Please review: X86 sext pattern optimization

[Nadav Rotem]

Hi Elena, 

Thank you for working on this.  Why is this a DAGCombine optimization and not a Lowering one ?   Also, you need to update the cost model of the SEXT operations. Please add tests to the cost model to make sure that we estimate the costs of these casts correctly. 

Thanks,
Nadav


On Feb 17, 2013, at 1:20 AM, "Demikhovsky, Elena" <elena.demikhovsky at intel.com> wrote:

> 
> I optimized the following patterns:
> sext <4 x i1> to <4 x i64>
> sext <4 x i8> to <4 x i64>
> sext <4 x i16> to <4 x i64>
> 
> I'm running Combine on SIGN_EXTEND_IN_REG and revert SEXT patterns:
> (sext_in_reg (v4i64 anyext (v4i32 x )), ExtraVT) -> (v4i64 sext (v4i32 sext_in_reg (v4i32 x , ExtraVT)))
> 
> The sext_in_reg (v4i32 x) may be lowered to shl+sar operations.
> 
> The "sar" does not exist on 64-bit operation, so lowering sext_in_reg (v4i64 x) has no vector solution.
> 
> 
> - Elena
> 
> 
> ---------------------------------------------------------------------
> Intel Israel (74) Limited
> 
> This e-mail and any attachments may contain confidential material for
> the sole use of the intended recipient(s). Any review or distribution
> by others is strictly prohibited. If you are not the intended
> recipient, please contact the sender and delete all copies.
> <sext_to_v4i64.diff>_______________________________________________
> llvm-commits mailing list
> llvm-commits at cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits