From 5d5ee507fb4a385f98ba19bd901ce4e3aca7def4 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Alejandro=20Pi=C3=B1eiro?= Date: Sat, 1 Jul 2017 08:11:05 +0200 Subject: [PATCH] i965/fs: Handle 32-bit to 16-bit conversions MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Conversions to 16-bit need having aligment between the 16-bit and 32-bit types. So the conversion operations unpack 16-bit types to with an stride=2 and then applies a MOV with the conversion. v2 (Jason Ekstrand): - Avoid the general use of stride=2 for 16-bit register types. v3 (Topi Pohjolainen) - Code style fix (Jason Ekstrand) - Now nir_op_f2f16 was renamed to nir_op_f2f16_undef because conversion to f16 with undefined rounding is explicit Signed-off-by: Eduardo Lima Signed-off-by: Alejandro Piñeiro Signed-off-by: Jose Maria Casanova Crespo Reviewed-by: Jason Ekstrand --- src/intel/compiler/brw_fs_nir.cpp | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/src/intel/compiler/brw_fs_nir.cpp b/src/intel/compiler/brw_fs_nir.cpp index bed1cd3b492..ddc0c6d105e 100644 --- a/src/intel/compiler/brw_fs_nir.cpp +++ b/src/intel/compiler/brw_fs_nir.cpp @@ -724,6 +724,31 @@ fs_visitor::nir_emit_alu(const fs_builder &bld, nir_alu_instr *instr) inst->saturate = instr->dest.saturate; break; + /* In theory, it would be better to use BRW_OPCODE_F32TO16. Depending + * on the HW gen, it is a special hw opcode or just a MOV, and + * brw_F32TO16 (at brw_eu_emit) would do the work to chose. + * + * But if we want to use that opcode, we need to provide support on + * different optimizations and lowerings. As right now HF support is + * only for gen8+, it will be better to use directly the MOV, and use + * BRW_OPCODE_F32TO16 when/if we work for HF support on gen7. + */ + + 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->saturate = instr->dest.saturate; + break; + } + case nir_op_f2f64: case nir_op_f2i64: case nir_op_f2u64: -- 2.30.2