diff --git a/bochs/cpu/cpu.h b/bochs/cpu/cpu.h
index e278cc58f..5a3227475 100644
--- a/bochs/cpu/cpu.h
+++ b/bochs/cpu/cpu.h
@@ -1954,8 +1954,14 @@ public: // for now...
 #if BX_SUPPORT_AVX
   BX_SMF void LOAD_Vector(bxInstruction_c *) BX_CPP_AttrRegparmN(1);
   BX_SMF void LOAD_Half_Vector(bxInstruction_c *) BX_CPP_AttrRegparmN(1);
+  BX_SMF void LOAD_MASK_Half_VectorB(bxInstruction_c *) BX_CPP_AttrRegparmN(1);
+  BX_SMF void LOAD_MASK_Half_VectorW(bxInstruction_c *) BX_CPP_AttrRegparmN(1);
+  BX_SMF void LOAD_MASK_Half_VectorD(bxInstruction_c *) BX_CPP_AttrRegparmN(1);
   BX_SMF void LOAD_Quarter_Vector(bxInstruction_c *) BX_CPP_AttrRegparmN(1);
+  BX_SMF void LOAD_MASK_Quarter_VectorB(bxInstruction_c *) BX_CPP_AttrRegparmN(1);
+  BX_SMF void LOAD_MASK_Quarter_VectorW(bxInstruction_c *) BX_CPP_AttrRegparmN(1);
   BX_SMF void LOAD_Eighth_Vector(bxInstruction_c *) BX_CPP_AttrRegparmN(1);
+  BX_SMF void LOAD_MASK_Eighth_VectorB(bxInstruction_c *) BX_CPP_AttrRegparmN(1);
 #endif
 #if BX_SUPPORT_EVEX
   BX_SMF void LOAD_MASK_Wss(bxInstruction_c *i) BX_CPP_AttrRegparmN(1);
diff --git a/bochs/cpu/decoder/ia_opcodes.def b/bochs/cpu/decoder/ia_opcodes.def
index 27a213eb9..8983c050b 100644
--- a/bochs/cpu/decoder/ia_opcodes.def
+++ b/bochs/cpu/decoder/ia_opcodes.def
@@ -2936,7 +2936,7 @@ bx_define_opcode(BX_IA_V512_VCVTTPD2DQ_VdqWpd, "vcvttpd2dq", "vcvttpd2dq", &BX_C
 bx_define_opcode(BX_IA_V512_VCVTTPD2DQ_VdqWpd_Kmask, "vcvttpd2dq", "vcvttpd2dq", &BX_CPU_C::LOAD_BROADCAST_MASK_VectorQ, &BX_CPU_C::VCVTTPD2DQ_MASK_VdqWpdR, BX_ISA_AVX512, OP_Vdq, OP_mVpd, OP_NONE, OP_NONE, BX_PREPARE_EVEX)
 
 bx_define_opcode(BX_IA_V512_VCVTPH2PS_VpsWps, "vcvtph2ps", "vcvtph2ps", &BX_CPU_C::LOAD_Half_Vector, &BX_CPU_C::VCVTPH2PS_VpsWpsR, BX_ISA_AVX512, OP_Vps, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_BROADCAST)
-bx_define_opcode(BX_IA_V512_VCVTPH2PS_VpsWps_Kmask, "vcvtph2ps", "vcvtph2ps", &BX_CPU_C::LOAD_Half_Vector, &BX_CPU_C::VCVTPH2PS_MASK_VpsWpsR, BX_ISA_AVX512, OP_Vps, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_BROADCAST)
+bx_define_opcode(BX_IA_V512_VCVTPH2PS_VpsWps_Kmask, "vcvtph2ps", "vcvtph2ps", &BX_CPU_C::LOAD_MASK_Half_VectorW, &BX_CPU_C::VCVTPH2PS_MASK_VpsWpsR, BX_ISA_AVX512, OP_Vps, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_BROADCAST)
 
 bx_define_opcode(BX_IA_V512_VCVTPS2PH_WpsVpsIb, "vcvtps2ph", "vcvtps2ph", &BX_CPU_C::VCVTPS2PH_WpsVpsIb, &BX_CPU_C::VCVTPS2PH_WpsVpsIb, BX_ISA_AVX512, OP_mVHV, OP_Vps, OP_Ib, OP_NONE, BX_PREPARE_EVEX_NO_BROADCAST)
 bx_define_opcode(BX_IA_V512_VCVTPS2PH_WpsVpsIb_Kmask, "vcvtps2ph", "vcvtps2ph", &BX_CPU_C::VCVTPS2PH_MASK_WpsVpsIbM, &BX_CPU_C::VCVTPS2PH_MASK_WpsVpsIbR, BX_ISA_AVX512, OP_mVHV, OP_Vps, OP_Ib, OP_NONE, BX_PREPARE_EVEX_NO_BROADCAST)
@@ -3168,12 +3168,12 @@ bx_define_opcode(BX_IA_V512_VPMOVSXWD_VdqWdq, "vpmovsxwd", "vpmovsxwd", &BX_CPU_
 bx_define_opcode(BX_IA_V512_VPMOVSXWQ_VdqWdq, "vpmovsxwq", "vpmovsxwq", &BX_CPU_C::LOAD_Quarter_Vector, &BX_CPU_C::VPMOVSXWQ_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVQV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
 bx_define_opcode(BX_IA_V512_VPMOVSXDQ_VdqWdq, "vpmovsxdq", "vpmovsxdq", &BX_CPU_C::LOAD_Half_Vector, &BX_CPU_C::VPMOVSXDQ_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
 
-bx_define_opcode(BX_IA_V512_VPMOVSXBW_VdqWdq_Kmask, "vpmovsxbw", "vpmovsxbw", &BX_CPU_C::LOAD_Half_Vector, &BX_CPU_C::VPMOVSXBW_MASK_VdqWdqR, BX_ISA_AVX512_BW, OP_Vdq, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
-bx_define_opcode(BX_IA_V512_VPMOVSXBD_VdqWdq_Kmask, "vpmovsxbd", "vpmovsxbd", &BX_CPU_C::LOAD_Quarter_Vector, &BX_CPU_C::VPMOVSXBD_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVQV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
-bx_define_opcode(BX_IA_V512_VPMOVSXBQ_VdqWdq_Kmask, "vpmovsxbq", "vpmovsxbq", &BX_CPU_C::LOAD_Eighth_Vector, &BX_CPU_C::VPMOVSXBQ_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVOV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
-bx_define_opcode(BX_IA_V512_VPMOVSXWD_VdqWdq_Kmask, "vpmovsxwd", "vpmovsxwd", &BX_CPU_C::LOAD_Half_Vector, &BX_CPU_C::VPMOVSXWD_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
-bx_define_opcode(BX_IA_V512_VPMOVSXWQ_VdqWdq_Kmask, "vpmovsxwq", "vpmovsxwq", &BX_CPU_C::LOAD_Quarter_Vector, &BX_CPU_C::VPMOVSXWQ_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVQV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
-bx_define_opcode(BX_IA_V512_VPMOVSXDQ_VdqWdq_Kmask, "vpmovsxdq", "vpmovsxdq", &BX_CPU_C::LOAD_Half_Vector, &BX_CPU_C::VPMOVSXDQ_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
+bx_define_opcode(BX_IA_V512_VPMOVSXBW_VdqWdq_Kmask, "vpmovsxbw", "vpmovsxbw", &BX_CPU_C::LOAD_MASK_Half_VectorB, &BX_CPU_C::VPMOVSXBW_MASK_VdqWdqR, BX_ISA_AVX512_BW, OP_Vdq, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
+bx_define_opcode(BX_IA_V512_VPMOVSXBD_VdqWdq_Kmask, "vpmovsxbd", "vpmovsxbd", &BX_CPU_C::LOAD_MASK_Quarter_VectorB, &BX_CPU_C::VPMOVSXBD_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVQV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
+bx_define_opcode(BX_IA_V512_VPMOVSXBQ_VdqWdq_Kmask, "vpmovsxbq", "vpmovsxbq", &BX_CPU_C::LOAD_MASK_Eighth_VectorB, &BX_CPU_C::VPMOVSXBQ_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVOV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
+bx_define_opcode(BX_IA_V512_VPMOVSXWD_VdqWdq_Kmask, "vpmovsxwd", "vpmovsxwd", &BX_CPU_C::LOAD_MASK_Half_VectorW, &BX_CPU_C::VPMOVSXWD_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
+bx_define_opcode(BX_IA_V512_VPMOVSXWQ_VdqWdq_Kmask, "vpmovsxwq", "vpmovsxwq", &BX_CPU_C::LOAD_MASK_Quarter_VectorW, &BX_CPU_C::VPMOVSXWQ_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVQV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
+bx_define_opcode(BX_IA_V512_VPMOVSXDQ_VdqWdq_Kmask, "vpmovsxdq", "vpmovsxdq", &BX_CPU_C::LOAD_MASK_Half_VectorD, &BX_CPU_C::VPMOVSXDQ_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
 
 bx_define_opcode(BX_IA_V512_VPMOVZXBW_VdqWdq, "vpmovzxbw", "vpmovzxbw", &BX_CPU_C::LOAD_Half_Vector, &BX_CPU_C::VPMOVZXBW_VdqWdqR, BX_ISA_AVX512_BW, OP_Vdq, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
 bx_define_opcode(BX_IA_V512_VPMOVZXBD_VdqWdq, "vpmovzxbd", "vpmovzxbd", &BX_CPU_C::LOAD_Quarter_Vector, &BX_CPU_C::VPMOVZXBD_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVQV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
@@ -3182,12 +3182,12 @@ bx_define_opcode(BX_IA_V512_VPMOVZXWD_VdqWdq, "vpmovzxwd", "vpmovzxwd", &BX_CPU_
 bx_define_opcode(BX_IA_V512_VPMOVZXWQ_VdqWdq, "vpmovzxwq", "vpmovzxwq", &BX_CPU_C::LOAD_Quarter_Vector, &BX_CPU_C::VPMOVZXWQ_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVQV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
 bx_define_opcode(BX_IA_V512_VPMOVZXDQ_VdqWdq, "vpmovzxdq", "vpmovzxdq", &BX_CPU_C::LOAD_Half_Vector, &BX_CPU_C::VPMOVZXDQ_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
 
-bx_define_opcode(BX_IA_V512_VPMOVZXBW_VdqWdq_Kmask, "vpmovzxbw", "vpmovzxbw", &BX_CPU_C::LOAD_Half_Vector, &BX_CPU_C::VPMOVZXBW_MASK_VdqWdqR, BX_ISA_AVX512_BW, OP_Vdq, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
-bx_define_opcode(BX_IA_V512_VPMOVZXBD_VdqWdq_Kmask, "vpmovzxbd", "vpmovzxbd", &BX_CPU_C::LOAD_Quarter_Vector, &BX_CPU_C::VPMOVZXBD_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVQV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
-bx_define_opcode(BX_IA_V512_VPMOVZXBQ_VdqWdq_Kmask, "vpmovzxbq", "vpmovzxbq", &BX_CPU_C::LOAD_Eighth_Vector, &BX_CPU_C::VPMOVZXBQ_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVOV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
-bx_define_opcode(BX_IA_V512_VPMOVZXWD_VdqWdq_Kmask, "vpmovzxwd", "vpmovzxwd", &BX_CPU_C::LOAD_Half_Vector, &BX_CPU_C::VPMOVZXWD_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
-bx_define_opcode(BX_IA_V512_VPMOVZXWQ_VdqWdq_Kmask, "vpmovzxwq", "vpmovzxwq", &BX_CPU_C::LOAD_Quarter_Vector, &BX_CPU_C::VPMOVZXWQ_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVQV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
-bx_define_opcode(BX_IA_V512_VPMOVZXDQ_VdqWdq_Kmask, "vpmovzxdq", "vpmovzxdq", &BX_CPU_C::LOAD_Half_Vector, &BX_CPU_C::VPMOVZXDQ_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
+bx_define_opcode(BX_IA_V512_VPMOVZXBW_VdqWdq_Kmask, "vpmovzxbw", "vpmovzxbw", &BX_CPU_C::LOAD_MASK_Half_VectorB, &BX_CPU_C::VPMOVZXBW_MASK_VdqWdqR, BX_ISA_AVX512_BW, OP_Vdq, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
+bx_define_opcode(BX_IA_V512_VPMOVZXBD_VdqWdq_Kmask, "vpmovzxbd", "vpmovzxbd", &BX_CPU_C::LOAD_MASK_Quarter_VectorB, &BX_CPU_C::VPMOVZXBD_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVQV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
+bx_define_opcode(BX_IA_V512_VPMOVZXBQ_VdqWdq_Kmask, "vpmovzxbq", "vpmovzxbq", &BX_CPU_C::LOAD_MASK_Eighth_VectorB, &BX_CPU_C::VPMOVZXBQ_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVOV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
+bx_define_opcode(BX_IA_V512_VPMOVZXWD_VdqWdq_Kmask, "vpmovzxwd", "vpmovzxwd", &BX_CPU_C::LOAD_MASK_Half_VectorW, &BX_CPU_C::VPMOVZXWD_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
+bx_define_opcode(BX_IA_V512_VPMOVZXWQ_VdqWdq_Kmask, "vpmovzxwq", "vpmovzxwq", &BX_CPU_C::LOAD_MASK_Quarter_VectorW, &BX_CPU_C::VPMOVZXWQ_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVQV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
+bx_define_opcode(BX_IA_V512_VPMOVZXDQ_VdqWdq_Kmask, "vpmovzxdq", "vpmovzxdq", &BX_CPU_C::LOAD_MASK_Half_VectorD, &BX_CPU_C::VPMOVZXDQ_MASK_VdqWdqR, BX_ISA_AVX512, OP_Vdq, OP_mVHV, OP_NONE, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
 
 bx_define_opcode(BX_IA_V512_VPSUBB_VdqHdqWdq, "vpsubb", "vpsubb", &BX_CPU_C::LOAD_Vector, &BX_CPU_C::VPSUBB_VdqHdqWdqR, BX_ISA_AVX512_BW, OP_Vdq, OP_Hdq, OP_mVdq, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
 bx_define_opcode(BX_IA_V512_VPSUBSB_VdqHdqWdq, "vpsubsb", "vpsubsb", &BX_CPU_C::LOAD_Vector, &BX_CPU_C::VPSUBSB_VdqHdqWdqR, BX_ISA_AVX512_BW, OP_Vdq, OP_Hdq, OP_mVdq, OP_NONE, BX_PREPARE_EVEX_NO_SAE | BX_PREPARE_EVEX_NO_BROADCAST)
diff --git a/bochs/cpu/load.cc b/bochs/cpu/load.cc
index b00b4a824..3212af05c 100644
--- a/bochs/cpu/load.cc
+++ b/bochs/cpu/load.cc
@@ -201,6 +201,57 @@ void BX_CPP_AttrRegparmN(1) BX_CPU_C::LOAD_Half_Vector(bxInstruction_c *i)
   BX_CPU_CALL_METHOD(i->execute2(), (i));
 }
 
+void BX_CPP_AttrRegparmN(1) BX_CPU_C::LOAD_MASK_Half_VectorB(bxInstruction_c *i)
+{
+  Bit32u opmask = (i->opmask() != 0) ? BX_READ_32BIT_OPMASK(i->opmask()) : 0xffffffff;
+  unsigned len = i->getVL();
+  opmask &= CUT_OPMASK_TO(BYTE_ELEMENTS(len));
+
+  if (opmask == 0) {
+    BX_CPU_CALL_METHOD(i->execute2(), (i)); // for now let execute method to deal with zero/merge masking semantics
+    return;
+  }
+
+  bx_address eaddr = BX_CPU_RESOLVE_ADDR(i);
+  avx_masked_load8(i, eaddr, &BX_READ_AVX_REG(BX_VECTOR_TMP_REGISTER), opmask);
+
+  BX_CPU_CALL_METHOD(i->execute2(), (i));
+}
+
+void BX_CPP_AttrRegparmN(1) BX_CPU_C::LOAD_MASK_Half_VectorW(bxInstruction_c *i)
+{
+  Bit32u opmask = (i->opmask() != 0) ? BX_READ_16BIT_OPMASK(i->opmask()) : 0xffff;
+  unsigned len = i->getVL();
+  opmask &= CUT_OPMASK_TO(WORD_ELEMENTS(len));
+
+  if (opmask == 0) {
+    BX_CPU_CALL_METHOD(i->execute2(), (i)); // for now let execute method to deal with zero/merge masking semantics
+    return;
+  }
+
+  bx_address eaddr = BX_CPU_RESOLVE_ADDR(i);
+  avx_masked_load16(i, eaddr, &BX_READ_AVX_REG(BX_VECTOR_TMP_REGISTER), opmask);
+
+  BX_CPU_CALL_METHOD(i->execute2(), (i));
+}
+
+void BX_CPP_AttrRegparmN(1) BX_CPU_C::LOAD_MASK_Half_VectorD(bxInstruction_c *i)
+{
+  Bit32u opmask = (i->opmask() != 0) ? BX_READ_8BIT_OPMASK(i->opmask()) : 0xff;
+  unsigned len = i->getVL();
+  opmask &= CUT_OPMASK_TO(DWORD_ELEMENTS(len));
+
+  if (opmask == 0) {
+    BX_CPU_CALL_METHOD(i->execute2(), (i)); // for now let execute method to deal with zero/merge masking semantics
+    return;
+  }
+
+  bx_address eaddr = BX_CPU_RESOLVE_ADDR(i);
+  avx_masked_load32(i, eaddr, &BX_READ_AVX_REG(BX_VECTOR_TMP_REGISTER), opmask);
+
+  BX_CPU_CALL_METHOD(i->execute2(), (i));
+}
+
 void BX_CPP_AttrRegparmN(1) BX_CPU_C::LOAD_Quarter_Vector(bxInstruction_c *i)
 {
   bx_address eaddr = BX_CPU_RESOLVE_ADDR(i);
@@ -226,6 +277,40 @@ void BX_CPP_AttrRegparmN(1) BX_CPU_C::LOAD_Quarter_Vector(bxInstruction_c *i)
   BX_CPU_CALL_METHOD(i->execute2(), (i));
 }
 
+void BX_CPP_AttrRegparmN(1) BX_CPU_C::LOAD_MASK_Quarter_VectorB(bxInstruction_c *i)
+{
+  Bit32u opmask = (i->opmask() != 0) ? BX_READ_16BIT_OPMASK(i->opmask()) : 0xffff;
+  unsigned len = i->getVL();
+  opmask &= CUT_OPMASK_TO(WORD_ELEMENTS(len));
+
+  if (opmask == 0) {
+    BX_CPU_CALL_METHOD(i->execute2(), (i)); // for now let execute method to deal with zero/merge masking semantics
+    return;
+  }
+
+  bx_address eaddr = BX_CPU_RESOLVE_ADDR(i);
+  avx_masked_load8(i, eaddr, &BX_READ_AVX_REG(BX_VECTOR_TMP_REGISTER), opmask);
+
+  BX_CPU_CALL_METHOD(i->execute2(), (i));
+}
+
+void BX_CPP_AttrRegparmN(1) BX_CPU_C::LOAD_MASK_Quarter_VectorW(bxInstruction_c *i)
+{
+  Bit32u opmask = (i->opmask() != 0) ? BX_READ_8BIT_OPMASK(i->opmask()) : 0xff;
+  unsigned len = i->getVL();
+  opmask &= CUT_OPMASK_TO(DWORD_ELEMENTS(len));
+
+  if (opmask == 0) {
+    BX_CPU_CALL_METHOD(i->execute2(), (i)); // for now let execute method to deal with zero/merge masking semantics
+    return;
+  }
+
+  bx_address eaddr = BX_CPU_RESOLVE_ADDR(i);
+  avx_masked_load16(i, eaddr, &BX_READ_AVX_REG(BX_VECTOR_TMP_REGISTER), opmask);
+
+  BX_CPU_CALL_METHOD(i->execute2(), (i));
+}
+
 void BX_CPP_AttrRegparmN(1) BX_CPU_C::LOAD_Eighth_Vector(bxInstruction_c *i)
 {
   bx_address eaddr = BX_CPU_RESOLVE_ADDR(i);
@@ -252,6 +337,23 @@ void BX_CPP_AttrRegparmN(1) BX_CPU_C::LOAD_Eighth_Vector(bxInstruction_c *i)
   BX_CPU_CALL_METHOD(i->execute2(), (i));
 }
 
+void BX_CPP_AttrRegparmN(1) BX_CPU_C::LOAD_MASK_Eighth_VectorB(bxInstruction_c *i)
+{
+  Bit32u opmask = (i->opmask() != 0) ? BX_READ_8BIT_OPMASK(i->opmask()) : 0xff;
+  unsigned len = i->getVL();
+  opmask &= CUT_OPMASK_TO(QWORD_ELEMENTS(len));
+
+  if (opmask == 0) {
+    BX_CPU_CALL_METHOD(i->execute2(), (i)); // for now let execute method to deal with zero/merge masking semantics
+    return;
+  }
+
+  bx_address eaddr = BX_CPU_RESOLVE_ADDR(i);
+  avx_masked_load8(i, eaddr, &BX_READ_AVX_REG(BX_VECTOR_TMP_REGISTER), opmask);
+
+  BX_CPU_CALL_METHOD(i->execute2(), (i));
+}
+
 #endif
 
 #if BX_SUPPORT_EVEX
@@ -445,9 +547,9 @@ void BX_CPP_AttrRegparmN(1) BX_CPU_C::LOAD_BROADCAST_Half_VectorD(bxInstruction_
 // load half vector of dwords, support broadcast and masked fault suppression
 void BX_CPP_AttrRegparmN(1) BX_CPU_C::LOAD_BROADCAST_MASK_Half_VectorD(bxInstruction_c *i)
 {
+  Bit32u opmask = (i->opmask() != 0) ? BX_READ_8BIT_OPMASK(i->opmask()) : 0xff;
   unsigned len = i->getVL();
-  Bit32u opmask = (i->opmask() != 0) ? BX_READ_16BIT_OPMASK(i->opmask()) : 0xffff;
-  opmask &= CUT_OPMASK_TO(DWORD_ELEMENTS(len)-1);
+  opmask &= CUT_OPMASK_TO(QWORD_ELEMENTS(len));
 
   if (opmask == 0) {
     BX_CPU_CALL_METHOD(i->execute2(), (i)); // for now let execute method to deal with zero/merge masking semantics