From 8c2bc15b41aa70b306ffccc6f355bc2ede1bbe7d Mon Sep 17 00:00:00 2001
From: Irmen de Jong <irmen@razorvine.net>
Date: Sat, 3 Oct 2026 13:56:15 +0200
Subject: [PATCH] Fix IR peephole crash on lsigb.l + ext.b with mismatched
 register types regression was introduced in commit 2ce7a63c1e

---
 .../intermediate/IRPeepholeOptimizer.kt       | 13 ++++--
 codeGenIntermediate/test/TestIRPeepholeOpt.kt | 45 +++++++++++++++++++
 2 files changed, 54 insertions(+), 4 deletions(-)

diff --git a/codeGenIntermediate/src/prog8/codegen/intermediate/IRPeepholeOptimizer.kt b/codeGenIntermediate/src/prog8/codegen/intermediate/IRPeepholeOptimizer.kt
index 411bc1c96..25d30b2e1 100644
--- a/codeGenIntermediate/src/prog8/codegen/intermediate/IRPeepholeOptimizer.kt
+++ b/codeGenIntermediate/src/prog8/codegen/intermediate/IRPeepholeOptimizer.kt
@@ -1158,13 +1158,18 @@ jump p8_label_gen_2
                     mods.add(Mod(i+1, IRInstructions.binaryImmediate(Opcode.AND, IRDataType.LONG, outer.requireDest().registerNumber, 0xffff)))
                     mods.add(Mod(i, IRInstructions.move(IRDataType.LONG, outer.requireDest().registerNumber, inner.requireSrcA().registerNumber)))
                 }
-                // truncate-long/word-to-byte followed by zero-extend byte-to-word == mask with $ff
+                // truncate-long/word-to-byte followed by zero-extend byte-to-word == mask with $ff.
+                // This is only valid when the source and destination have the same type, because
+                // the rewritten loadr would otherwise access the source register with a different
+                // type than its definition (e.g. long source to word dest).
                 inner.opcode==Opcode.LSIGB && inner.type in setOf(IRDataType.WORD, IRDataType.LONG)
                         && outer.opcode==Opcode.EXT && outer.type==IRDataType.BYTE
                         && mid!=null && mid==outer.srcA?.register && inner.srcA!=null && outer.dest!=null
-                        && readCounts.getValue(mid)==1 -> {
-                    mods.add(Mod(i+1, IRInstructions.binaryImmediate(Opcode.AND, inner.type!!, outer.requireDest().registerNumber, 0xff)))
-                    mods.add(Mod(i, IRInstructions.move(inner.type!!, outer.requireDest().registerNumber, inner.requireSrcA().registerNumber)))
+                        && readCounts.getValue(mid)==1
+                        && inner.type == outer.requireDest().type -> {
+                    val resultType = outer.requireDest().type
+                    mods.add(Mod(i+1, IRInstructions.binaryImmediate(Opcode.AND, resultType, outer.requireDest().registerNumber, 0xff)))
+                    mods.add(Mod(i, IRInstructions.move(resultType, outer.requireDest().registerNumber, inner.requireSrcA().registerNumber)))
                 }
                 else -> continue
             }
diff --git a/codeGenIntermediate/test/TestIRPeepholeOpt.kt b/codeGenIntermediate/test/TestIRPeepholeOpt.kt
index a097af4d6..322d97654 100644
--- a/codeGenIntermediate/test/TestIRPeepholeOpt.kt
+++ b/codeGenIntermediate/test/TestIRPeepholeOpt.kt
@@ -514,6 +514,51 @@ class TestIRPeepholeOpt: FunSpec({
         instr[2].requireImmediateInt() shouldBe 42
     }
 
+    test("collapse lsigb.w + ext.b into loadr.w + and.w") {
+        val irProg = makeIRProgram(listOf(
+            IRInstructions.loadMemory(Opcode.LOADM, IRDataType.WORD, 7, IRMemory.direct("src")),
+            IRInstructions.binary(Opcode.LSIGB, IRDataType.WORD, 8, 7),
+            IRInstructions.binary(Opcode.EXT, IRDataType.BYTE, 9, 8),
+            IRInstructions.binary(Opcode.ADDR, IRDataType.WORD, 2, 9),
+            IRInstructions.returnVoid()
+        ))
+        val opt = IRPeepholeOptimizer(irProg, false)
+        opt.optimize(true, ErrorReporterForTests())
+        val instr = irProg.chunks().single().instructions
+        instr.any { it.opcode == Opcode.LSIGB } shouldBe false
+        instr.any { it.opcode == Opcode.EXT && it.requireDest().register == VirtualRegister.int(9) } shouldBe false
+        instr.any {
+            it.opcode == Opcode.LOADR &&
+                    it.type == IRDataType.WORD &&
+                    it.requireDest().register == VirtualRegister.int(9) &&
+                    it.requireSrcA().register == VirtualRegister.int(7)
+        } shouldBe true
+        instr.any {
+            it.opcode == Opcode.AND &&
+                    it.type == IRDataType.WORD &&
+                    it.requireDest().register == VirtualRegister.int(9) &&
+                    it.requireImmediateInt() == 0xff
+        } shouldBe true
+    }
+
+    test("do not collapse lsigb.l + ext.b when source and dest types differ") {
+        // lsigb.l produces a byte from a long; ext.b widens it to word. Rewriting this as
+        // loadr + and would require accessing the long source as word, which conflicts with
+        // the register type system. The optimizer must leave the original sequence intact.
+        val irProg = makeIRProgram(listOf(
+            IRInstructions.loadMemory(Opcode.LOADM, IRDataType.LONG, 7, IRMemory.direct("src")),
+            IRInstructions.binary(Opcode.LSIGB, IRDataType.LONG, 8, 7),
+            IRInstructions.binary(Opcode.EXT, IRDataType.BYTE, 9, 8),
+            IRInstructions.binary(Opcode.ADDR, IRDataType.WORD, 2, 9),
+            IRInstructions.returnVoid()
+        ))
+        val opt = IRPeepholeOptimizer(irProg, false)
+        opt.optimize(true, ErrorReporterForTests())
+        val instr = irProg.chunks().single().instructions
+        instr.any { it.opcode == Opcode.LSIGB } shouldBe true
+        instr.any { it.opcode == Opcode.EXT && it.requireDest().register == VirtualRegister.int(9) } shouldBe true
+    }
+
     test("coalesce redundant LOADX/STOREX to same index is removed") {
         val irProg = makeIRProgram(listOf(
             IRInstructions.loadMemory(Opcode.LOADX, IRDataType.BYTE, 1, IRMemory.indexed("myArray", 10, indexRegType)),