ac: fix nir_op_fdd{x,y} handling

radeonsi, i965 and anv all treat fdd{x,y} opcodes the same as
fdd{x,y}_coarse by default. The SPIR-V spec lets the implementation
decide how it should be handled and radv was previously going
for the higher quality option. Here we change the shared amd
code to match how nir_op_fdd{x,y} is expected to be handled
by the other NIR drivers.

Fixes piglit test:
./bin/arb_shader_texture_lod-texgrad -auto

Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>

diff --git a/src/amd/common/ac_nir_to_llvm.c b/src/amd/common/ac_nir_to_llvm.c
index fabecb1..b010128 100644 (file)
--- a/src/amd/common/ac_nir_to_llvm.c
+++ b/src/amd/common/ac_nir_to_llvm.c
@@ -1613,9 +1613,9 @@ static LLVMValueRef emit_ddxy(struct ac_nir_context *ctx,
        int idx;
        LLVMValueRef result;
 
-       if (op == nir_op_fddx_fine || op == nir_op_fddx)
+       if (op == nir_op_fddx_fine)
                mask = AC_TID_MASK_LEFT;
-       else if (op == nir_op_fddy_fine || op == nir_op_fddy)
+       else if (op == nir_op_fddy_fine)
                mask = AC_TID_MASK_TOP;
        else
                mask = AC_TID_MASK_TOP_LEFT;