agx: Allow some 8-bit sources

8-bit sources are useful for int8->float32 conversions, which we can do in a
single hardware instruction.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19996>

src/asahi/compiler/agx_compile.c

@@ -852,7 +852,7 @@ agx_alu_src_index(agx_builder *b, nir_alu_src src)
    unsigned comps = nir_src_num_components(src.src);
    unsigned channel = src.swizzle[0];
 
-   assert(bitsize == 1 || bitsize == 16 || bitsize == 32 || bitsize == 64);
+   assert(bitsize == 1 || bitsize == 8 || bitsize == 16 || bitsize == 32 || bitsize == 64);
    assert(!(src.negate || src.abs));
    assert(channel < comps);
 

src/asahi/compiler/agx_compiler.h

@@ -442,6 +442,7 @@ agx_size_for_bits(unsigned bits)
 {
    switch (bits) {
    case 1:
+   case 8:
    case 16: return AGX_SIZE_16;
    case 32: return AGX_SIZE_32;
    case 64: return AGX_SIZE_64;