gallivm: optimize lp_build_minify for sse

SSE can't handle true vector shifts (with variable shift count),
so llvm is turning them into a mess of extracts, scalar shifts and inserts.
It is however possible to emulate them in lp_build_minify with float muls,
which should be way faster (saves over 20 instructions per 8-wide
lp_build_minify). This wouldn't work for "generic" 32bit shifts though
since we've got only 24bits of mantissa (actually for left shifts it would
work by using sse41 int mul instead of float mul but not for right shifts).
Note that this has very limited scope for now, since this is only used with
per-pixel lod (otherwise we're avoiding the non-constant shift count by doing
per-quad shifts manually), and only 1d textures even then (though the latter
should change).

Reviewed-by: Brian Paul <[email protected]>
Reviewed-by: Jose Fonseca <[email protected]>

1 files changed, 1 insertions, 1 deletions

diff --git a/src/gallium/auxiliary/gallivm/lp_bld_sample_soa.c b/src/gallium/auxiliary/gallivm/lp_bld_sample_soa.c
index 2d833318aee..e8c04d1e6c5 100644
--- a/src/gallium/auxiliary/gallivm/lp_bld_sample_soa.c
+++ b/src/gallium/auxiliary/gallivm/lp_bld_sample_soa.c
@@ -2940,7 +2940,7 @@ lp_build_size_query_soa(struct gallivm_state *gallivm,
                                     lp_build_const_int32(gallivm, 2), "");
    }
 
-   size = lp_build_minify(&bld_int_vec4, size, lod);
+   size = lp_build_minify(&bld_int_vec4, size, lod, TRUE);
 
    if (has_array)
       size = LLVMBuildInsertElement(gallivm->builder, size,