From 96b51537908cd2aace85f54b437eeb72e6346b7e Mon Sep 17 00:00:00 2001 From: Iago Toral Quiroga Date: Tue, 6 Mar 2018 12:14:05 +0100 Subject: [PATCH] i965/compiler: handle conversion to smaller type in the lowering pass for that The lowering pass was specialized to act on 64-bit to 32-bit conversions only, but the implementation is valid for other cases. Reviewed-by: Jason Ekstrand --- src/intel/compiler/brw_fs_lower_conversions.cpp | 5 ++++- src/intel/compiler/brw_fs_nir.cpp | 14 +++----------- 2 files changed, 7 insertions(+), 12 deletions(-) diff --git a/src/intel/compiler/brw_fs_lower_conversions.cpp b/src/intel/compiler/brw_fs_lower_conversions.cpp index 663c9674c49..f95b39d3e86 100644 --- a/src/intel/compiler/brw_fs_lower_conversions.cpp +++ b/src/intel/compiler/brw_fs_lower_conversions.cpp @@ -54,7 +54,7 @@ fs_visitor::lower_conversions() bool saturate = inst->saturate; if (supports_type_conversion(inst)) { - if (get_exec_type_size(inst) == 8 && type_sz(inst->dst.type) < 8) { + if (type_sz(inst->dst.type) < get_exec_type_size(inst)) { /* From the Broadwell PRM, 3D Media GPGPU, "Double Precision Float to * Single Precision Float": * @@ -64,6 +64,9 @@ fs_visitor::lower_conversions() * So we need to allocate a temporary that's two registers, and then do * a strided MOV to get the lower DWord of every Qword that has the * result. + * + * This restriction applies, in general, whenever we convert to + * a type with a smaller bit-size. */ fs_reg temp = ibld.vgrf(get_exec_type(inst)); fs_reg strided_temp = subscript(temp, dst.type, 0); diff --git a/src/intel/compiler/brw_fs_nir.cpp b/src/intel/compiler/brw_fs_nir.cpp index db120efab80..2f341931ff5 100644 --- a/src/intel/compiler/brw_fs_nir.cpp +++ b/src/intel/compiler/brw_fs_nir.cpp @@ -755,19 +755,9 @@ fs_visitor::nir_emit_alu(const fs_builder &bld, nir_alu_instr *instr) */ case nir_op_f2f16_undef: - case nir_op_i2i16: - case nir_op_u2u16: { - /* TODO: Fixing aligment rules for conversions from 32-bits to - * 16-bit types should be moved to lower_conversions - */ - fs_reg tmp = bld.vgrf(op[0].type, 1); - tmp = subscript(tmp, result.type, 0); - inst = bld.MOV(tmp, op[0]); - inst->saturate = instr->dest.saturate; - inst = bld.MOV(result, tmp); + inst = bld.MOV(result, op[0]); inst->saturate = instr->dest.saturate; break; - } case nir_op_f2f64: case nir_op_f2i64: @@ -805,6 +795,8 @@ fs_visitor::nir_emit_alu(const fs_builder &bld, nir_alu_instr *instr) case nir_op_f2u32: case nir_op_i2i32: case nir_op_u2u32: + case nir_op_i2i16: + case nir_op_u2u16: inst = bld.MOV(result, op[0]); inst->saturate = instr->dest.saturate; break; -- 2.30.2