feat(arm64): wide immediates, SIMD compare and system operand forms

Assisted-by: GLM 5.3 Flash

asm/arm64_encode_test.go

@@ -4,6 +4,7 @@
 package asm
 
 import (
+	"strings"
 	"testing"
 
 	"sourcedock.dev/petrbalvin/gasm-devkit/ast"
@@ -1295,20 +1296,170 @@ func TestArm64ExclNoOffset(t *testing.T) {
 	}
 }
 
-// TestArm64AddSubImmRange: immediates that cannot ride the imm12 field are
-// rejected instead of wrapping through int32.
-func TestArm64AddSubImmRange(t *testing.T) {
-	for _, body := range []string{
-		"\tADD $0x100000000, R0, R1\n",
-		"\tSUB $-0x100000000, R0, R1\n",
-		"\tCMP $0x100000000, R0\n",
-	} {
-		f, errs := parser.Parse("test_arm64.s", "#include \"textflag.h\"\n\nTEXT ·f(SB), NOSPLIT, $0-0\n"+body+"\tRET\n")
-		if len(errs) > 0 {
-			t.Fatalf("parse: %v", errs)
+// TestArm64AddSubImmWide pins the wide-immediate classification the toolchain
+// applies to the ADD/SUB family (asm7.go cases 48, 62, 13): the ADDCON2 split
+// into two imm12 instructions for plain ADD/SUB, the bitmask ORR into REGTMP,
+// and the MOVZ/MOVN/MOVK materialisations followed by the register form.
+// Comparisons never split, and the W forms classify the 32-bit value.  Every
+// word is go tool asm's own for the same source.
+func TestArm64AddSubImmWide(t *testing.T) {
+	got := arm64Words(t, strings.Join([]string{
+		"\tADD $0xaaaaaa, R2, R3",
+		"\tSUB $0xaaaaaa, R2",
+		"\tADD $0x186a0, R2, R5",
+		"\tADD $0x1ffe00, R2, R3",
+		"\tADD $0x3fffffffc000, R5",
+		"\tADD $-100000, R2, R3",
+		"\tADD $-2048, R2, R3",
+		"\tCMP $0xaaaaaa, R2",
+		"\tCMP $0xffffffffffa0, R3",
+		"\tCMPW $27745, R2",
+		"\tCMPW $0x60060, R2",
+		"\tADDS $0xaaaaaa, R2, R3",
+		"\tADD $0x12345678, R2, R3",
+		"\tADDW $0x60060, R2",
+		"\tSUB $0xe7791f700, R3, R1",
+		"\tADDW $0x12345678, R2, R3",
+		"\tCMN $0x1000000, R2",
+	}, "\n")+"\n")
+	want := []uint32{
+		0x912aa843, 0x916aa863, // ADD $0xaaaaaa, R2, R3: ADDCON2 split
+		0xd12aa842, 0xd16aa842, // SUB $0xaaaaaa, R2: split with Rd = Rn
+		0x911a8045, 0x914060a5, // ADD $0x186a0, R2, R5: split
+		0xb2772ffb, 0x8b1b0043, // ADD $0x1ffe00: bitmask beats the split
+		0xb2727ffb, 0x8b1b00a5, // ADD $0x3fffffffc000: bitmask into REGTMP
+		0x9290d3fb, 0xf2bfffdb, 0x8b1b0043, // ADD $-100000: MOVN + MOVK
+		0x9280fffb, 0x8b1b0043, // ADD $-2048: single MOVN + ADD
+		0xd295555b, 0xf2a0155b, 0xeb1b005f, // CMP: never split, MOVZ + MOVK
+		0x92800bfb, 0xf2e0001b, 0xeb1b007f, // CMP $0xffffffffffa0: MOVN + fixup
+		0x528d8c3b, 0x6b1b005f, // CMPW $27745: W movcon, single MOVZW
+		0x52800c1b, 0x72a000db, 0x6b1b005f, // CMPW $0x60060: S form skips the split
+		0xd295555b, 0xf2a0155b, 0xab1b0043, // ADDS $0xaaaaaa: MOVZ + MOVK + ADDS
+		0xd28acf1b, 0xf2a2469b, 0x8b1b0043, // ADD $0x12345678: MOVZ + MOVK
+		0x11018042, 0x11418042, // ADDW $0x60060: W split
+		0xd29ee01b, 0xf2aef23b, 0xf2c001db, 0xcb1b0061, // SUB $0xe7791f700
+		0x528acf1b, 0x72a2469b, 0x0b1b0043, // ADDW $0x12345678: MOVZW + MOVKW
+		0xd2a0201b, 0xab1b005f, // CMN $0x1000000: single MOVZ + CMN
+		0xd65f03c0, // RET
+	}
+	if len(got) != len(want) {
+		t.Fatalf("word count = %d, want %d", len(got), len(want))
+	}
+	for i := range want {
+		if got[i] != want[i] {
+			t.Errorf("wide word %d = %08x, want %08x", i, got[i], want[i])
 		}
-		if _, err := AssembleFileARM64(f); err == nil {
-			t.Errorf("%s: expected an error, got none", body)
+	}
+}
+
+// TestArm64CarryImmWide pins the carry family's $0 spellings in two and
+// three operands, the ROR shift on the logical group (and its rejection for
+// the arithmetic forms), the NGC/MNEG zero-register aliases and the vector
+// alias with an element selector.  Words are go tool asm's own.
+func TestArm64CarryShiftAlias(t *testing.T) {
+	got := arm64Words(t, "\tADC $0, R20\n\tADC $0, R20, R4\n\tSBCS $0, R4, R12\n"+
+		"\tSBCS R15, R4, R12\n\tANDW R9@>7, R19, R26\n\tAND R1@>33, R2, R3\n"+
+		"\tNEGSW R23<<1, R30\n\tNGC R2, R7\n\tMNEG R14, R27, R23\n")
+	want := []uint32{
+		0x9a1f0294, // ADC ZR, R20, R20
+		0x9a1f0284, // ADC ZR, R20, R4
+		0xfa1f008c, // SBCS ZR, R4, R12
+		0xfa0f008c, // SBCS R15, R4, R12
+		0x0ac91e7a, // ANDW R9 ROR 7, R19, R26
+		0x8ac18443, // AND R1 ROR 33, R2, R3
+		0x6b1707fe, // SUBSW ZR, R30, R23 LSL 1
+		0xda0203e7, // SBC ZR, R7, R2
+		0x9b0eff77, // MSUB ZR, R27, R14, R23
+		0xd65f03c0, // RET
+	}
+	if len(got) != len(want) {
+		t.Fatalf("word count = %d, want %d", len(got), len(want))
+	}
+	for i := range want {
+		if got[i] != want[i] {
+			t.Errorf("carry word %d = %08x, want %08x", i, got[i], want[i])
+		}
+	}
+
+	// ROR on an arithmetic form is unallocated: the toolchain reports an
+	// unsupported shift operator.
+	f, errs := parser.Parse("test_arm64.s", "#include \"textflag.h\"\n\nTEXT ·f(SB), NOSPLIT, $0-0\n\tADD R1@>33, R2, R3\n\tRET\n")
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	if _, err := AssembleFileARM64(f); err == nil {
+		t.Error("ADD R1@>33: expected an error, got none")
+	}
+}
+
+// TestArm64VecAliasElement pins the register-alias rewrite inside a vector
+// operand with an element selector and inside a split register list: the
+// aliases resolve textually where the parser carries the selector apart from
+// the name.  Words are go tool asm's own.
+func TestArm64VecAliasElement(t *testing.T) {
+	src := `#include "textflag.h"
+
+#define POLY V15
+#define ACC0 V8
+#define ACC1 V9
+
+TEXT ·f(SB), NOSPLIT, $0-0
+	VMOV R1, POLY.D[0]
+	VEOR POLY.B16, POLY.B16, POLY.B16
+	VLD1 (R0), [ACC0.B16]
+	VLD1.P (R0), [ACC0.B16, ACC1.B16]
+	VST1.P [ACC0.B16, ACC1.B16], 32(R1)
+	RET
+`
+	f, errs := parser.Parse("test_arm64.s", src)
+	if len(errs) > 0 {
+		t.Fatalf("parse: %v", errs)
+	}
+	img, err := AssembleFileARM64(f)
+	if err != nil {
+		t.Fatalf("AssembleFileARM64: %v", err)
+	}
+	got := leWords(img.Code)
+	want := []uint32{
+		0x4e081c2f, // INS V15.D[0], R1
+		0x6e2f1def, // VEOR V15.B16, V15.B16, V15.B16
+		0x4c407008, // VLD1 (R0), [V8.B16]
+		0x4cdfa008, // VLD1.P (R0), [V8.B16, V9.B16]
+		0x4c9fa028, // VST1.P [V8.B16, V9.B16], 32(R1)
+		0xd65f03c0, // RET
+	}
+	if len(got) != len(want) {
+		t.Fatalf("word count = %d, want %d", len(got), len(want))
+	}
+	for i := range want {
+		if got[i] != want[i] {
+			t.Errorf("vecalias word %d = %08x, want %08x", i, got[i], want[i])
+		}
+	}
+}
+
+// TestArm64AddSubImmBeyond32 pins the materialisation the toolchain applies
+// once the value leaves every imm12 form: a constant sequence into REGTMP
+// (R27) followed by the register form.  SUB $-0x100000000 is a bitmask
+// immediate, so it rides the ORR form; the others take MOVZ.  Words are go
+// tool asm's own.
+func TestArm64AddSubImmBeyond32(t *testing.T) {
+	got := arm64Words(t, "\tADD $0x100000000, R0, R1\n\tSUB $-0x100000000, R0, R1\n\tCMP $0x100000000, R0\n")
+	want := []uint32{
+		0xd2c0003b, // MOVZ $(1<<32>>16), R27 (hw=2)
+		0x8b1b0001, // ADD R27, R0, R1
+		0xb2607ffb, // ORR $-4294967296, ZR, R27 (bitmask)
+		0xcb1b0001, // SUB R27, R0, R1
+		0xd2c0003b, // MOVZ $(1<<32>>16), R27 (hw=2)
+		0xeb1b001f, // CMP R27, R0
+		0xd65f03c0, // RET
+	}
+	if len(got) != len(want) {
+		t.Fatalf("word count = %d, want %d", len(got), len(want))
+	}
+	for i := range want {
+		if got[i] != want[i] {
+			t.Errorf("word %d = %08x, want %08x", i, got[i], want[i])
 		}
 	}
 }