intel/compiler: Lower find_lsb in NIR

No shader-db or fossil-db changes on any Intel platform.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19042>

diff --git a/src/intel/compiler/brw_compiler.c b/src/intel/compiler/brw_compiler.c
index 2daadcb..7ecf630 100644 (file)
--- a/src/intel/compiler/brw_compiler.c
+++ b/src/intel/compiler/brw_compiler.c
@@ -188,6 +188,7 @@ brw_compiler_create(void *mem_ctx, const struct intel_device_info *devinfo)
 
       nir_options->lower_rotate = devinfo->ver < 11;
       nir_options->lower_bitfield_reverse = devinfo->ver < 7;
+      nir_options->lower_find_lsb = devinfo->ver < 7;
       nir_options->has_iadd3 = devinfo->verx10 >= 125;
 
       nir_options->has_sdot_4x8 = devinfo->ver >= 12;

diff --git a/src/intel/compiler/brw_fs_nir.cpp b/src/intel/compiler/brw_fs_nir.cpp
index d9bfc06..36bbef7 100644 (file)
--- a/src/intel/compiler/brw_fs_nir.cpp
+++ b/src/intel/compiler/brw_fs_nir.cpp
@@ -1737,27 +1737,8 @@ fs_visitor::nir_emit_alu(const fs_builder &bld, nir_alu_instr *instr,
 
    case nir_op_find_lsb:
       assert(nir_dest_bit_size(instr->dest.dest) < 64);
-
-      if (devinfo->ver < 7) {
-         fs_reg temp = vgrf(glsl_type::int_type);
-
-         /* (x & -x) generates a value that consists of only the LSB of x.
-          * For all powers of 2, findMSB(y) == findLSB(y).
-          */
-         fs_reg src = retype(op[0], BRW_REGISTER_TYPE_D);
-         fs_reg negated_src = src;
-
-         /* One must be negated, and the other must be non-negated.  It
-          * doesn't matter which is which.
-          */
-         negated_src.negate = true;
-         src.negate = false;
-
-         bld.AND(temp, src, negated_src);
-         emit_find_msb_using_lzd(bld, result, temp, false);
-      } else {
-         bld.FBL(result, op[0]);
-      }
+      assert(devinfo->ver >= 7);
+      bld.FBL(result, op[0]);
       break;
 
    case nir_op_ubitfield_extract:

diff --git a/src/intel/compiler/brw_vec4_nir.cpp b/src/intel/compiler/brw_vec4_nir.cpp
index 6adb5e6..5f40288 100644 (file)
--- a/src/intel/compiler/brw_vec4_nir.cpp
+++ b/src/intel/compiler/brw_vec4_nir.cpp
@@ -1688,32 +1688,11 @@ vec4_visitor::nir_emit_alu(nir_alu_instr *instr)
       break;
    }
 
-   case nir_op_find_lsb: {
+   case nir_op_find_lsb:
       assert(nir_dest_bit_size(instr->dest.dest) < 64);
-      vec4_builder bld = vec4_builder(this).at_end();
-
-      if (devinfo->ver < 7) {
-         dst_reg temp = bld.vgrf(BRW_REGISTER_TYPE_D);
-
-         /* (x & -x) generates a value that consists of only the LSB of x.
-          * For all powers of 2, findMSB(y) == findLSB(y).
-          */
-         src_reg src = src_reg(retype(op[0], BRW_REGISTER_TYPE_D));
-         src_reg negated_src = src;
-
-         /* One must be negated, and the other must be non-negated.  It
-          * doesn't matter which is which.
-          */
-         negated_src.negate = true;
-         src.negate = false;
-
-         bld.AND(temp, src, negated_src);
-         emit_find_msb_using_lzd(bld, dst, src_reg(temp), false);
-      } else {
-         bld.FBL(dst, op[0]);
-      }
+      assert(devinfo->ver >= 7);
+      emit(FBL(dst, op[0]));
       break;
-   }
 
    case nir_op_ubitfield_extract:
    case nir_op_ibitfield_extract: