From 55e6454d5e9dae6f8f29992af83f99217446da38 Mon Sep 17 00:00:00 2001 From: Ian Romanick Date: Wed, 27 Feb 2019 15:53:55 -0800 Subject: [PATCH] intel/fs: Fix extract_u8 of an odd byte from a 64-bit integer In the old code, we would generate the exact same instruction for extract_u8(some_u64, 0) and extract_u8(some_u64, 1). The mask-a-word trick only works for even numbered bytes. This fixes the (new) piglit test tests/spec/arb_gpu_shader_int64/execution/fs-ushr-and-mask.shader_test. v2: Use a SHR instead of an AND. This saves an instruction compared to using two moves. Suggested by Jason. Fixes: 6ac2d169019 ("i965/fs: Fix extract_i8/u8 to a 64-bit destination") Reviewed-by: Jason Ekstrand --- src/intel/compiler/brw_fs_nir.cpp | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/src/intel/compiler/brw_fs_nir.cpp b/src/intel/compiler/brw_fs_nir.cpp index eb7ea7ece98..747529e72d8 100644 --- a/src/intel/compiler/brw_fs_nir.cpp +++ b/src/intel/compiler/brw_fs_nir.cpp @@ -1639,6 +1639,13 @@ fs_visitor::nir_emit_alu(const fs_builder &bld, nir_alu_instr *instr) fs_reg w_temp = bld.vgrf(BRW_REGISTER_TYPE_W); bld.MOV(w_temp, subscript(op[0], type, byte)); bld.MOV(result, w_temp); + } else if (byte & 1) { + /* Extract the high byte from the word containing the desired byte + * offset. + */ + bld.SHR(result, + subscript(op[0], BRW_REGISTER_TYPE_UW, byte / 2), + brw_imm_uw(8)); } else { /* Otherwise use an AND with 0xff and a word type */ bld.AND(result, -- 2.30.2