diff --git a/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp b/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp index 4f6aa41d1e03b..e835de47f7dae 100644 --- a/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp +++ b/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp @@ -688,6 +688,26 @@ bool RISCVDAGToDAGISel::tryUnsignedBitfieldExtract(SDNode *Node, SDLoc DL, return true; } +bool RISCVDAGToDAGISel::tryUnsignedBitfieldInsertInZero(SDNode *Node, SDLoc DL, + MVT VT, SDValue X, + unsigned Msb, + unsigned Lsb) { + // Only supported with XAndesPerf at the moment. + if (!Subtarget->hasVendorXAndesPerf()) + return false; + + unsigned Opc = RISCV::NDS_BFOZ; + + // If the Lsb is equal to the Msb, then the Lsb should be 0. + if (Lsb == Msb) + Lsb = 0; + SDNode *Ubi = CurDAG->getMachineNode(Opc, DL, VT, X, + CurDAG->getTargetConstant(Lsb, DL, VT), + CurDAG->getTargetConstant(Msb, DL, VT)); + ReplaceNode(Node, Ubi); + return true; +} + bool RISCVDAGToDAGISel::tryIndexedLoad(SDNode *Node) { // Target does not support indexed loads. if (!Subtarget->hasVendorXTHeadMemIdx()) @@ -1324,6 +1344,19 @@ void RISCVDAGToDAGISel::Select(SDNode *Node) { return; } + // Try to use an unsigned bitfield insert (e.g., nds.bfoz) if + // available. + // Transform (and (shl x, c2), c1) + // -> ( x, msb, lsb) + // e.g. + // (and (shl x, 12), 0x00fff000) + // If XLen = 32 and C2 = 12, then + // Msb = 32 - 8 - 1 = 23 and Lsb = 12 + const unsigned Msb = XLen - Leading - 1; + const unsigned Lsb = C2; + if (tryUnsignedBitfieldInsertInZero(Node, DL, VT, X, Msb, Lsb)) + return; + // (srli (slli c2+c3), c3) if (OneUseOrZExtW && !IsCANDI) { SDNode *SLLI = CurDAG->getMachineNode( diff --git a/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.h b/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.h index 11d62e5edad3f..f199c2031b9a9 100644 --- a/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.h +++ b/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.h @@ -79,6 +79,8 @@ class RISCVDAGToDAGISel : public SelectionDAGISel { bool trySignedBitfieldExtract(SDNode *Node); bool tryUnsignedBitfieldExtract(SDNode *Node, SDLoc DL, MVT VT, SDValue X, unsigned Msb, unsigned Lsb); + bool tryUnsignedBitfieldInsertInZero(SDNode *Node, SDLoc DL, MVT VT, + SDValue X, unsigned Msb, unsigned Lsb); bool tryIndexedLoad(SDNode *Node); bool selectShiftMask(SDValue N, unsigned ShiftWidth, SDValue &ShAmt); diff --git a/llvm/test/CodeGen/RISCV/rv32xandesperf.ll b/llvm/test/CodeGen/RISCV/rv32xandesperf.ll index 71473ab5dfb58..3996420d477b2 100644 --- a/llvm/test/CodeGen/RISCV/rv32xandesperf.ll +++ b/llvm/test/CodeGen/RISCV/rv32xandesperf.ll @@ -2,6 +2,10 @@ ; RUN: llc -O0 -mtriple=riscv32 -mattr=+xandesperf -verify-machineinstrs < %s \ ; RUN: | FileCheck %s +; NDS.BFOZ + +; MSB >= LSB + define i32 @bfoz_from_and_i32(i32 %x) { ; CHECK-LABEL: bfoz_from_and_i32: ; CHECK: # %bb.0: @@ -70,6 +74,54 @@ define i64 @bfoz_from_lshr_and_i64(i64 %x) { ret i64 %shifted } +; MSB = 0 + +define i32 @bfoz_from_and_shl_with_msb_zero_i32(i32 %x) { +; CHECK-LABEL: bfoz_from_and_shl_with_msb_zero_i32: +; CHECK: # %bb.0: +; CHECK-NEXT: nds.bfoz a0, a0, 0, 15 +; CHECK-NEXT: ret + %shifted = shl i32 %x, 15 + %masked = and i32 %shifted, 32768 + ret i32 %masked +} + +define i32 @bfoz_from_lshr_shl_with_msb_zero_i32(i32 %x) { +; CHECK-LABEL: bfoz_from_lshr_shl_with_msb_zero_i32: +; CHECK: # %bb.0: +; CHECK-NEXT: nds.bfoz a0, a0, 0, 18 +; CHECK-NEXT: ret + %shl = shl i32 %x, 31 + %lshr = lshr i32 %shl, 13 + ret i32 %lshr +} + +; MSB < LSB + +define i32 @bfoz_from_and_shl_i32(i32 %x) { +; CHECK-LABEL: bfoz_from_and_shl_i32: +; CHECK: # %bb.0: +; CHECK-NEXT: nds.bfoz a0, a0, 12, 23 +; CHECK-NEXT: ret + %shifted = shl i32 %x, 12 + %masked = and i32 %shifted, 16773120 + ret i32 %masked +} + +define i32 @bfoz_from_lshr_shl_i32(i32 %x) { +; CHECK-LABEL: bfoz_from_lshr_shl_i32: +; CHECK: # %bb.0: +; CHECK-NEXT: nds.bfoz a0, a0, 19, 24 +; CHECK-NEXT: ret + %shl = shl i32 %x, 26 + %lshr = lshr i32 %shl, 7 + ret i32 %lshr +} + +; NDS.BFOS + +; MSB >= LSB + define i32 @bfos_from_ashr_shl_i32(i32 %x) { ; CHECK-LABEL: bfos_from_ashr_shl_i32: ; CHECK: # %bb.0: diff --git a/llvm/test/CodeGen/RISCV/rv64xandesperf.ll b/llvm/test/CodeGen/RISCV/rv64xandesperf.ll index 260d30be686dc..af7c300a92d1f 100644 --- a/llvm/test/CodeGen/RISCV/rv64xandesperf.ll +++ b/llvm/test/CodeGen/RISCV/rv64xandesperf.ll @@ -2,6 +2,10 @@ ; RUN: llc -mtriple=riscv64 -mattr=+xandesperf -verify-machineinstrs < %s \ ; RUN: | FileCheck %s +; NDS.BFOZ + +; MSB >= LSB + define i32 @bfoz_from_and_i32(i32 %x) { ; CHECK-LABEL: bfoz_from_and_i32: ; CHECK: # %bb.0: @@ -60,6 +64,94 @@ define i64 @bfoz_from_lshr_and_i64(i64 %x) { ret i64 %shifted } +; MSB = 0 + +define i32 @bfoz_from_and_shl_with_msb_zero_i32(i32 %x) { +; CHECK-LABEL: bfoz_from_and_shl_with_msb_zero_i32: +; CHECK: # %bb.0: +; CHECK-NEXT: nds.bfoz a0, a0, 0, 15 +; CHECK-NEXT: ret + %shifted = shl i32 %x, 15 + %masked = and i32 %shifted, 32768 + ret i32 %masked +} + +define i64 @bfoz_from_and_shl_with_msb_zero_i64(i64 %x) { +; CHECK-LABEL: bfoz_from_and_shl_with_msb_zero_i64: +; CHECK: # %bb.0: +; CHECK-NEXT: nds.bfoz a0, a0, 0, 48 +; CHECK-NEXT: ret + %shifted = shl i64 %x, 48 + %masked = and i64 %shifted, 281474976710656 + ret i64 %masked +} + +define i32 @bfoz_from_lshr_shl_with_msb_zero_i32(i32 %x) { +; CHECK-LABEL: bfoz_from_lshr_shl_with_msb_zero_i32: +; CHECK: # %bb.0: +; CHECK-NEXT: nds.bfoz a0, a0, 0, 18 +; CHECK-NEXT: ret + %shl = shl i32 %x, 31 + %lshr = lshr i32 %shl, 13 + ret i32 %lshr +} + +define i64 @bfoz_from_lshr_shl_with_msb_zero_i64(i64 %x) { +; CHECK-LABEL: bfoz_from_lshr_shl_with_msb_zero_i64: +; CHECK: # %bb.0: +; CHECK-NEXT: nds.bfoz a0, a0, 0, 44 +; CHECK-NEXT: ret + %shl = shl i64 %x, 63 + %lshr = lshr i64 %shl, 19 + ret i64 %lshr +} + +; MSB < LSB + +define i32 @bfoz_from_and_shl_i32(i32 %x) { +; CHECK-LABEL: bfoz_from_and_shl_i32: +; CHECK: # %bb.0: +; CHECK-NEXT: nds.bfoz a0, a0, 12, 23 +; CHECK-NEXT: ret + %shifted = shl i32 %x, 12 + %masked = and i32 %shifted, 16773120 + ret i32 %masked +} + +define i64 @bfoz_from_and_shl_i64(i64 %x) { +; CHECK-LABEL: bfoz_from_and_shl_i64: +; CHECK: # %bb.0: +; CHECK-NEXT: nds.bfoz a0, a0, 24, 35 +; CHECK-NEXT: ret + %shifted = shl i64 %x, 24 + %masked = and i64 %shifted, 68702699520 + ret i64 %masked +} + +define i32 @bfoz_from_lshr_shl_i32(i32 %x) { +; CHECK-LABEL: bfoz_from_lshr_shl_i32: +; CHECK: # %bb.0: +; CHECK-NEXT: nds.bfoz a0, a0, 19, 24 +; CHECK-NEXT: ret + %shl = shl i32 %x, 26 + %lshr = lshr i32 %shl, 7 + ret i32 %lshr +} + +define i64 @bfoz_from_lshr_shl_i64(i64 %x) { +; CHECK-LABEL: bfoz_from_lshr_shl_i64: +; CHECK: # %bb.0: +; CHECK-NEXT: nds.bfoz a0, a0, 25, 48 +; CHECK-NEXT: ret + %shl = shl i64 %x, 40 + %lshr = lshr i64 %shl, 15 + ret i64 %lshr +} + +; NDS.BFOS + +; MSB >= LSB + define i32 @bfos_from_ashr_shl_i32(i32 %x) { ; CHECK-LABEL: bfos_from_ashr_shl_i32: ; CHECK: # %bb.0: diff --git a/llvm/test/CodeGen/RISCV/rv64zba.ll b/llvm/test/CodeGen/RISCV/rv64zba.ll index a4d3b80edbd58..c93dc1f502f23 100644 --- a/llvm/test/CodeGen/RISCV/rv64zba.ll +++ b/llvm/test/CodeGen/RISCV/rv64zba.ll @@ -24,8 +24,7 @@ define i64 @slliuw(i64 %a) nounwind { ; ; RV64XANDESPERF-LABEL: slliuw: ; RV64XANDESPERF: # %bb.0: -; RV64XANDESPERF-NEXT: slli a0, a0, 32 -; RV64XANDESPERF-NEXT: srli a0, a0, 31 +; RV64XANDESPERF-NEXT: nds.bfoz a0, a0, 1, 32 ; RV64XANDESPERF-NEXT: ret %conv1 = shl i64 %a, 1 %shl = and i64 %conv1, 8589934590