[PATCH] D26767: [AMDGPU] Promote f16/i16 conversions to f32/i32 + custom lower f16 = fp_round f64
Konstantin Zhuravlyov via llvm-commits
llvm-commits at lists.llvm.org
Wed Nov 16 15:26:35 PST 2016
kzhuravl added a comment.
In https://reviews.llvm.org/D26767#597992, @arsenm wrote:
> If fp_tound has integer type after legalization, the legalization for it is broken
Agreed, I have bitcasted it to f16 and removed bitcast from combining. However I found that in some existing cases we legalize fp_to_fp16 to integer types (which got me confused), namely:
https://github.com/llvm-mirror/llvm/blob/master/lib/Target/AMDGPU/AMDGPUISelLowering.cpp#L2100
Also, why are our f16->f32 and f32->f16 are using i32?
https://github.com/llvm-mirror/llvm/blob/master/lib/Target/AMDGPU/VOP1Instructions.td#L132
https://reviews.llvm.org/D26767
More information about the llvm-commits
mailing list