@@ -458,6 +458,13 @@ static const struct test avx512bw_128[]
INSN(pinsrw, 66, 0f, c4, el, w, el),
};
+static const struct test avx512cd_all[] = {
+// pbroadcastmb2q, f3, 0f38, 2a, q
+// pbroadcastmw2d, f3, 0f38, 3a, d
+ INSN(pconflict, 66, 0f38, c4, vl, dq, vl),
+ INSN(plzcnt, 66, 0f38, 44, vl, dq, vl),
+};
+
static const struct test avx512dq_all[] = {
INSN_PFP(and, 0f, 54),
INSN_PFP(andn, 0f, 55),
@@ -903,6 +910,7 @@ void evex_disp8_test(void *instr, struct
RUN(avx512f, 512);
RUN(avx512bw, all);
RUN(avx512bw, 128);
+ RUN(avx512cd, all);
RUN(avx512dq, all);
RUN(avx512dq, 128);
RUN(avx512dq, no128);
@@ -138,6 +138,7 @@ static inline bool xcr0_mask(uint64_t ma
#define cpu_has_avx512f (cp.feat.avx512f && xcr0_mask(0xe6))
#define cpu_has_avx512dq (cp.feat.avx512dq && xcr0_mask(0xe6))
#define cpu_has_avx512er (cp.feat.avx512er && xcr0_mask(0xe6))
+#define cpu_has_avx512cd (cp.feat.avx512cd && xcr0_mask(0xe6))
#define cpu_has_avx512bw (cp.feat.avx512bw && xcr0_mask(0xe6))
#define cpu_has_avx512vl (cp.feat.avx512vl && xcr0_mask(0xe6))
#define cpu_has_avx512_vbmi (cp.feat.avx512_vbmi && xcr0_mask(0xe6))
@@ -473,6 +473,7 @@ static const struct ext0f38_table {
[0x41] = { .simd_size = simd_packed_int, .two_op = 1 },
[0x42] = { .simd_size = simd_packed_fp, .two_op = 1, .d8s = d8s_vl },
[0x43] = { .simd_size = simd_scalar_vexw, .d8s = d8s_dq },
+ [0x44] = { .simd_size = simd_packed_int, .two_op = 1, .d8s = d8s_vl },
[0x45 ... 0x47] = { .simd_size = simd_packed_int, .d8s = d8s_vl },
[0x4c] = { .simd_size = simd_packed_fp, .two_op = 1, .d8s = d8s_vl },
[0x4d] = { .simd_size = simd_scalar_vexw, .d8s = d8s_dq },
@@ -525,6 +526,7 @@ static const struct ext0f38_table {
[0xbd] = { .simd_size = simd_scalar_vexw, .d8s = d8s_dq },
[0xbe] = { .simd_size = simd_packed_fp, .d8s = d8s_vl },
[0xbf] = { .simd_size = simd_scalar_vexw, .d8s = d8s_dq },
+ [0xc4] = { .simd_size = simd_packed_int, .two_op = 1, .d8s = d8s_vl },
[0xc6 ... 0xc7] = { .simd_size = simd_other, .vsib = 1, .d8s = d8s_dq },
[0xc8] = { .simd_size = simd_packed_fp, .two_op = 1, .d8s = d8s_vl },
[0xc9] = { .simd_size = simd_other },
@@ -1874,6 +1876,7 @@ in_protmode(
#define vcpu_has_clwb() (ctxt->cpuid->feat.clwb)
#define vcpu_has_avx512pf() (ctxt->cpuid->feat.avx512pf)
#define vcpu_has_avx512er() (ctxt->cpuid->feat.avx512er)
+#define vcpu_has_avx512cd() (ctxt->cpuid->feat.avx512cd)
#define vcpu_has_sha() (ctxt->cpuid->feat.sha)
#define vcpu_has_avx512bw() (ctxt->cpuid->feat.avx512bw)
#define vcpu_has_avx512vl() (ctxt->cpuid->feat.avx512vl)
@@ -8792,6 +8795,20 @@ x86_emulate(
evex.opcx = vex_0f;
goto vmovdqa;
+ case X86EMUL_OPC_EVEX_F3(0x0f38, 0x2a): /* vpbroadcastmb2q k,[xyz]mm */
+ case X86EMUL_OPC_EVEX_F3(0x0f38, 0x3a): /* vpbroadcastmw2d k,[xyz]mm */
+ generate_exception_if((ea.type != OP_REG || evex.opmsk ||
+ evex.w == ((b >> 4) & 1)),
+ EXC_UD);
+ d |= TwoOp;
+ /* fall through */
+ case X86EMUL_OPC_EVEX_66(0x0f38, 0xc4): /* vpconflict{d,q} [xyz]mm/mem,[xyz]mm{k} */
+ fault_suppression = false;
+ /* fall through */
+ case X86EMUL_OPC_EVEX_66(0x0f38, 0x44): /* vplzcnt{d,q} [xyz]mm/mem,[xyz]mm{k} */
+ host_and_vcpu_must_have(avx512cd);
+ goto avx512f_no_sae;
+
case X86EMUL_OPC_VEX_66(0x0f38, 0x2c): /* vmaskmovps mem,{x,y}mm,{x,y}mm */
case X86EMUL_OPC_VEX_66(0x0f38, 0x2d): /* vmaskmovpd mem,{x,y}mm,{x,y}mm */
case X86EMUL_OPC_VEX_66(0x0f38, 0x2e): /* vmaskmovps {x,y}mm,{x,y}mm,mem */
@@ -102,6 +102,7 @@
#define cpu_has_rdseed boot_cpu_has(X86_FEATURE_RDSEED)
#define cpu_has_smap boot_cpu_has(X86_FEATURE_SMAP)
#define cpu_has_avx512er boot_cpu_has(X86_FEATURE_AVX512ER)
+#define cpu_has_avx512cd boot_cpu_has(X86_FEATURE_AVX512CD)
#define cpu_has_sha boot_cpu_has(X86_FEATURE_SHA)
#define cpu_has_avx512bw boot_cpu_has(X86_FEATURE_AVX512BW)
#define cpu_has_avx512vl boot_cpu_has(X86_FEATURE_AVX512VL)