feat(debug): add YMM vector register display via PTRACE_GETFPREGS

Assisted-by: DeepSeek V4 Pro

debug/repl.go

@@ -78,6 +78,13 @@ func REPL(s *Session, bm *Breakpoints, codeBase uint64, funcOffset, funcSize, ar
 				continue
 			}
 			printRegs(&regs, codeBase, uint64(funcOffset))
+			// Also show vector registers.
+			vregs, err := s.GetVectorRegs()
+			if err != nil {
+				fmt.Printf("  (vector regs unavailable: %v)\n", err)
+			} else {
+				printVectorRegs(&vregs)
+			}
 
 		case "step", "s":
 			n := 1
@@ -508,6 +515,26 @@ func printRegs(regs *Regs, codeBase, funcOff uint64) {
 	fmt.Printf("  RFLAGS = %#x  [%s]\n", regs.RFLAGS, decodeRflags(regs.RFLAGS))
 }
 
+// printVectorRegs displays the YMM registers.
+func printVectorRegs(v *VectorRegs) {
+	fmt.Println("\n  Vector registers (YMM):")
+	for i := 0; i < 16; i += 2 {
+		fmt.Printf("  YMM%-2d = ", i)
+		printYMM(v.YMM[i][:])
+		fmt.Printf("  YMM%-2d = ", i+1)
+		printYMM(v.YMM[i+1][:])
+		fmt.Println()
+	}
+}
+
+func printYMM(b []byte) {
+	// Show as 8 32-bit values.
+	for j := 0; j < 32; j += 4 {
+		v := uint32(b[j]) | uint32(b[j+1])<<8 | uint32(b[j+2])<<16 | uint32(b[j+3])<<24
+		fmt.Printf("%08x ", v)
+	}
+}
+
 func decodeRflags(f uint64) string {
 	var flags string
 	if f&1 != 0 {