maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[RISCV][SelectionDAG] Support VECREDUCE_ADD mask operation 

Reviewed By: craig.topper

Differential Revision: https://reviews.llvm.org/D125206
This commit is contained in:
Lian Wang 2022-05-09 06:18:34 +00:00
parent 3b3ff24037
commit 17a8a1bb71
3 changed files with 225 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
View File

@ -5311,6 +5311,11 @@ SDValue SelectionDAG::getNode(unsigned Opcode, const SDLoc &DL, EVT VT,
if (Operand.getValueType().getScalarType() == MVT::i1)
return getNOT(DL, Operand, Operand.getValueType());
break;
case ISD::VECREDUCE_ADD:
// If it is VECREDUCE_ADD mask operation then turn it to VECREDUCE_XOR
if (Operand.getValueType().getScalarType() == MVT::i1)
return getNode(ISD::VECREDUCE_XOR, DL, VT, Operand);
break;
case ISD::VECREDUCE_SMIN:
case ISD::VECREDUCE_UMAX:
if (Operand.getValueType().getScalarType() == MVT::i1)

122
llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vreductions-mask.ll
View File

@ -116,6 +116,22 @@ define signext i1 @vreduce_smin_v1i1(<1 x i1> %v) {
ret i1 %red
}
declare i1 @llvm.vector.reduce.add.v1i1(<1 x i1>)
define signext i1 @vreduce_add_v1i1(<1 x i1> %v) {
; CHECK-LABEL: vreduce_add_v1i1:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e8, mf8, ta, mu
; CHECK-NEXT: vmv.v.i v8, 0
; CHECK-NEXT: vmerge.vim v8, v8, 1, v0
; CHECK-NEXT: vmv.x.s a0, v8
; CHECK-NEXT: andi a0, a0, 1
; CHECK-NEXT: neg a0, a0
; CHECK-NEXT: ret
%red = call i1 @llvm.vector.reduce.add.v1i1(<1 x i1> %v)
ret i1 %red
}
declare i1 @llvm.vector.reduce.or.v2i1(<2 x i1>)
define signext i1 @vreduce_or_v2i1(<2 x i1> %v) {
@ -217,6 +233,20 @@ define signext i1 @vreduce_smin_v2i1(<2 x i1> %v) {
ret i1 %red
}
declare i1 @llvm.vector.reduce.add.v2i1(<2 x i1>)
define signext i1 @vreduce_add_v2i1(<2 x i1> %v) {
; CHECK-LABEL: vreduce_add_v2i1:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 2, e8, mf8, ta, mu
; CHECK-NEXT: vcpop.m a0, v0
; CHECK-NEXT: andi a0, a0, 1
; CHECK-NEXT: neg a0, a0
; CHECK-NEXT: ret
%red = call i1 @llvm.vector.reduce.add.v2i1(<2 x i1> %v)
ret i1 %red
}
declare i1 @llvm.vector.reduce.or.v4i1(<4 x i1>)
define signext i1 @vreduce_or_v4i1(<4 x i1> %v) {
@ -318,6 +348,20 @@ define signext i1 @vreduce_smin_v4i1(<4 x i1> %v) {
ret i1 %red
}
declare i1 @llvm.vector.reduce.add.v4i1(<4 x i1>)
define signext i1 @vreduce_add_v4i1(<4 x i1> %v) {
; CHECK-LABEL: vreduce_add_v4i1:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 4, e8, mf4, ta, mu
; CHECK-NEXT: vcpop.m a0, v0
; CHECK-NEXT: andi a0, a0, 1
; CHECK-NEXT: neg a0, a0
; CHECK-NEXT: ret
%red = call i1 @llvm.vector.reduce.add.v4i1(<4 x i1> %v)
ret i1 %red
}
declare i1 @llvm.vector.reduce.or.v8i1(<8 x i1>)
define signext i1 @vreduce_or_v8i1(<8 x i1> %v) {
@ -419,6 +463,20 @@ define signext i1 @vreduce_smin_v8i1(<8 x i1> %v) {
ret i1 %red
}
declare i1 @llvm.vector.reduce.add.v8i1(<8 x i1>)
define signext i1 @vreduce_add_v8i1(<8 x i1> %v) {
; CHECK-LABEL: vreduce_add_v8i1:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 8, e8, mf2, ta, mu
; CHECK-NEXT: vcpop.m a0, v0
; CHECK-NEXT: andi a0, a0, 1
; CHECK-NEXT: neg a0, a0
; CHECK-NEXT: ret
%red = call i1 @llvm.vector.reduce.add.v8i1(<8 x i1> %v)
ret i1 %red
}
declare i1 @llvm.vector.reduce.or.v16i1(<16 x i1>)
define signext i1 @vreduce_or_v16i1(<16 x i1> %v) {
@ -520,6 +578,20 @@ define signext i1 @vreduce_smin_v16i1(<16 x i1> %v) {
ret i1 %red
}
declare i1 @llvm.vector.reduce.add.v16i1(<16 x i1>)
define signext i1 @vreduce_add_v16i1(<16 x i1> %v) {
; CHECK-LABEL: vreduce_add_v16i1:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetivli zero, 16, e8, m1, ta, mu
; CHECK-NEXT: vcpop.m a0, v0
; CHECK-NEXT: andi a0, a0, 1
; CHECK-NEXT: neg a0, a0
; CHECK-NEXT: ret
%red = call i1 @llvm.vector.reduce.add.v16i1(<16 x i1> %v)
ret i1 %red
}
declare i1 @llvm.vector.reduce.or.v32i1(<32 x i1>)
define signext i1 @vreduce_or_v32i1(<32 x i1> %v) {
@ -691,6 +763,30 @@ define signext i1 @vreduce_smin_v32i1(<32 x i1> %v) {
ret i1 %red
}
declare i1 @llvm.vector.reduce.add.v32i1(<32 x i1>)
define signext i1 @vreduce_add_v32i1(<32 x i1> %v) {
; LMULMAX1-LABEL: vreduce_add_v32i1:
; LMULMAX1: # %bb.0:
; LMULMAX1-NEXT: vsetivli zero, 16, e8, m1, ta, mu
; LMULMAX1-NEXT: vmxor.mm v8, v0, v8
; LMULMAX1-NEXT: vcpop.m a0, v8
; LMULMAX1-NEXT: andi a0, a0, 1
; LMULMAX1-NEXT: neg a0, a0
; LMULMAX1-NEXT: ret
;
; LMULMAX8-LABEL: vreduce_add_v32i1:
; LMULMAX8: # %bb.0:
; LMULMAX8-NEXT: li a0, 32
; LMULMAX8-NEXT: vsetvli zero, a0, e8, m2, ta, mu
; LMULMAX8-NEXT: vcpop.m a0, v0
; LMULMAX8-NEXT: andi a0, a0, 1
; LMULMAX8-NEXT: neg a0, a0
; LMULMAX8-NEXT: ret
%red = call i1 @llvm.vector.reduce.add.v32i1(<32 x i1> %v)
ret i1 %red
}
declare i1 @llvm.vector.reduce.or.v64i1(<64 x i1>)
define signext i1 @vreduce_or_v64i1(<64 x i1> %v) {
@ -875,3 +971,29 @@ define signext i1 @vreduce_smin_v64i1(<64 x i1> %v) {
%red = call i1 @llvm.vector.reduce.smin.v64i1(<64 x i1> %v)
ret i1 %red
}
declare i1 @llvm.vector.reduce.add.v64i1(<64 x i1>)
define signext i1 @vreduce_add_v64i1(<64 x i1> %v) {
; LMULMAX1-LABEL: vreduce_add_v64i1:
; LMULMAX1: # %bb.0:
; LMULMAX1-NEXT: vsetivli zero, 16, e8, m1, ta, mu
; LMULMAX1-NEXT: vmxor.mm v8, v8, v10
; LMULMAX1-NEXT: vmxor.mm v9, v0, v9
; LMULMAX1-NEXT: vmxor.mm v8, v9, v8
; LMULMAX1-NEXT: vcpop.m a0, v8
; LMULMAX1-NEXT: andi a0, a0, 1
; LMULMAX1-NEXT: neg a0, a0
; LMULMAX1-NEXT: ret
;
; LMULMAX8-LABEL: vreduce_add_v64i1:
; LMULMAX8: # %bb.0:
; LMULMAX8-NEXT: li a0, 64
; LMULMAX8-NEXT: vsetvli zero, a0, e8, m4, ta, mu
; LMULMAX8-NEXT: vcpop.m a0, v0
; LMULMAX8-NEXT: andi a0, a0, 1
; LMULMAX8-NEXT: neg a0, a0
; LMULMAX8-NEXT: ret
%red = call i1 @llvm.vector.reduce.add.v64i1(<64 x i1> %v)
ret i1 %red
}

98
llvm/test/CodeGen/RISCV/rvv/vreductions-mask.ll
View File

@ -103,6 +103,20 @@ define signext i1 @vreduce_smin_nxv1i1(<vscale x 1 x i1> %v) {
ret i1 %red
}
declare i1 @llvm.vector.reduce.add.nxv1i1(<vscale x 1 x i1>)
define signext i1 @vreduce_add_nxv1i1(<vscale x 1 x i1> %v) {
; CHECK-LABEL: vreduce_add_nxv1i1:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e8, mf8, ta, mu
; CHECK-NEXT: vcpop.m a0, v0
; CHECK-NEXT: andi a0, a0, 1
; CHECK-NEXT: neg a0, a0
; CHECK-NEXT: ret
%red = call i1 @llvm.vector.reduce.add.nxv1i1(<vscale x 1 x i1> %v)
ret i1 %red
}
declare i1 @llvm.vector.reduce.or.nxv2i1(<vscale x 2 x i1>)
define signext i1 @vreduce_or_nxv2i1(<vscale x 2 x i1> %v) {
@ -204,6 +218,20 @@ define signext i1 @vreduce_smin_nxv2i1(<vscale x 2 x i1> %v) {
ret i1 %red
}
declare i1 @llvm.vector.reduce.add.nxv2i1(<vscale x 2 x i1>)
define signext i1 @vreduce_add_nxv2i1(<vscale x 2 x i1> %v) {
; CHECK-LABEL: vreduce_add_nxv2i1:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e8, mf4, ta, mu
; CHECK-NEXT: vcpop.m a0, v0
; CHECK-NEXT: andi a0, a0, 1
; CHECK-NEXT: neg a0, a0
; CHECK-NEXT: ret
%red = call i1 @llvm.vector.reduce.add.nxv2i1(<vscale x 2 x i1> %v)
ret i1 %red
}
declare i1 @llvm.vector.reduce.or.nxv4i1(<vscale x 4 x i1>)
define signext i1 @vreduce_or_nxv4i1(<vscale x 4 x i1> %v) {
@ -305,6 +333,20 @@ define signext i1 @vreduce_smin_nxv4i1(<vscale x 4 x i1> %v) {
ret i1 %red
}
declare i1 @llvm.vector.reduce.add.nxv4i1(<vscale x 4 x i1>)
define signext i1 @vreduce_add_nxv4i1(<vscale x 4 x i1> %v) {
; CHECK-LABEL: vreduce_add_nxv4i1:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e8, mf2, ta, mu
; CHECK-NEXT: vcpop.m a0, v0
; CHECK-NEXT: andi a0, a0, 1
; CHECK-NEXT: neg a0, a0
; CHECK-NEXT: ret
%red = call i1 @llvm.vector.reduce.add.nxv4i1(<vscale x 4 x i1> %v)
ret i1 %red
}
declare i1 @llvm.vector.reduce.or.nxv8i1(<vscale x 8 x i1>)
define signext i1 @vreduce_or_nxv8i1(<vscale x 8 x i1> %v) {
@ -406,6 +448,20 @@ define signext i1 @vreduce_smin_nxv8i1(<vscale x 8 x i1> %v) {
ret i1 %red
}
declare i1 @llvm.vector.reduce.add.nxv8i1(<vscale x 8 x i1>)
define signext i1 @vreduce_add_nxv8i1(<vscale x 8 x i1> %v) {
; CHECK-LABEL: vreduce_add_nxv8i1:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e8, m1, ta, mu
; CHECK-NEXT: vcpop.m a0, v0
; CHECK-NEXT: andi a0, a0, 1
; CHECK-NEXT: neg a0, a0
; CHECK-NEXT: ret
%red = call i1 @llvm.vector.reduce.add.nxv8i1(<vscale x 8 x i1> %v)
ret i1 %red
}
declare i1 @llvm.vector.reduce.or.nxv16i1(<vscale x 16 x i1>)
define signext i1 @vreduce_or_nxv16i1(<vscale x 16 x i1> %v) {
@ -507,6 +563,20 @@ define signext i1 @vreduce_smin_nxv16i1(<vscale x 16 x i1> %v) {
ret i1 %red
}
declare i1 @llvm.vector.reduce.add.nxv16i1(<vscale x 16 x i1>)
define signext i1 @vreduce_add_nxv16i1(<vscale x 16 x i1> %v) {
; CHECK-LABEL: vreduce_add_nxv16i1:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e8, m2, ta, mu
; CHECK-NEXT: vcpop.m a0, v0
; CHECK-NEXT: andi a0, a0, 1
; CHECK-NEXT: neg a0, a0
; CHECK-NEXT: ret
%red = call i1 @llvm.vector.reduce.add.nxv16i1(<vscale x 16 x i1> %v)
ret i1 %red
}
declare i1 @llvm.vector.reduce.or.nxv32i1(<vscale x 32 x i1>)
define signext i1 @vreduce_or_nxv32i1(<vscale x 32 x i1> %v) {
@ -608,6 +678,20 @@ define signext i1 @vreduce_smin_nxv32i1(<vscale x 32 x i1> %v) {
ret i1 %red
}
declare i1 @llvm.vector.reduce.add.nxv32i1(<vscale x 32 x i1>)
define signext i1 @vreduce_add_nxv32i1(<vscale x 32 x i1> %v) {
; CHECK-LABEL: vreduce_add_nxv32i1:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e8, m4, ta, mu
; CHECK-NEXT: vcpop.m a0, v0
; CHECK-NEXT: andi a0, a0, 1
; CHECK-NEXT: neg a0, a0
; CHECK-NEXT: ret
%red = call i1 @llvm.vector.reduce.add.nxv32i1(<vscale x 32 x i1> %v)
ret i1 %red
}
declare i1 @llvm.vector.reduce.or.nxv64i1(<vscale x 64 x i1>)
define signext i1 @vreduce_or_nxv64i1(<vscale x 64 x i1> %v) {
@ -708,3 +792,17 @@ define signext i1 @vreduce_smin_nxv64i1(<vscale x 64 x i1> %v) {
%red = call i1 @llvm.vector.reduce.smin.nxv64i1(<vscale x 64 x i1> %v)
ret i1 %red
}
declare i1 @llvm.vector.reduce.add.nxv64i1(<vscale x 64 x i1>)
define signext i1 @vreduce_add_nxv64i1(<vscale x 64 x i1> %v) {
; CHECK-LABEL: vreduce_add_nxv64i1:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli a0, zero, e8, m8, ta, mu
; CHECK-NEXT: vcpop.m a0, v0
; CHECK-NEXT: andi a0, a0, 1
; CHECK-NEXT: neg a0, a0
; CHECK-NEXT: ret
%red = call i1 @llvm.vector.reduce.add.nxv64i1(<vscale x 64 x i1> %v)
ret i1 %red
}