replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Add the PPC popcntw instruction 

The popcntw instruction is available whenever the popcntd instruction is
available, and performs a separate popcnt on the lower and upper 32-bits.
Ignoring the high-order count, this can be used for the 32-bit input case
(saving on the explicit zero extension otherwise required to use popcntd).

llvm-svn: 178470
This commit is contained in:
Hal Finkel 2013-04-01 15:58:15 +00:00
parent be79a7ac7a
commit 290376dd78
3 changed files with 13 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/Target/PowerPC/PPCISelLowering.cpp
View File

@ -190,7 +190,7 @@ PPCTargetLowering::PPCTargetLowering(PPCTargetMachine &TM)
setOperationAction(ISD::CTLZ_ZERO_UNDEF, MVT::i64, Expand);
if (Subtarget->hasPOPCNTD()) {
setOperationAction(ISD::CTPOP, MVT::i32 , Promote);
setOperationAction(ISD::CTPOP, MVT::i32 , Legal);
setOperationAction(ISD::CTPOP, MVT::i64 , Legal);
} else {
setOperationAction(ISD::CTPOP, MVT::i32 , Expand);

7
llvm/lib/Target/PowerPC/PPCInstr64Bit.td
View File

@ -468,6 +468,13 @@ def POPCNTD : XForm_11<31, 506, (outs G8RC:$rA), (ins G8RC:$rS),
"popcntd $rA, $rS", IntGeneral,
[(set i64:$rA, (ctpop i64:$rS))]>;
// popcntw also does a population count on the high 32 bits (storing the
// results in the high 32-bits of the output). We'll ignore that here (which is
// safe because we never separately use the high part of the 64-bit registers).
def POPCNTW : XForm_11<31, 378, (outs GPRC:$rA), (ins GPRC:$rS),
"popcntw $rA, $rS", IntGeneral,
[(set i32:$rA, (ctpop i32:$rS))]>;
def DIVD : XOForm_1<31, 489, 0, (outs G8RC:$rT), (ins G8RC:$rA, G8RC:$rB),
"divd $rT, $rA, $rB", IntDivD,
[(set i64:$rT, (sdiv i64:$rA, i64:$rB))]>, isPPC64,

11
llvm/test/CodeGen/PowerPC/popcnt.ll
View File

@ -4,8 +4,8 @@ define i8 @cnt8(i8 %x) nounwind readnone {
%cnt = tail call i8 @llvm.ctpop.i8(i8 %x)
ret i8 %cnt
; CHECK: @cnt8
; CHECK: rldicl
; CHECK: popcntd
; CHECK: rlwinm
; CHECK: popcntw
; CHECK: blr
}
@ -13,8 +13,8 @@ define i16 @cnt16(i16 %x) nounwind readnone {
%cnt = tail call i16 @llvm.ctpop.i16(i16 %x)
ret i16 %cnt
; CHECK: @cnt16
; CHECK: rldicl
; CHECK: popcntd
; CHECK: rlwinm
; CHECK: popcntw
; CHECK: blr
}
@ -22,8 +22,7 @@ define i32 @cnt32(i32 %x) nounwind readnone {
%cnt = tail call i32 @llvm.ctpop.i32(i32 %x)
ret i32 %cnt
; CHECK: @cnt32
; CHECK: rldicl
; CHECK: popcntd
; CHECK: popcntw
; CHECK: blr
}