedt@intel.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
TGSI doesn't use these - it just translates ir_quadop_bitfield_insert
directly. NIR can handle ir_quadop_bitfield_insert as well.
These opcodes were only used for i965, and with Jason's recent patches,
we can do this lowering in NIR (which also gains us SPIR-V handling).
So there's not much point to retaining this GLSL IR lowering code.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
|
|
|
|
|
|
|
|
|
|
| |
We have to break open a new vec4 for gl_DrawIDARB. We've used up all
space in the vec4 we use for SGVS and gl_DrawIDARB has to come from its
own separate vertex buffer anyway. This is because we point the vb for
base vertex and base instance into the draw parameter BO for indirect
draw calls, but the draw id is generated by mesa in a different buffer.
Reviewed-by: Anuj Phogat <anuj.phogat@gmail.com>
|
|
|
|
|
|
|
| |
We already have gl_BaseVertexARB in the .x component of the SGVS vec4
and plug gl_BaseInstanceARB into the last free component (.y).
Reviewed-by: Anuj Phogat <anuj.phogat@gmail.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When Connor originally drafted NIR, he copied the same function+overload
system that GLSL IR had with a few names changed. However, this
double-indirection is not really needed and has only served to confuse
people. Instead, let's just have functions which may not have unique names
and may or may not have an implementation. If someone wants to do overload
resolving, they can hav a hash table based function+overload system in the
overload resolving pass. There's no good reason to keep it in core NIR.
Reviewed-by: Connor Abbott <cwabbott0@gmail.com>
Acked-by: Kenneth Graunke <kenneth@whitecape.org>
ir3 bits are
Reviewed-by: Rob Clark <robclark@gmail.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The TCS is the first tessellation shader stage, and the most
complicated. It has access to each of the control points in the input
patch, and computes a new output patch. There is one logical invocation
per output control point; all invocations run in parallel, and can
communicate by reading and writing output variables.
One of the main responsibilities of the TCS is to write the special
gl_TessLevelOuter[] and gl_TessLevelInner[] output variables which
control how much new geometry the hardware tessellation engine will
produce. Otherwise, it simply writes outputs that are passed along
to the TES.
We run in SIMD4x2 mode, handling two logical invocations per EU thread.
The hardware doesn't properly manage the dispatch mask for us; it always
initializes it to 0xFF. We wrap the whole program in an IF..ENDIF block
to handle an odd number of invocations, essentially falling back to
SIMD4x1 on the last thread.
v2: Update comments (requested by Jordan Justen).
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
For a select whose condition is any(v), instead of emitting
cmp.nz.f0(8) null<1>D g1<0,4,1>D 0D
mov(8) g7<1>.xUD 0x00000000UD
(+f0.any4h) mov(8) g7<1>.xUD 0xffffffffUD
cmp.nz.f0(8) null<1>D g7<4,4,1>.xD 0D
(+f0) sel(8) g8<1>UD g4<4,4,1>UD g3<4,4,1>UD
we now emit
cmp.nz.f0(8) null<1>D g1<0,4,1>D 0D
(+f0.any4h) sel(8) g9<1>UD g4<4,4,1>UD g3<4,4,1>UD
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
|
|
|
|
|
|
|
|
|
|
|
| |
As in the previous patches, these can be implemented as
any(v) -> any_nequal(v, false)
all(v) -> all_equal(v, true)
and their removal simplifies the code in the next patch.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
There is some special-casing needed in a competent back-end. However, they
can do their special-casing easily enough based on whether or not the
offset is a constant. In the mean time, having the *_indirect variants
adds special cases a number of places where they don't need to be and, in
general, only complicates things. To complicate matters, NIR had no way to
convdert an indirect load/store to a direct one in the case that the
indirect was a constant so we would still not really get what the back-ends
wanted. The best solution seems to be to get rid of the *_indirect
variants entirely.
This commit is a bunch of different changes squashed together:
- nir: Get rid of *_indirect variants of input/output load/store intrinsics
- nir/glsl: Stop handling UBO/SSBO load/stores differently depending on indirect
- nir/lower_io: Get rid of load/store_foo_indirect
- i965/fs: Get rid of load/store_foo_indirect
- i965/vec4: Get rid of load/store_foo_indirect
- tgsi_to_nir: Get rid of load/store_foo_indirect
- ir3/nir: Use the new unified io intrinsics
- vc4: Do all uniform loads with byte offsets
- vc4/nir: Use the new unified io intrinsics
- vc4: Fix load_user_clip_plane crash
- vc4: add missing src for store outputs
- vc4: Fix state uniforms
- nir/lower_clip: Update to the new load/store intrinsics
- nir/lower_two_sided_color: Update to the new load intrinsic
NIR and i965 changes are
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
NIR indirect declarations and vc4 changes are
Reviewed-by: Eric Anholt <eric@anholt.net>
ir3 changes are
Reviewed-by: Rob Clark <robdclark@gmail.com>
NIR changes are
Acked-by: Rob Clark <robdclark@gmail.com>
|
|
|
|
|
|
|
|
|
|
| |
This commit pushes makes uniform offsets be terms of bytes starting with
nir_lower_io. They get converted to be in terms of vec4s or floats when we
cram them in the UNIFORM register file but reladdr remains in terms of
bytes all the way down to the point where we lower it to a pull constant
load.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
|
|
|
|
|
|
| |
Cc: "11.0" <mesa-stable@lists.freedesktop.org>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=92909
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
|