intel/fs: Add need_dest parameter to fs_visitor::nir_emit_alu

This is the same as the need_dest parameter to
prepare_alu_destination_and_sources.  This allows us to not change the
register that is expected to hold an result if an instruction is
re-emitted.  This is particularly a problem if the re-emitted
instruction is a partial write.  A later patch will use this feature.

No shader-db changes on any Intel platform.

v2: Don't do the Boolean resolve when there is no destination.  If the
ALU instruction didn't write a register, there's nothing to resolve.
This replaces an earlier patch "intel/fs: Allocate dummy destination
register when need_dest is false".

Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>

diff --git a/src/intel/compiler/brw_fs.h b/src/intel/compiler/brw_fs.h
index 7db4866..230f9ab 100644 (file)
--- a/src/intel/compiler/brw_fs.h
+++ b/src/intel/compiler/brw_fs.h
@@ -206,7 +206,8 @@ public:
    void nir_emit_loop(nir_loop *loop);
    void nir_emit_block(nir_block *block);
    void nir_emit_instr(nir_instr *instr);
-   void nir_emit_alu(const brw::fs_builder &bld, nir_alu_instr *instr);
+   void nir_emit_alu(const brw::fs_builder &bld, nir_alu_instr *instr,
+                     bool need_dest);
    bool try_emit_b2fi_of_inot(const brw::fs_builder &bld, fs_reg result,
                               nir_alu_instr *instr);
    void nir_emit_load_const(const brw::fs_builder &bld,

diff --git a/src/intel/compiler/brw_fs_nir.cpp b/src/intel/compiler/brw_fs_nir.cpp
index eef2129..b499542 100644 (file)
--- a/src/intel/compiler/brw_fs_nir.cpp
+++ b/src/intel/compiler/brw_fs_nir.cpp
@@ -450,7 +450,7 @@ fs_visitor::nir_emit_instr(nir_instr *instr)
 
    switch (instr->type) {
    case nir_instr_type_alu:
-      nir_emit_alu(abld, nir_instr_as_alu(instr));
+      nir_emit_alu(abld, nir_instr_as_alu(instr), true);
       break;
 
    case nir_instr_type_deref:
@@ -981,13 +981,14 @@ can_fuse_fmul_fsign(nir_alu_instr *instr, unsigned fsign_src)
 }
 
 void
-fs_visitor::nir_emit_alu(const fs_builder &bld, nir_alu_instr *instr)
+fs_visitor::nir_emit_alu(const fs_builder &bld, nir_alu_instr *instr,
+                         bool need_dest)
 {
    struct brw_wm_prog_key *fs_key = (struct brw_wm_prog_key *) this->key;
    fs_inst *inst;
 
    fs_reg op[4];
-   fs_reg result = prepare_alu_destination_and_sources(bld, instr, op, true);
+   fs_reg result = prepare_alu_destination_and_sources(bld, instr, op, need_dest);
 
    switch (instr->op) {
    case nir_op_mov:
@@ -1836,6 +1837,7 @@ fs_visitor::nir_emit_alu(const fs_builder &bld, nir_alu_instr *instr)
     * to sign extend the low bit to 0/~0
     */
    if (devinfo->gen <= 5 &&
+       !result.is_null() &&
        (instr->instr.pass_flags & BRW_NIR_BOOLEAN_MASK) == BRW_NIR_BOOLEAN_NEEDS_RESOLVE) {
       fs_reg masked = vgrf(glsl_type::int_type);
       bld.AND(masked, result, brw_imm_d(1));