summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorJason Ekstrand <[email protected]>2019-02-13 16:22:37 -0600
committerJason Ekstrand <[email protected]>2019-02-21 00:08:42 +0000
commit558c3145045f1c6da8bddb31ed77a418ab27f2f9 (patch)
tree85b1abca800b6868fad6358f32f1fe3ac5668e56
parent4e69fba534e7377f3bc6c40c73e6bc5c23437d4e (diff)
nir/xfb: Work in terms of components rather than slots
We needed to better handle cases where a chunk of a variable starts at some non-zero location_frac and rolls over into the next slot but may not be more than 4 dwords. For example, if gl_CullDistance is an array of 3 things and has location_frac = 2, it will span across two vec4s but is not, itself, bigger than a vec4. If you ignore the clip/cull special case, it's not allowed to happen for anything else because the only things that can span more than one slot is dvec3 and dvec4 and they're both bigger than a vec4. The current code uses this attrib_slot thing where we count attribute slots and iterate over them. However, that doesn't work in the case above because gl_CullDistance will have an attrib_slot count of 1 even though it does span two slots. We could fix this by adjusting attrib_slot but we already have comp_mask and it's easier to just handle it that way. Reviewed-by: Alejandro PiƱeiro <[email protected]>
-rw-r--r--src/compiler/nir/nir_gather_xfb_info.c10
1 files changed, 5 insertions, 5 deletions
diff --git a/src/compiler/nir/nir_gather_xfb_info.c b/src/compiler/nir/nir_gather_xfb_info.c
index 446b7ac0495..081ef77b48a 100644
--- a/src/compiler/nir/nir_gather_xfb_info.c
+++ b/src/compiler/nir/nir_gather_xfb_info.c
@@ -76,18 +76,18 @@ add_var_xfb_outputs(nir_xfb_info *xfb,
assert(var->data.location_frac + comp_slots <= 8);
uint8_t comp_mask = ((1 << comp_slots) - 1) << var->data.location_frac;
- assert(attrib_slots <= 2);
- for (unsigned s = 0; s < attrib_slots; s++) {
+ while (comp_mask) {
nir_xfb_output_info *output = &xfb->outputs[xfb->output_count++];
output->buffer = buffer;
- output->offset = *offset + s * 16;
+ output->offset = *offset;
output->location = *location;
- output->component_mask = (comp_mask >> (s * 4)) & 0xf;
+ output->component_mask = comp_mask & 0xf;
+ *offset += util_bitcount(output->component_mask) * 4;
(*location)++;
+ comp_mask >>= 4;
}
- *offset += comp_slots * 4;
}
}