On Mon, 2011-01-31 at 16:02 +0200, Ira Rosen wrote: > Hi, > > I am trying to implement interleave_high/low and extract_even/odd > using vzip and vuzp instructions. I am attaching a patch that attempts > to do that. It uses already existing neon_vzip<mode>_internal. The > problem with it is that it doesn't express the fact that the two > outputs of vzip depend on both inputs, which causes wrong code > generation in CSE: > for > (a,b)<- vzip (c,d) > and > (e,f) <- vzip (g,d) > CSE decides that b==f, since on RTL level b and f depend only on d. > > Here is neon_vzip<mode>_internal: > > (define_insn "neon_vzip<mode>_internal" > [(set (match_operand:VDQW 0 "s_register_operand" "=w") > (unspec:VDQW [(match_operand:VDQW 1 "s_register_operand" "0")] > UNSPEC_VZIP1)) > (set (match_operand:VDQW 2 "s_register_operand" "=w") > (unspec:VDQW [(match_operand:VDQW 3 "s_register_operand" "2")] > UNSPEC_VZIP2))]
Just to let you know, here, when I tried to make the two sets parallel and "+w" for operands 0 and 2 (instead of =w), it made reload ICE. I did this to represent the 'meaning' of the instruction in md-speak, but no success :-( Tejas. > "TARGET_NEON" > "vzip.<V_sz_elem>\t%<V_reg>0, %<V_reg>2" > [(set (attr "neon_type") > (if_then_else (ne (symbol_ref "<Is_d_reg>") (const_int 0)) > (const_string "neon_bp_simple") > (const_string "neon_bp_3cycle")))] > ) > > Is there a way to properly mark the dependence? > > Thanks, > Ira > _______________________________________________ linaro-toolchain mailing list > linaro-toolchain@lists.linaro.org > http://lists.linaro.org/mailman/listinfo/linaro-toolchain -- IMPORTANT NOTICE: The contents of this email and any attachments are confidential and may also be privileged. If you are not the intended recipient, please notify the sender immediately and do not disclose the contents to any other person, use it for any purpose, or store or copy the information in any medium. Thank you. _______________________________________________ linaro-toolchain mailing list linaro-toolchain@lists.linaro.org http://lists.linaro.org/mailman/listinfo/linaro-toolchain
