| Age | Commit message (Collapse) | Author |
|---|
|
Do not constant-fold a reciprocal if any component of the reciprocated
expression is 0. For example, do not constant-fold `1 / vec4(0, 1, 2, 3)`.
Incorrect, previous behavior
----------------------------
Reciprocals were constant-folded even when some component of the
reciprocated expression was 0. The incorrectly applied arithmetic was:
1 / 0 := 0
For example,
1 / vec4(0, 1, 2, 3) = vec4(0, 1, 1/2, 1/3)
NOTE: This is a candidate for the 7.9 and 7.10 branches.
|
|
Based on work from Jakob Bornecrantz, Michel Dänzer, and Brian Paul.
|
|
This has probably existed since e5e34ab18eeaffa465 or so.
NOTE: This is a candidate for the 7.9 and 7.10 branches.
|
|
This was my mistake when converting from talloc to ralloc. I was
confused because the other calls in the function are to asprintf_append
and the original code used str as the context rather than NULL.
Fixes bug #33823.
|
|
Join multiple exports into just one instruction
instead of exporting each register separately.
|
|
There's no such device. 0x4243 is a pci bridge id,
not a GPU.
Signed-off-by: Alex Deucher <alexdeucher@gmail.com>
|
|
Previously a register would be marked as available if any component
was written. This caused shaders such as this:
0: TEX TEMP[0].xyz, INPUT[14].xyyy, texture[0], 2D;
1: MUL TEMP[1], UNIFORM[0], TEMP[0].xxxx;
2: MAD TEMP[2], UNIFORM[1], TEMP[0].yyyy, TEMP[1];
3: MAD TEMP[1], UNIFORM[2], TEMP[0].zzzz, TEMP[2];
4: ADD TEMP[0].xyz, TEMP[1].xyzx, UNIFORM[3].xyzx;
5: TEX TEMP[1].w, INPUT[14].xyyy, texture[0], 2D;
6: MOV TEMP[0].w, TEMP[1].wwww;
7: MOV OUTPUT[2], TEMP[0];
8: END
to produce incorrect code such as this:
BEGIN
DCL S[0]
DCL T_TEX0
R[0] = MOV T_TEX0.xyyy
U[0] = TEXLD S[0],R[0]
R[0].xyz = MOV U[0]
R[1] = MUL CONST[0], R[0].xxxx
R[2] = MAD CONST[1], R[0].yyyy, R[1]
R[1] = MAD CONST[2], R[0].zzzz, R[2]
R[0].xyz = ADD R[1].xyzx, CONST[3].xyzx
R[0] = MOV T_TEX0.xyyy
U[0] = TEXLD S[0],R[0]
R[1].w = MOV U[0]
R[0].w = MOV R[1].wwww
oC = MOV R[0]
END
Note that T_TEX0 is copied to R[0], but the xyz components of R[0] are
still expected to hold a calculated value.
Fixes piglit tests draw-elements-vs-inputs, fp-kill, and
glsl-fs-color-matrix. It also fixes Meego bugzilla #13005.
NOTE: This is a candidate for the 7.9 and 7.10 branches.
|
|
Also return it as the correct type. Previously the whole array would
be returned and each element would be expanded to a vec4.
Fixes piglit test getuniform-01 and bugzilla #29823.
|
|
|
|
Passing ralloc_vasprintf_append a 0-byte allocation doesn't work. If
passed a non-NULL argument, ralloc calls strlen to find the end of the
string. Since there's no terminating '\0', it runs off the end.
Fixes a crash introduced in 14880a510a1a288df0778395097d5a52806abfb0.
|
|
Not 100% sure on this one, but this is how it should work,
the question is whether it will uncover other bugs elsewhere.
|
|
If we see a MACRO bit on r600g its 2D tiled,
if don't see a MACRO bit and we do see a MICRO bit then its 1D tiled.
Signed-off-by: Dave Airlie <airlied@redhat.com>
|
|
|
|
If the tile type for the buffer is 1 then its been bound to the
DB at some point, we need to decompress it, otherwise its only
been bound as texture/cb so don't do anything.
This fixes 5 piglit tests here on r600g.
|
|
|
|
this just adds the ioctl interface and sets the tile type
and array mode in the correct place.
This seems to bring eg 1D tiling to the same level, and issues
as on r600. No idea how to address 2D yet.
|
|
sampler view on a depth texture.
R600/R700 was using incorrect tiling information from the (compressed) depth
buffer. Evergreen worked anyway because tiling doesn't work.
|
|
For the previous commit.
|
|
Previously we'd happily compile GLSL 1.30 shaders on any driver. We'd
also happily compile GLSL 1.10 and 1.20 shaders in an ES2 context.
This has been a long standing FINISHME in the compiler.
NOTE: This is a candidate for the 7.9 and 7.10 branches
|
|
NOTE: This is a candidate for the 7.9 and 7.10 branches
|
|
|
|
See table 6.7 on page 347 of the OpenGL 3.0 specification.
|
|
Only decrement ref count if r600_upload_const_buffer
really changes the buffer.
|
|
|
|
|
|
To silence warning about missing prototype.
|
|
To avoid using the /usr/include/GL/gl.h file which may be lacking
some special #defines.
|
|
|
|
|
|
|
|
|
|
|
|
Rather than passing "True", pass a bitfield describing the particular
variant's features - either projection or offset.
This should make the code a bit more readable ("Proj" instead of "True")
and make it easier to support offsets in the future.
|
|
For offsets, we'll want the straight sampler dimensionality, without the
+1 for array types. Create a new function to do that; refactor.
|
|
This annotation is for an "in" function parameter for which it is only legal
to pass constant expressions. The only known example of this, currently,
is the textureOffset functions.
This should never be used for globals.
|
|
Having these as actual integer values makes it difficult to implement
the texture*Offset built-in functions, since the offset is actually a
function parameter (which doesn't have a constant value).
The original rationale was that some hardware needs these offset baked
into the instruction opcode. However, at least i965 should be able to
support non-constant offsets. Others should be able to rely on inlining
and constant propagation.
|
|
Since the introduction of ir_var_system_value, system variables would be
printed as "temporary" and temporaries would result in out-of-bounds
array access, showing up as garbage in printed IR.
|
|
Print warnings and continue build.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Signed-off-by: Brian Paul <brianp@vmware.com>
|
|
SVGA3D only supports SGN for vertex shaders, and this requires two additional
temporary registers for intermediate results.
For fragment shaders, lower to two CMPs and one ADD.
|
|
|
|
Makes it easier to figure out which opcode it's about.
|
|
Signed-off-by: Brian Paul <brianp@vmware.com>
|
|
Signed-off-by: Brian Paul <brianp@vmware.com>
|
