From b9aa66aa516c100d5476ee966f428aaf743d786c Mon Sep 17 00:00:00 2001 From: Iago Toral Quiroga Date: Mon, 25 Jan 2016 13:37:50 +0100 Subject: [PATCH] i965/fs: add shuffle_64bit_data_for_32bit_write helper This does the inverse operation of shuffle_32bit_load_result_to_64bit_data and we will use it when we need to write 64-bit data in the layout expected by untyped write messages. v2 (curro): - Use subscript() instead of stride() - Assert on the input types rather than silently retyping. - Use offset() instead of horiz_offset(), drop the multiplier definition. - Drop the temporary vgrf and force_writemask_all. - Make component_i const. - Move to brw_fs_nir.cpp v3 (curro): - Pass dst and src by reference. - Simplify allocation of tmp register. - Move to brw_fs_nir.cpp. - Get rid of the temporary. v3 (Iago): - Check that the src and dst regions do not overlap, since that would typically be a bug in the caller. Reviewed-by: Kenneth Graunke Reviewed-by: Francisco Jerez --- src/mesa/drivers/dri/i965/brw_fs.h | 5 ++++ src/mesa/drivers/dri/i965/brw_fs_nir.cpp | 32 ++++++++++++++++++++++++ 2 files changed, 37 insertions(+) diff --git a/src/mesa/drivers/dri/i965/brw_fs.h b/src/mesa/drivers/dri/i965/brw_fs.h index 286e7186d1f..f9e6792e8d6 100644 --- a/src/mesa/drivers/dri/i965/brw_fs.h +++ b/src/mesa/drivers/dri/i965/brw_fs.h @@ -540,3 +540,8 @@ void shuffle_32bit_load_result_to_64bit_data(const brw::fs_builder &bld, const fs_reg &dst, const fs_reg &src, uint32_t components); + +void shuffle_64bit_data_for_32bit_write(const brw::fs_builder &bld, + const fs_reg &dst, + const fs_reg &src, + uint32_t components); diff --git a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp index 0d9fcdad888..143d5f32e40 100644 --- a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp +++ b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp @@ -4128,3 +4128,35 @@ shuffle_32bit_load_result_to_64bit_data(const fs_builder &bld, bld.MOV(offset(dst, bld, i), tmp); } } + +/** + * This helper does the inverse operation of + * SHUFFLE_32BIT_LOAD_RESULT_TO_64BIT_DATA. + * + * We need to do this when we are going to use untyped write messsages that + * operate with 32-bit components in order to arrange our 64-bit data to be + * in the expected layout. + * + * Notice that callers of this function, unlike in the case of the inverse + * operation, would typically need to call this with dst and src being + * different registers, since they would otherwise corrupt the original + * 64-bit data they are about to write. Because of this the function checks + * that the src and dst regions involved in the operation do not overlap. + */ +void +shuffle_64bit_data_for_32bit_write(const fs_builder &bld, + const fs_reg &dst, + const fs_reg &src, + uint32_t components) +{ + assert(type_sz(src.type) == 8); + assert(type_sz(dst.type) == 4); + + assert(!src.in_range(dst, 2 * components * bld.dispatch_width() / 8)); + + for (unsigned i = 0; i < components; i++) { + const fs_reg component_i = offset(src, bld, i); + bld.MOV(offset(dst, bld, 2 * i), subscript(component_i, dst.type, 0)); + bld.MOV(offset(dst, bld, 2 * i + 1), subscript(component_i, dst.type, 1)); + } +} -- 2.30.2