Hi, Justin> We're been writing multiclasses for each unique type of instruction. The > current PTX_LOGIC version is for 3-operand instructions. A new multiclass > needs to be created for 2-operand logic instructions.I am trying to add a multiclass for 2-operand logic instructions. For example, multiclass PTX_LOGIC_2OP<string opcstr, SDNode opnode> { def ripreds : InstPTX<(outs Preds:$d), (ins Preds:$a), !strconcat(opcstr, ".pred\t$d, $a"), [(set Preds:$d, (opnode Preds:$a))]>; ... } But the error is still the same. Where else should I look into? Thanks. Regards, chenwj -- Wei-Ren Chen (陳韋任) Computer Systems Lab, Institute of Information Science, Academia Sinica, Taiwan (R.O.C.) Tel:886-2-2788-3799 #1667
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"> <html> <head> <meta content="text/html;charset=UTF-8" http-equiv="Content-Type"> </head> <body bgcolor="#ffffff" text="#000000"> 陳韋任 wrote: <blockquote cite="mid:20110509013918.GA13760@cs.nctu.edu.tw" type="cite"> <pre wrap="">Hi, Justin </pre> <blockquote type="cite"> <pre wrap="">We're been writing multiclasses for each unique type of instruction. The current PTX_LOGIC version is for 3-operand instructions. A new multiclass needs to be created for 2-operand logic instructions. </pre> </blockquote> <pre wrap=""><!----> I am trying to add a multiclass for 2-operand logic instructions. For example, multiclass PTX_LOGIC_2OP<string opcstr, SDNode opnode> { def ripreds : InstPTX<(outs Preds:$d), (ins Preds:$a), !strconcat(opcstr, ".pred\t$d, $a"), [(set Preds:$d, (opnode Preds:$a))]>; ... } </pre> </blockquote> The error here is due to the fact that the 'not' dag is defined as a pattern fragment rather than being an explicit dag node in itself.<br> <br> As a result, you'd need to define your multiclass as:<br> <br> multiclass PTX_LOGIC_20P<string opcstr, PatFrag opnode> { ... }<br> <br> This will correctly match the opnode, though it'll depend on the other 2-operand logic instructions whether this is how it should be done. If you look at the definitions in include/Target/TargetSelectionDAG.td, you'll see which instructions are defined as a PatFrag and which are plain SDNodes.<br> <br> Dan<br> <br> <blockquote cite="mid:20110509013918.GA13760@cs.nctu.edu.tw" type="cite"> <pre wrap=""> But the error is still the same. Where else should I look into? Thanks. Regards, chenwj </pre> </blockquote> </body> </html>
> The error here is due to the fact that the 'not' dag is defined as a > pattern fragment rather than being an explicit dag node in itself. > > As a result, you'd need to define your multiclass as: > > multiclass PTX_LOGIC_20P<string opcstr, PatFrag opnode> { ... } > > This will correctly match the opnode, though it'll depend on the other > 2-operand logic instructions whether this is how it should be done. If > you look at the definitions in include/Target/TargetSelectionDAG.td, > you'll see which instructions are defined as a PatFrag and which are > plain SDNodes. > >DanThanks, Dan. -- Wer-Ren Chen (陳韋任) Computer Systems Lab, Institute of Information Science, Academia Sinica, Taiwan (R.O.C.) Tel:886-2-2788-3799 #1667
Hi, Dan I add "not" instruction support in PTXInstrInfo.td as you suggested before. multiclass PTX_LOGIC_2OP<string opcstr,PatFrag opnode> { ... } Now I am trying to write test case for logic and shift operations. But I have a trouble in mapping LLVM IR to PTX IR for "not" instruction. The test case I wrote is, define ptx_device i16 @t4_u16(i16 %x) { ; CHECK: not.b16 rh0, rh1, rh2; ; CHECK-NEXT: ret; %z = xor i16 %x, 1 ret i16 %z } Since LLVM IR doesn't support logical not directly, I use "xor i16 %x, 1" to represent logical not in LLVM IR. It turns out the IR is mapped to PTX "xor" not PTX "not". Any idea on how to get the mapping correct? Thanks. Regards, chenwj -- Wei-Ren Chen (陳韋任) Computer Systems Lab, Institute of Information Science, Academia Sinica, Taiwan (R.O.C.) Tel:886-2-2788-3799 #1667
Reasonably Related Threads
- [LLVMdev] [LLVMDev] Add not instruction to PTX backend
- [LLVMdev] [LLVMDev] Add not instruction to PTX backend
- [LLVMdev] [LLVMDev] Add not instruction to PTX backend
- [LLVMdev] [LLVMDev] Add not instruction to PTX backend
- [LLVMdev] proposal: add macro expansion of for-loop to TableGen