feat(amd64): encode the mixed-width extend family and PMOVMSKB

Assisted-by: GLM 5.3

asm/encodable.go

@@ -86,9 +86,16 @@ func Encodable(mnemonic string) bool {
 		"BSWAP",
 		"PREFETCHNTA", "PREFETCHT0", "PREFETCHT1", "PREFETCHT2",
 		"MOVBLZX", "MOVBQZX", "MOVWLZX", "MOVWQZX", "MOVWLSX", "MOVLQSX",
+		"MOVBWZX", "MOVBWSX", "MOVBLSX", "MOVBQSX", "MOVWQSX", "MOVLQZX",
 		"CVTSL2SD", "CVTSQ2SD",
 		"MOVOU", "MOVO", "MOVUPS", "MOVAPS", "MOVUPD", "MOVAPD", "MOVSD", "MOVSS":
 		return true
 	}
+	// Full-name dispatches the size split would eat (a trailing width
+	// letter that is part of the mnemonic).
+	switch upper {
+	case "PMOVMSKB":
+		return true
+	}
 	return false
 }

asm/encode.go

@@ -101,6 +101,11 @@ func (e *enc) encode(mnem string, ops []Operand) error {
 	if m, ok := sseBinTable[base]; ok {
 		return e.encodeSSEBin(m, ops)
 	}
+	// PMOVMSKB ends in a width letter the size split would eat, so it
+	// dispatches on the full name like the packed binaries above.
+	if upper == "PMOVMSKB" {
+		return e.encodePmovmskb(upper, ops)
+	}
 	switch base {
 	case "MOV":
 		return e.encodeMov(ops, size)
@@ -126,7 +131,8 @@ func (e *enc) encode(mnem string, ops []Operand) error {
 		return e.encodeBswap(ops, size)
 	case "PREFETCHNTA", "PREFETCHT0", "PREFETCHT1", "PREFETCHT2":
 		return e.encodePrefetch(base, ops)
-	case "MOVBLZX", "MOVBQZX", "MOVWLZX", "MOVWQZX", "MOVWLSX", "MOVLQSX":
+	case "MOVBLZX", "MOVBQZX", "MOVWLZX", "MOVWQZX", "MOVWLSX", "MOVLQSX",
+		"MOVBWZX", "MOVBWSX", "MOVBLSX", "MOVBQSX", "MOVWQSX", "MOVLQZX":
 		return e.encodeMovExtend(base, ops)
 	case "CVTSL2SD", "CVTSQ2SD":
 		return e.encodeCvtsi2sd(base == "CVTSQ2SD", ops)

asm/encode_test.go

@@ -357,6 +357,18 @@ func TestScalarGroundTruth(t *testing.T) {
 		{"MOVBQZX AL,R8", "MOVBQZX", []Operand{AL, r8}, "4c0fb6c0", "MOVZX"},
 		{"MOVWLZX AX,CX", "MOVWLZX", []Operand{AX, CX}, "0fb7c8", "MOVZX"},
 		{"MOVWQZX AX,R8", "MOVWQZX", []Operand{AX, r8}, "4c0fb7c0", "MOVZX"},
+		// The width pairs the toolchain accepts and GOROOT uses; bytes
+		// pinned from go tool asm (see testdata/verify/widen_amd64.s).
+		{"MOVBWZX (BX),R11W", "MOVBWZX", []Operand{Ptr(BX, 0, 1), Reg{idx: 11, size: 2}}, "66440fb61b", "MOVZX"},
+		{"MOVBWSX (BX),R11W", "MOVBWSX", []Operand{Ptr(BX, 0, 1), Reg{idx: 11, size: 2}}, "66440fbe1b", "MOVSX"},
+		{"MOVBLSX (BX),AX", "MOVBLSX", []Operand{Ptr(BX, 0, 1), AX}, "0fbe03", "MOVSX"},
+		{"MOVBQSX (BX),R8", "MOVBQSX", []Operand{Ptr(BX, 0, 1), r8}, "4c0fbe03", "MOVSX"},
+		{"MOVWQSX (BX),R9", "MOVWQSX", []Operand{Ptr(BX, 0, 2), r9}, "4c0fbf0b", "MOVSX"},
+		// A long to quad zero-extend is a plain 32-bit move.
+		{"MOVLQZX (BX),DX", "MOVLQZX", []Operand{Ptr(BX, 0, 4), DX}, "8b13", "MOV"},
+		{"MOVLQZX AX,DX", "MOVLQZX", []Operand{AX, DX}, "8bd0", "MOV"},
+		{"PMOVMSKB X1,AX", "PMOVMSKB", []Operand{vreg(t, "X1"), AX}, "660fd7c1", "PMOVMSKB"},
+		{"PMOVMSKB X11,CX", "PMOVMSKB", []Operand{vreg(t, "X11"), CX}, "66410fd7cb", "PMOVMSKB"},
 		{"CVTSL2SD R8,X13", "CVTSL2SD", []Operand{r8, vreg(t, "X13")}, "f2450f2ae8", "CVTSI2SD"},
 		{"CVTSL2SD AX,X0", "CVTSL2SD", []Operand{AX, vreg(t, "X0")}, "f20f2ac0", "CVTSI2SD"},
 		{"CVTSQ2SD R8,X13", "CVTSQ2SD", []Operand{r8, vreg(t, "X13")}, "f24d0f2ae8", "CVTSI2SD"},

asm/instrs.go

@@ -839,14 +839,23 @@ func (e *enc) encodeBswap(ops []Operand, size int) error {
 // convention does not apply to these names.
 var movExtendOp = map[string]struct {
 	op      []byte
-	dst64 bool
+	dstSize int
 }{
-	"MOVBLZX": {[]byte{0x0F, 0xB6}, false}, // byte → long, zero-extend
+	"MOVBLZX": {[]byte{0x0F, 0xB6}, 4}, // byte → long, zero-extend
-	"MOVBQZX": {[]byte{0x0F, 0xB6}, true},  // byte → quad, zero-extend
+	"MOVBQZX": {[]byte{0x0F, 0xB6}, 8}, // byte → quad, zero-extend
-	"MOVWLZX": {[]byte{0x0F, 0xB7}, false}, // word → long, zero-extend
+	"MOVWLZX": {[]byte{0x0F, 0xB7}, 4}, // word → long, zero-extend
-	"MOVWQZX": {[]byte{0x0F, 0xB7}, true},  // word → quad, zero-extend
+	"MOVWQZX": {[]byte{0x0F, 0xB7}, 8}, // word → quad, zero-extend
-	"MOVWLSX": {[]byte{0x0F, 0xBF}, false}, // word → long, sign-extend
+	"MOVWLSX": {[]byte{0x0F, 0xBF}, 4}, // word → long, sign-extend
-	"MOVLQSX": {[]byte{0x63}, true},        // long → quad, sign-extend (MOVSXD)
+	"MOVLQSX": {[]byte{0x63}, 8},       // long → quad, sign-extend (MOVSXD)
+	"MOVBWZX": {[]byte{0x0F, 0xB6}, 2}, // byte → word, zero-extend
+	"MOVBWSX": {[]byte{0x0F, 0xBE}, 2}, // byte → word, sign-extend
+	"MOVBLSX": {[]byte{0x0F, 0xBE}, 4}, // byte → long, sign-extend
+	"MOVBQSX": {[]byte{0x0F, 0xBE}, 8}, // byte → quad, sign-extend
+	"MOVWQSX": {[]byte{0x0F, 0xBF}, 8}, // word → quad, sign-extend
+	// A long → quad zero-extend is a plain 32-bit move: every 32-bit
+	// operation zero-extends its result into the full register, so the
+	// toolchain lowers MOVLQZX to the plain MOVL encoding.
+	"MOVLQZX": {[]byte{0x8B}, 4},
 }
 
 // encodeMovExtend encodes a mixed-width extending move: reg = dst (the wider
@@ -860,12 +869,30 @@ func (e *enc) encodeMovExtend(base string, ops []Operand) error {
 	if !ok {
 		return fmt.Errorf("%s destination must be a register", base)
 	}
-	size := 4
+	i := newInstr(spec.dstSize, spec.op)
-	if spec.dst64 {
+	if err := setRM(i, dstReg, ops[0], spec.dstSize); err != nil {
-		size = 8
+		return err
 	}
-	i := newInstr(size, spec.op)
+	return e.emit(i)
-	if err := setRM(i, dstReg, ops[0], size); err != nil {
+}
+
+// encodePmovmskb encodes PMOVMSKB, the legacy SSE2 byte mask extract: the
+// XMM source's sign bytes pack into a GP destination, 66 0F D7 /r.
+func (e *enc) encodePmovmskb(base string, ops []Operand) error {
+	if len(ops) != 2 {
+		return fmt.Errorf("%s expects 2 operands, got %d", base, len(ops))
+	}
+	srcReg, srcVec := vecReg(ops[0])
+	if !srcVec {
+		return fmt.Errorf("%s source must be an XMM register", base)
+	}
+	dstReg, ok := ops[1].(Reg)
+	if !ok {
+		return fmt.Errorf("%s destination must be a register", base)
+	}
+	i := newInstr(4, []byte{0x0F, 0xD7})
+	i.prefix = 0x66
+	if err := setRM(i, dstReg, srcReg, 4); err != nil {
 		return err
 	}
 	return e.emit(i)

testdata/verify/widen_amd64.s

@@ -0,0 +1,39 @@
+// Mixed-width sign- and zero-extending moves plus PMOVMSKB, the spellings
+// GOROOT's runtime and bytealg kernels use.  Every result is folded back so
+// no instruction is dead.
+
+#include "textflag.h"
+
+// func widen(p *byte) uint64
+TEXT ·widen(SB), NOSPLIT, $0-16
+	MOVBQZX 0(DI), AX
+	MOVWQZX 2(DI), CX
+	ADDQ    CX, AX
+	MOVLQZX 4(DI), DX
+	ADDQ    DX, AX
+	MOVBQSX 8(DI), R8
+	ADDQ    R8, AX
+	MOVWQSX 12(DI), R9
+	ADDQ    R9, AX
+	MOVBLSX 16(DI), R10
+	ADDL    R10, AX
+	MOVLQSX 20(DI), R11
+	ADDQ    R11, AX
+	MOVQ    AX, ret+8(FP)
+	RET
+
+// func widenw(p *byte) int32
+TEXT ·widenw(SB), NOSPLIT, $0-16
+	MOVBWZX 0(DI), AX
+	MOVBWSX 1(DI), CX
+	ADDL    CX, AX
+	MOVLQZX AX, DX
+	MOVL    DX, ret+8(FP)
+	RET
+
+// func mask(x *XMM) int
+TEXT ·mask(SB), NOSPLIT, $0-16
+	MOVOU    0(DI), X1
+	PMOVMSKB X1, AX
+	MOVQ     AX, ret+8(FP)
+	RET