[llvm] [RISCV] Add TSFlag for reading past VL behaviour. NFCI (PR #149704)

[Luke Lau via llvm-commits]

https://github.com/lukel97 updated https://github.com/llvm/llvm-project/pull/149704

>From fc44f43f530dfb72724813f770d1666fd6f31078 Mon Sep 17 00:00:00 2001
From: Luke Lau <luke at igalia.com>
Date: Sun, 20 Jul 2025 19:59:42 +0800
Subject: [PATCH] [RISCV] Add TSFlag for reading past VL behaviour. NFCI

Currently we have a switch statement that checks if a vector instruction may read elements past VL. However it currently doesn't account for instructions in vendor extensions.

Handling all possible vendor instructions will result in quite a lot of opcodes being added, so I've created a new TSFlag that we can declare in TableGen, and added it to the existing instruction definitions.

I've tried to be conservative as possible here: All SiFive vendor vector instructions should be covered by the flag, as well as all of XRivosVizip, and ri.vextract from XRivosVisni.

For now this should be NFC because coincidentally, these instructions aren't handled in getOperandInfo, so RISCVVLOptimizer should currently avoid touching them despite them being liberally handled in getMinimumVLForUser.

However in an upcoming patch we'll need to also bail in getMinimumVLForUser, so this prepares for it.
---
 .../Target/RISCV/MCTargetDesc/RISCVBaseInfo.h |  9 ++++++
 llvm/lib/Target/RISCV/RISCVInstrFormats.td    |  6 ++++
 llvm/lib/Target/RISCV/RISCVInstrInfoV.td      |  9 +++---
 llvm/lib/Target/RISCV/RISCVInstrInfoXRivos.td |  3 +-
 llvm/lib/Target/RISCV/RISCVInstrInfoXSf.td    |  2 ++
 llvm/lib/Target/RISCV/RISCVInstrInfoXSfmm.td  |  5 +++
 llvm/lib/Target/RISCV/RISCVVLOptimizer.cpp    | 31 ++-----------------
 7 files changed, 31 insertions(+), 34 deletions(-)

diff --git a/llvm/lib/Target/RISCV/MCTargetDesc/RISCVBaseInfo.h b/llvm/lib/Target/RISCV/MCTargetDesc/RISCVBaseInfo.h
index 7ad5d5f3118b6..e032455ff2ab3 100644
--- a/llvm/lib/Target/RISCV/MCTargetDesc/RISCVBaseInfo.h
+++ b/llvm/lib/Target/RISCV/MCTargetDesc/RISCVBaseInfo.h
@@ -139,6 +139,9 @@ enum {
   // 3 -> SEW * 4
   DestEEWShift = ElementsDependOnMaskShift + 1,
   DestEEWMask = 3ULL << DestEEWShift,
+
+  ReadsPastVLShift = DestEEWShift + 2,
+  ReadsPastVLMask = 1ULL << ReadsPastVLShift,
 };
 
 // Helper functions to read TSFlags.
@@ -195,6 +198,12 @@ static inline bool elementsDependOnMask(uint64_t TSFlags) {
   return TSFlags & ElementsDependOnMaskMask;
 }
 
+/// \returns true if the instruction may read elements past VL, e.g.
+/// vslidedown/vrgather
+static inline bool readsPastVL(uint64_t TSFlags) {
+  return TSFlags & ReadsPastVLMask;
+}
+
 static inline unsigned getVLOpNum(const MCInstrDesc &Desc) {
   const uint64_t TSFlags = Desc.TSFlags;
   // This method is only called if we expect to have a VL operand, and all
diff --git a/llvm/lib/Target/RISCV/RISCVInstrFormats.td b/llvm/lib/Target/RISCV/RISCVInstrFormats.td
index d9c6101478064..878a0ec938919 100644
--- a/llvm/lib/Target/RISCV/RISCVInstrFormats.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrFormats.td
@@ -261,6 +261,12 @@ class RVInstCommon<dag outs, dag ins, string opcodestr, string argstr,
   // Indicates the EEW of a vector instruction's destination operand.
   EEW DestEEW = EEWSEWx1;
   let TSFlags{25-24} = DestEEW.Value;
+
+  // Some vector instructions like vslidedown/vrgather will read elements past
+  // VL, and should be marked to make sure RISCVVLOptimizer doesn't reduce its
+  // operands' VLs.
+  bit ReadsPastVL = 0;
+  let TSFlags{26} = ReadsPastVL;
 }
 
 class RVInst<dag outs, dag ins, string opcodestr, string argstr,
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoV.td b/llvm/lib/Target/RISCV/RISCVInstrInfoV.td
index 33c713833d8b9..cebab2112d02d 100644
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoV.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoV.td
@@ -1703,8 +1703,9 @@ let Constraints = "@earlyclobber $vd", RVVConstraint = SlideUp in {
 defm VSLIDEUP_V : VSLD_IV_X_I<"vslideup", 0b001110, /*slidesUp=*/true>;
 defm VSLIDE1UP_V : VSLD1_MV_X<"vslide1up", 0b001110>;
 } // Constraints = "@earlyclobber $vd", RVVConstraint = SlideUp
+let ReadsPastVL = 1 in
 defm VSLIDEDOWN_V : VSLD_IV_X_I<"vslidedown", 0b001111, /*slidesUp=*/false>;
-let ElementsDependOn = EltDepsVL in
+let ElementsDependOn = EltDepsVL, ReadsPastVL = 1 in
 defm VSLIDE1DOWN_V : VSLD1_MV_X<"vslide1down", 0b001111>;
 } // Predicates = [HasVInstructions]
 
@@ -1712,19 +1713,19 @@ let Predicates = [HasVInstructionsAnyF] in {
 let Constraints = "@earlyclobber $vd", RVVConstraint = SlideUp in {
 defm VFSLIDE1UP_V : VSLD1_FV_F<"vfslide1up", 0b001110>;
 } // Constraints = "@earlyclobber $vd", RVVConstraint = SlideUp
-let ElementsDependOn = EltDepsVL in
+let ElementsDependOn = EltDepsVL, ReadsPastVL = 1 in
 defm VFSLIDE1DOWN_V : VSLD1_FV_F<"vfslide1down", 0b001111>;
 } // Predicates = [HasVInstructionsAnyF]
 
 let Predicates = [HasVInstructions] in {
 // Vector Register Gather Instruction
-let Constraints = "@earlyclobber $vd", RVVConstraint = Vrgather in {
+let Constraints = "@earlyclobber $vd", RVVConstraint = Vrgather, ReadsPastVL = 1 in {
 defm VRGATHER_V : VGTR_IV_V_X_I<"vrgather", 0b001100>;
 def VRGATHEREI16_VV : VALUVV<0b001110, OPIVV, "vrgatherei16.vv">,
                       SchedBinaryMC<"WriteVRGatherEI16VV",
                                     "ReadVRGatherEI16VV_data",
                                     "ReadVRGatherEI16VV_index">;
-} // Constraints = "@earlyclobber $vd", RVVConstraint = Vrgather
+} // Constraints = "@earlyclobber $vd", RVVConstraint = Vrgather, ReadsPastVL = 1
 
 // Vector Compress Instruction
 let Constraints = "@earlyclobber $vd", RVVConstraint = Vcompress, ElementsDependOn = EltDepsVLMask in {
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoXRivos.td b/llvm/lib/Target/RISCV/RISCVInstrInfoXRivos.td
index 3912eb0d16c59..6e8e910249c82 100644
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoXRivos.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoXRivos.td
@@ -58,7 +58,7 @@ class CustomRivosXVI<bits<6> funct6, RISCVVFormat opv, dag outs, dag ins,
 
 let Predicates = [HasVendorXRivosVizip], DecoderNamespace = "XRivos",
   Constraints = "@earlyclobber $vd", RVVConstraint = Vrgather,
-  Inst<6-0> = OPC_CUSTOM_2.Value in  {
+  Inst<6-0> = OPC_CUSTOM_2.Value, ReadsPastVL = 1 in  {
 defm RI_VZIPEVEN_V : VALU_IV_V<"ri.vzipeven", 0b001100>;
 defm RI_VZIPODD_V : VALU_IV_V<"ri.vzipodd", 0b011100>;
 defm RI_VZIP2A_V : VALU_IV_V<"ri.vzip2a", 0b000100>;
@@ -126,6 +126,7 @@ def RI_VINSERT : CustomRivosVXI<0b010000, OPMVX, (outs VR:$vd_wb),
                                 (ins VR:$vd, GPR:$rs1, uimm5:$imm),
                                 "ri.vinsert.v.x", "$vd, $rs1, $imm">;
 
+let ReadsPastVL = 1 in
 def RI_VEXTRACT : CustomRivosXVI<0b010111, OPMVV, (outs GPR:$rd),
                                 (ins VR:$vs2, uimm5:$imm),
                                 "ri.vextract.x.v", "$rd, $vs2, $imm">;
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoXSf.td b/llvm/lib/Target/RISCV/RISCVInstrInfoXSf.td
index 17fb75eb851c4..8b3b3ed6db188 100644
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoXSf.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoXSf.td
@@ -74,6 +74,7 @@ class RVInstVCCustom2<bits<4> funct6_hi4, bits<3> funct3, dag outs, dag ins,
   let Uses = [VL, VTYPE];
   let RVVConstraint = NoConstraint;
   let ElementsDependOn = EltDepsVLMask;
+  let ReadsPastVL = 1;
 }
 
 class RVInstVCFCustom2<bits<4> funct6_hi4, bits<3> funct3, dag outs, dag ins,
@@ -98,6 +99,7 @@ class RVInstVCFCustom2<bits<4> funct6_hi4, bits<3> funct3, dag outs, dag ins,
   let Uses = [VL, VTYPE];
   let RVVConstraint = NoConstraint;
   let ElementsDependOn = EltDepsVLMask;
+  let ReadsPastVL = 1;
 }
 
 class VCIXInfo<string suffix, VCIXType type, DAGOperand TyRd,
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoXSfmm.td b/llvm/lib/Target/RISCV/RISCVInstrInfoXSfmm.td
index 66cb2d53da960..a5ee701386b6d 100644
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoXSfmm.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoXSfmm.td
@@ -65,6 +65,7 @@ class SFInstTileMemOp<dag outs, dag ins, bits<3> nf, RISCVOpcode opcode,
   let Inst{6-0} = opcode.Value;
 
   let Uses = [VTYPE, VL];
+  let ReadsPastVL = 1;
 }
 
 let hasSideEffects = 0, mayLoad = 1, mayStore = 0 in
@@ -94,6 +95,7 @@ class SFInstTileMoveOp<bits<6> funct6, dag outs, dag ins, string opcodestr,
   let Inst{6-0} = OPC_OP_V.Value;
 
   let Uses = [VTYPE, VL];
+  let ReadsPastVL = 1;
 }
 
 let hasSideEffects = 0, mayLoad = 0, mayStore = 0 in
@@ -113,6 +115,7 @@ class SFInstMatmulF<dag outs, dag ins, string opcodestr, string argstr>
   let Inst{6-0} = OPC_OP_VE.Value;
 
   let Uses = [VTYPE, VL];
+  let ReadsPastVL = 1;
 }
 
 let hasSideEffects = 0, mayLoad = 0, mayStore = 0 in
@@ -135,6 +138,7 @@ class SFInstMatmulF8<bit a, bit b, dag outs, dag ins,
   let Inst{6-0} = OPC_OP_VE.Value;
 
   let Uses = [VTYPE, VL];
+  let ReadsPastVL = 1;
 }
 
 
@@ -167,6 +171,7 @@ class SFInstMatmulI8<bit funct6_1, bit a, bit b, dag outs, dag ins,
   let Inst{6-0} = OPC_OP_VE.Value;
 
   let Uses = [VTYPE, VL];
+  let ReadsPastVL = 1;
 }
 
 class I8Encode<bit encoding, string name> {
diff --git a/llvm/lib/Target/RISCV/RISCVVLOptimizer.cpp b/llvm/lib/Target/RISCV/RISCVVLOptimizer.cpp
index 15bd3466373a7..b16f817064ce2 100644
--- a/llvm/lib/Target/RISCV/RISCVVLOptimizer.cpp
+++ b/llvm/lib/Target/RISCV/RISCVVLOptimizer.cpp
@@ -1227,34 +1227,6 @@ static bool isVectorOpUsedAsScalarOp(const MachineOperand &MO) {
   }
 }
 
-/// Return true if MI may read elements past VL.
-static bool mayReadPastVL(const MachineInstr &MI) {
-  const RISCVVPseudosTable::PseudoInfo *RVV =
-      RISCVVPseudosTable::getPseudoInfo(MI.getOpcode());
-  if (!RVV)
-    return true;
-
-  switch (RVV->BaseInstr) {
-  // vslidedown instructions may read elements past VL. They are handled
-  // according to current tail policy.
-  case RISCV::VSLIDEDOWN_VI:
-  case RISCV::VSLIDEDOWN_VX:
-  case RISCV::VSLIDE1DOWN_VX:
-  case RISCV::VFSLIDE1DOWN_VF:
-
-  // vrgather instructions may read the source vector at any index < VLMAX,
-  // regardless of VL.
-  case RISCV::VRGATHER_VI:
-  case RISCV::VRGATHER_VV:
-  case RISCV::VRGATHER_VX:
-  case RISCV::VRGATHEREI16_VV:
-    return true;
-
-  default:
-    return false;
-  }
-}
-
 bool RISCVVLOptimizer::isCandidate(const MachineInstr &MI) const {
   const MCInstrDesc &Desc = MI.getDesc();
   if (!RISCVII::hasVLOp(Desc.TSFlags) || !RISCVII::hasSEWOp(Desc.TSFlags))
@@ -1315,7 +1287,8 @@ RISCVVLOptimizer::getMinimumVLForUser(const MachineOperand &UserOp) const {
     return std::nullopt;
   }
 
-  if (mayReadPastVL(UserMI)) {
+  if (RISCVII::readsPastVL(
+          TII->get(RISCV::getRVVMCOpcode(UserMI.getOpcode())).TSFlags)) {
     LLVM_DEBUG(dbgs() << "    Abort because used by unsafe instruction\n");
     return std::nullopt;
   }