gallivm: fix sampling with texture offsets in SoA path

When using nearest filtering and clamp / clamp to edge wrapping results could
be wrong for negative offsets. Fix this by adding the offset before doing
the conversion to int coords (could also use floor instead of trunc int
conversion but probably more complex on "typical" cpu).

This fixes the piglit texwrap offset failures with this filter/wrap combo
(which only leaves the linear/mirror repeat combination broken).

Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>

diff --git a/src/gallium/auxiliary/gallivm/lp_bld_sample_soa.c b/src/gallium/auxiliary/gallivm/lp_bld_sample_soa.c
index b5c06b695711f16c4b2d01f70416a0995d6ed247..125505eeb4b9fce11143a37ddbcb0811310635fc 100644 (file)
--- a/src/gallium/auxiliary/gallivm/lp_bld_sample_soa.c
+++ b/src/gallium/auxiliary/gallivm/lp_bld_sample_soa.c
@@ -567,12 +567,13 @@ lp_build_sample_wrap_nearest(struct lp_build_sample_context *bld,
          coord = lp_build_mul(coord_bld, coord, length_f);
       }
 
+      if (offset) {
+         offset = lp_build_int_to_float(coord_bld, offset);
+         coord = lp_build_add(coord_bld, coord, offset);
+      }
       /* floor */
       /* use itrunc instead since we clamp to 0 anyway */
       icoord = lp_build_itrunc(coord_bld, coord);
-      if (offset) {
-         icoord = lp_build_add(int_coord_bld, icoord, offset);
-      }
 
       /* clamp to [0, length - 1]. */
       icoord = lp_build_clamp(int_coord_bld, icoord, int_coord_bld->zero,
@@ -2586,6 +2587,10 @@ lp_build_sample_soa_code(struct gallivm_state *gallivm,
       derived_sampler_state.wrap_s = PIPE_TEX_WRAP_CLAMP_TO_EDGE;
       derived_sampler_state.wrap_t = PIPE_TEX_WRAP_CLAMP_TO_EDGE;
    }
+   /*
+    * We could force CLAMP to CLAMP_TO_EDGE here if min/mag filter is nearest,
+    * so AoS path could be used. Not sure it's worth the trouble...
+    */
 
    min_img_filter = derived_sampler_state.min_img_filter;
    mag_img_filter = derived_sampler_state.mag_img_filter;