CharlesKWON
b1d89b9783
Second pcode peephole to match the one added for FieldGet(literal). SqlExprToPrg auto-wraps CHAR column references with AllTrim() to match SqlCmpEq's CHAR-padding trim semantics, so every string WHERE predicate evaluates `AllTrim(FieldGet(n)) == 'literal'` per row. Before this commit each of those per-row evaluations did: 1. PushSymbol ALLTRIM 2. PushSymbol FIELDGET → Function(1) [1 RTL Frame] 3. parseCharField → MakeString [alloc: copies raw bytes] 4. Function(1) → AllTrim RTL [1 RTL Frame] 5. strings.TrimSpace [alloc: new string] 6. Return, continue New opcode `PcOpFieldTrim <idx>` (0x47) fuses the two RTL calls into a single opcode that: 1. Calls FastFieldGetter directly (no Frame/Function dispatch). 2. Walks the returned string with ASCII-space trim in place. 3. Pushes `s[lo:hi]` — a sub-slice, no new allocation. 4. Short-circuits back to the same string if no trim needed. genpc recognizes the shape `AllTrim(FieldGet(<int-literal>))` in emitCall and emits the fused opcode automatically — no SQL-side API change. Matches the existing FieldGet peephole's shape. Bench impact (50k rows, 3-run steady state, vs raw RDD baseline 6.2ms): String WHERE before 7.9ms → after 6.2ms 1.00x (parity!) Numeric WHERE 6.9ms (unchanged) 1.11x No WHERE 9.1ms (unchanged) 1.47x String WHERE is now at parity with the raw Harbour-style RDD scan. Compared to session start (119ms), that's a 19x speedup. Validation: - FiveSql2 43/43 - Harbour compat 51/51 - go test ./... ALL PASS Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
126 lines
3.6 KiB
Go
126 lines
3.6 KiB
Go
// Copyright (c) 2026 Charles KWON OhJun (charleskwonohjun@gmail.com)
|
|
// All rights reserved.
|
|
|
|
// Five pcode — stack-based bytecode for FRB interpreter mode.
|
|
// Each opcode maps 1:1 to a Thread method call, making the pcode
|
|
// a direct serialization of what gengo generates as Go code.
|
|
//
|
|
// Format: [opcode:1byte] [operands:variable]
|
|
// Strings: [len:uint16 LE] [bytes]
|
|
// Numbers: int64 = 8 bytes LE, float64 = 8 bytes LE
|
|
|
|
package hbrt
|
|
|
|
// Opcode definitions
|
|
const (
|
|
// Stack operations
|
|
PcOpNop byte = 0x00
|
|
PcOpPushNil byte = 0x01
|
|
PcOpPushTrue byte = 0x02
|
|
PcOpPushFalse byte = 0x03
|
|
PcOpPushInt byte = 0x04 // + int64 LE
|
|
PcOpPushDouble byte = 0x05 // + float64 LE (8 bytes)
|
|
PcOpPushString byte = 0x06 // + uint16 len + bytes
|
|
PcOpPushLocal byte = 0x07 // + uint16 index
|
|
PcOpPopLocal byte = 0x08 // + uint16 index
|
|
PcOpPop byte = 0x09
|
|
PcOpDup byte = 0x0A
|
|
|
|
// Arithmetic
|
|
PcOpPlus byte = 0x10
|
|
PcOpMinus byte = 0x11
|
|
PcOpMult byte = 0x12
|
|
PcOpDivide byte = 0x13
|
|
PcOpMod byte = 0x14
|
|
PcOpPower byte = 0x15
|
|
PcOpNegate byte = 0x16
|
|
|
|
// Comparison
|
|
PcOpEqual byte = 0x20
|
|
PcOpNotEqual byte = 0x21
|
|
PcOpLess byte = 0x22
|
|
PcOpGreater byte = 0x23
|
|
PcOpLessEq byte = 0x24
|
|
PcOpGreaterEq byte = 0x25
|
|
PcOpInString byte = 0x26
|
|
|
|
// Logical
|
|
PcOpAnd byte = 0x28
|
|
PcOpOr byte = 0x29
|
|
PcOpNot byte = 0x2A
|
|
|
|
// String
|
|
PcOpConcat byte = 0x2C // same as Plus for strings
|
|
|
|
// Flow control
|
|
PcOpJump byte = 0x30 // + int32 LE (relative offset)
|
|
PcOpJumpFalse byte = 0x31 // + int32 LE
|
|
PcOpJumpTrue byte = 0x32 // + int32 LE
|
|
PcOpReturn byte = 0x33
|
|
PcOpRetValue byte = 0x34
|
|
|
|
// Frame
|
|
PcOpFrame byte = 0x38 // + uint16 params + uint16 locals
|
|
PcOpEndProc byte = 0x39
|
|
|
|
// Function calls
|
|
PcOpPushSymbol byte = 0x40 // + uint16 string len + name
|
|
PcOpPushNilArg byte = 0x41 // push NIL for function self
|
|
PcOpFunction byte = 0x42 // + uint16 nArgs
|
|
PcOpDo byte = 0x43 // + uint16 nArgs
|
|
|
|
// Workarea field access — skips PushSymbol + Function dispatch
|
|
// for `FieldGet(n)` where n is a literal. Emitted by genpc as a
|
|
// peephole optimization. Operand: uint16 1-based field position.
|
|
PcOpFieldGet byte = 0x46
|
|
|
|
// `AllTrim(FieldGet(n))` peephole — fetch the field, trim the
|
|
// result in place, push one string. Skips two Function dispatches
|
|
// (FieldGet + AllTrim) and one intermediate string allocation
|
|
// per invocation. Operand: uint16 1-based field position.
|
|
PcOpFieldTrim byte = 0x47
|
|
|
|
// Self / OOP
|
|
PcOpPushSelf byte = 0x48
|
|
PcOpPushSelfField byte = 0x49 // + uint16 len + name
|
|
PcOpSetSelfField byte = 0x4A // + uint16 len + name
|
|
PcOpSend byte = 0x4B // + uint16 len + name + uint16 nArgs
|
|
|
|
// Array / Hash
|
|
PcOpArrayGen byte = 0x50 // + uint16 count
|
|
PcOpHashGen byte = 0x51 // + uint16 count
|
|
PcOpArrayPush byte = 0x52
|
|
PcOpArrayPop byte = 0x53
|
|
|
|
// Block
|
|
PcOpPushBlock byte = 0x58 // + uint32 codeLen + pcode bytes + uint16 nDetached
|
|
|
|
// Local operations
|
|
PcOpLocalAddInt byte = 0x60 // + uint16 index + int32 value
|
|
PcOpInc byte = 0x61
|
|
PcOpDec byte = 0x62
|
|
|
|
// Special
|
|
PcOpPopLogical byte = 0x70 // pop and store logical result
|
|
PcOpPushBool byte = 0x71 // + 1 byte (0 or 1)
|
|
|
|
// Line info (for debugging)
|
|
PcOpLine byte = 0xFE // + uint16 lineNo
|
|
PcOpHalt byte = 0xFF
|
|
)
|
|
|
|
// PcodeFunc represents a pcode-compiled function.
|
|
type PcodeFunc struct {
|
|
Name string
|
|
Code []byte // bytecode
|
|
Params int // number of parameters
|
|
Locals int // number of locals
|
|
}
|
|
|
|
// PcodeModule represents a compiled pcode module (multiple functions).
|
|
type PcodeModule struct {
|
|
Name string
|
|
Funcs map[string]*PcodeFunc
|
|
Strings []string // string constant pool
|
|
}
|