fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-05-05 18:18:06 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

i965/vec4/tes: fix setup_payload() for 64bit data types

Browse source 
Use a width of 2 with 64-bit attributes.

Also, if we have a dvec3/4 attribute that gets split across two registers
such that components XY are stored in the second half of a register and
components ZW are stored in the first half of the next, we need to fix
regioning for any instruction that reads components Z/W of the attribute.
Notice this also means that we can't support sources that read cross-dvec2
swizzles (like XZ for example).

v2: don't assert that we have a single channel swizzle in the case that we
    have to fix up Z/W access on the first half of the next register. We
    can handle any swizzle that does not cross dvec2 boundaries, which
    the double scalarization pass should have prevented anyway.

Reviewed-by: Matt Turner <mattst88@gmail.com>
This commit is contained in:
Iago Toral Quiroga 2016-07-01 09:22:34 +02:00 • committed by Samuel Iglesias Gonsálvez
parent 183cd8ab94
commit 49d4d0268b
1 changed files with 20 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
src/mesa/drivers/dri/i965/brw_vec4_tes.cpp
View file

@ -82,14 +82,33 @@ vec4_tes_visitor::setup_payload()
if (inst->src[i].file != ATTR)
continue;
bool is_64bit = type_sz(inst->src[i].type) == 8;
struct brw_reg grf =
brw_vec4_grf(reg + inst->src[i].nr / 2, 4 * (inst->src[i].nr % 2));
grf = stride(grf, 0, 4, 1);
grf = stride(grf, 0, is_64bit ? 2 : 4, 1);
grf.swizzle = inst->src[i].swizzle;
grf.type = inst->src[i].type;
grf.abs = inst->src[i].abs;
grf.negate = inst->src[i].negate;
/* For 64-bit attributes we can end up with components XY in the
* second half of a register and components ZW in the first half
* of the next. Fix it up here.
*/
if (is_64bit && grf.subnr > 0) {
/* We can't do swizzles that mix XY and ZW channels in this case.
* Such cases should have been handled by the scalarization pass.
*/
assert((brw_mask_for_swizzle(grf.swizzle) & 0x3) ^
(brw_mask_for_swizzle(grf.swizzle) & 0xc));
if (brw_mask_for_swizzle(grf.swizzle) & 0xc) {
grf.subnr = 0;
grf.nr++;
grf.swizzle -= BRW_SWIZZLE_ZZZZ;
}
}
inst->src[i] = grf;
}
}