For more details about these instructions, please refer to the latest ISE document: https://www.intel.com/content/www/us/en/develop/download/intel-architecture-instruction-set-extensions-programming-reference.html
Reviewed By: pengfei
Differential Revision: https://reviews.llvm.org/D135930
* Support intrinsic of ``_mm(256)_dpbssd(s)_epi32``.
* Support intrinsic of ``_mm(256)_dpbsud(s)_epi32``.
* Support intrinsic of ``_mm(256)_dpbuud(s)_epi32``.
+- Support ISA of ``AVX-NE-CONVERT``.
+ * Support intrinsic of ``_mm(256)_bcstnebf16_ps``.
+ * Support intrinsic of ``_mm(256)_bcstnesh_ps``.
+ * Support intrinsic of ``_mm(256)_cvtneebf16_ps``.
+ * Support intrinsic of ``_mm(256)_cvtneeph_ps``.
+ * Support intrinsic of ``_mm(256)_cvtneobf16_ps``.
+ * Support intrinsic of ``_mm(256)_cvtneoph_ps``.
+ * Support intrinsic of ``_mm(256)_cvtneps_avx_pbh``.
WebAssembly Support in Clang
----------------------------
TARGET_HEADER_BUILTIN(__readgsdword, "UNiUNi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
TARGET_HEADER_BUILTIN(__readgsqword, "ULLiUNi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
+// AVX-NE-CONVERT
+TARGET_BUILTIN(__builtin_ia32_vbcstnebf162ps128, "V4fyC*", "nV:128:", "avxneconvert")
+TARGET_BUILTIN(__builtin_ia32_vbcstnebf162ps256, "V8fyC*", "nV:256:", "avxneconvert")
+TARGET_BUILTIN(__builtin_ia32_vbcstnesh2ps128, "V4fxC*", "nV:128:", "avxneconvert")
+TARGET_BUILTIN(__builtin_ia32_vbcstnesh2ps256, "V8fxC*", "nV:256:", "avxneconvert")
+TARGET_BUILTIN(__builtin_ia32_vcvtneebf162ps128, "V4fV8yC*", "nV:128:", "avxneconvert")
+TARGET_BUILTIN(__builtin_ia32_vcvtneebf162ps256, "V8fV16yC*", "nV:256:", "avxneconvert")
+TARGET_BUILTIN(__builtin_ia32_vcvtneeph2ps128, "V4fV8xC*", "nV:128:", "avxneconvert")
+TARGET_BUILTIN(__builtin_ia32_vcvtneeph2ps256, "V8fV16xC*", "nV:256:", "avxneconvert")
+TARGET_BUILTIN(__builtin_ia32_vcvtneobf162ps128, "V4fV8yC*", "nV:128:", "avxneconvert")
+TARGET_BUILTIN(__builtin_ia32_vcvtneobf162ps256, "V8fV16yC*", "nV:256:", "avxneconvert")
+TARGET_BUILTIN(__builtin_ia32_vcvtneoph2ps128, "V4fV8xC*", "nV:128:", "avxneconvert")
+TARGET_BUILTIN(__builtin_ia32_vcvtneoph2ps256, "V8fV16xC*", "nV:256:", "avxneconvert")
+TARGET_BUILTIN(__builtin_ia32_vcvtneps2bf16128, "V8yV4f", "nV:128:", "avx512bf16,avx512vl|avxneconvert")
+TARGET_BUILTIN(__builtin_ia32_vcvtneps2bf16256, "V8yV8f", "nV:256:", "avx512bf16,avx512vl|avxneconvert")
+
TARGET_HEADER_BUILTIN(_InterlockedAnd64, "WiWiD*Wi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
TARGET_HEADER_BUILTIN(_InterlockedDecrement64, "WiWiD*", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
TARGET_HEADER_BUILTIN(_InterlockedExchange64, "WiWiD*Wi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
def mno_avx512vp2intersect : Flag<["-"], "mno-avx512vp2intersect">, Group<m_x86_Features_Group>;
def mavxifma : Flag<["-"], "mavxifma">, Group<m_x86_Features_Group>;
def mno_avxifma : Flag<["-"], "mno-avxifma">, Group<m_x86_Features_Group>;
+def mavxneconvert : Flag<["-"], "mavxneconvert">, Group<m_x86_Features_Group>;
+def mno_avxneconvert : Flag<["-"], "mno-avxneconvert">, Group<m_x86_Features_Group>;
def mavxvnniint8 : Flag<["-"], "mavxvnniint8">, Group<m_x86_Features_Group>;
def mno_avxvnniint8 : Flag<["-"], "mno-avxvnniint8">, Group<m_x86_Features_Group>;
def mavxvnni : Flag<["-"], "mavxvnni">, Group<m_x86_Features_Group>;
HasRAOINT = true;
} else if (Feature == "+avxifma") {
HasAVXIFMA = true;
+ } else if (Feature == "+avxneconvert") {
+ HasAVXNECONVERT= true;
} else if (Feature == "+avxvnni") {
HasAVXVNNI = true;
} else if (Feature == "+avxvnniint8") {
Builder.defineMacro("__RAOINT__");
if (HasAVXIFMA)
Builder.defineMacro("__AVXIFMA__");
+ if (HasAVXNECONVERT)
+ Builder.defineMacro("__AVXNECONVERT__");
if (HasAVXVNNI)
Builder.defineMacro("__AVXVNNI__");
if (HasAVXVNNIINT8)
.Case("avx512ifma", true)
.Case("avx512vp2intersect", true)
.Case("avxifma", true)
+ .Case("avxneconvert", true)
.Case("avxvnni", true)
.Case("avxvnniint8", true)
.Case("bmi", true)
.Case("avx512ifma", HasAVX512IFMA)
.Case("avx512vp2intersect", HasAVX512VP2INTERSECT)
.Case("avxifma", HasAVXIFMA)
- .Case("avxvnni", HasAVXVNNI)
+ .Case("avxneconvert", HasAVXNECONVERT)
.Case("avxvnni", HasAVXVNNI)
.Case("avxvnniint8", HasAVXVNNIINT8)
.Case("bmi", HasBMI)
bool HasCMPCCXADD = false;
bool HasRAOINT = false;
bool HasAVXVNNIINT8 = false;
+ bool HasAVXNECONVERT = false;
bool HasKL = false; // For key locker
bool HasWIDEKL = false; // For wide key locker
bool HasHRESET = false;
avx512vpopcntdqvlintrin.h
avxifmaintrin.h
avxintrin.h
+ avxneconvertintrin.h
avxvnniint8intrin.h
avxvnniintrin.h
bmi2intrin.h
/// A 128-bit vector of [4 x float].
/// \returns A 128-bit vector of [8 x bfloat] whose lower 64 bits come from
/// conversion of __A, and higher 64 bits are 0.
-static __inline__ __m128bh __DEFAULT_FN_ATTRS128
-_mm_cvtneps_pbh(__m128 __A) {
- return (__m128bh)__builtin_ia32_cvtneps2bf16_128_mask((__v4sf) __A,
- (__v8bf)_mm_undefined_si128(),
- (__mmask8)-1);
-}
+#define _mm_cvtneps_pbh(A) \
+ ((__m128bh)__builtin_ia32_vcvtneps2bf16128((__v4sf)(A)))
/// Convert Packed Single Data to Packed BF16 Data.
///
/// \param __A
/// A 256-bit vector of [8 x float].
/// \returns A 128-bit vector of [8 x bfloat] comes from conversion of __A.
-static __inline__ __m128bh __DEFAULT_FN_ATTRS256
-_mm256_cvtneps_pbh(__m256 __A) {
- return (__m128bh)__builtin_ia32_cvtneps2bf16_256_mask((__v8sf)__A,
- (__v8bf)_mm_undefined_si128(),
- (__mmask8)-1);
-}
+#define _mm256_cvtneps_pbh(A) \
+ ((__m128bh)__builtin_ia32_vcvtneps2bf16256((__v8sf)(A)))
/// Convert Packed Single Data to Packed BF16 Data.
///
--- /dev/null
+/*===-------------- avxneconvertintrin.h - AVXNECONVERT --------------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===-----------------------------------------------------------------------===
+ */
+
+#ifndef __IMMINTRIN_H
+#error \
+ "Never use <avxneconvertintrin.h> directly; include <immintrin.h> instead."
+#endif // __IMMINTRIN_H
+
+#ifdef __SSE2__
+
+#ifndef __AVXNECONVERTINTRIN_H
+#define __AVXNECONVERTINTRIN_H
+
+/* Define the default attributes for the functions in this file. */
+#define __DEFAULT_FN_ATTRS128 \
+ __attribute__((__always_inline__, __nodebug__, __target__("avxneconvert"), \
+ __min_vector_width__(128)))
+#define __DEFAULT_FN_ATTRS256 \
+ __attribute__((__always_inline__, __nodebug__, __target__("avxneconvert"), \
+ __min_vector_width__(256)))
+
+/// Convert scalar BF16 (16-bit) floating-point element
+/// stored at memory locations starting at location \a __A to a
+/// single-precision (32-bit) floating-point, broadcast it to packed
+/// single-precision (32-bit) floating-point elements, and store the results in
+/// \a dst.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// _mm_bcstnebf16_ps(const void *__A);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c VBCSTNEBF162PS instruction.
+///
+/// \param __A
+/// A pointer to a 16-bit memory location. The address of the memory
+/// location does not have to be aligned.
+/// \returns
+/// A 128-bit vector of [4 x float].
+///
+/// \code{.operation}
+/// b := Convert_BF16_To_FP32(MEM[__A+15:__A])
+/// FOR j := 0 to 3
+/// m := j*32
+/// dst[m+31:m] := b
+/// ENDFOR
+/// dst[MAX:128] := 0
+/// \endcode
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_bcstnebf16_ps(const void *__A) {
+ return (__m128)__builtin_ia32_vbcstnebf162ps128((const __bf16 *)__A);
+}
+
+/// Convert scalar BF16 (16-bit) floating-point element
+/// stored at memory locations starting at location \a __A to a
+/// single-precision (32-bit) floating-point, broadcast it to packed
+/// single-precision (32-bit) floating-point elements, and store the results in
+/// \a dst.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// _mm256_bcstnebf16_ps(const void *__A);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c VBCSTNEBF162PS instruction.
+///
+/// \param __A
+/// A pointer to a 16-bit memory location. The address of the memory
+/// location does not have to be aligned.
+/// \returns
+/// A 256-bit vector of [8 x float].
+///
+/// \code{.operation}
+/// b := Convert_BF16_To_FP32(MEM[__A+15:__A])
+/// FOR j := 0 to 7
+/// m := j*32
+/// dst[m+31:m] := b
+/// ENDFOR
+/// dst[MAX:256] := 0
+/// \endcode
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_bcstnebf16_ps(const void *__A) {
+ return (__m256)__builtin_ia32_vbcstnebf162ps256((const __bf16 *)__A);
+}
+
+/// Convert scalar half-precision (16-bit) floating-point element
+/// stored at memory locations starting at location \a __A to a
+/// single-precision (32-bit) floating-point, broadcast it to packed
+/// single-precision (32-bit) floating-point elements, and store the results in
+/// \a dst.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// _mm_bcstnesh_ps(const void *__A);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c VBCSTNESH2PS instruction.
+///
+/// \param __A
+/// A pointer to a 16-bit memory location. The address of the memory
+/// location does not have to be aligned.
+/// \returns
+/// A 128-bit vector of [4 x float].
+///
+/// \code{.operation}
+/// b := Convert_FP16_To_FP32(MEM[__A+15:__A])
+/// FOR j := 0 to 3
+/// m := j*32
+/// dst[m+31:m] := b
+/// ENDFOR
+/// dst[MAX:128] := 0
+/// \endcode
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_bcstnesh_ps(const void *__A) {
+ return (__m128)__builtin_ia32_vbcstnesh2ps128((const _Float16 *)__A);
+}
+
+/// Convert scalar half-precision (16-bit) floating-point element
+/// stored at memory locations starting at location \a __A to a
+/// single-precision (32-bit) floating-point, broadcast it to packed
+/// single-precision (32-bit) floating-point elements, and store the results in
+/// \a dst.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// _mm256_bcstnesh_ps(const void *__A);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c VBCSTNESH2PS instruction.
+///
+/// \param __A
+/// A pointer to a 16-bit memory location. The address of the memory
+/// location does not have to be aligned.
+/// \returns
+/// A 256-bit vector of [8 x float].
+///
+/// \code{.operation}
+/// b := Convert_FP16_To_FP32(MEM[__A+15:__A])
+/// FOR j := 0 to 7
+/// m := j*32
+/// dst[m+31:m] := b
+/// ENDFOR
+/// dst[MAX:256] := 0
+/// \endcode
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_bcstnesh_ps(const void *__A) {
+ return (__m256)__builtin_ia32_vbcstnesh2ps256((const _Float16 *)__A);
+}
+
+/// Convert packed BF16 (16-bit) floating-point even-indexed elements
+/// stored at memory locations starting at location \a __A to packed
+/// single-precision (32-bit) floating-point elements, and store the results in
+/// \a dst.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// _mm_cvtneebf16_ps(const __m128bh *__A);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c VCVTNEEBF162PS instruction.
+///
+/// \param __A
+/// A pointer to a 128-bit memory location containing 8 consecutive
+/// BF16 (16-bit) floating-point values.
+/// \returns
+/// A 128-bit vector of [4 x float].
+///
+/// \code{.operation}
+/// FOR j := 0 to 3
+/// k := j*2
+/// i := k*16
+/// m := j*32
+/// dst[m+31:m] := Convert_BF16_To_FP32(MEM[__A+i+15:__A+i])
+/// ENDFOR
+/// dst[MAX:128] := 0
+/// \endcode
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_cvtneebf16_ps(const __m128bh *__A) {
+ return (__m128)__builtin_ia32_vcvtneebf162ps128((const __v8bf *)__A);
+}
+
+/// Convert packed BF16 (16-bit) floating-point even-indexed elements
+/// stored at memory locations starting at location \a __A to packed
+/// single-precision (32-bit) floating-point elements, and store the results in
+/// \a dst.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// _mm256_cvtneebf16_ps(const __m256bh *__A);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c VCVTNEEBF162PS instruction.
+///
+/// \param __A
+/// A pointer to a 256-bit memory location containing 16 consecutive
+/// BF16 (16-bit) floating-point values.
+/// \returns
+/// A 256-bit vector of [8 x float].
+///
+/// \code{.operation}
+/// FOR j := 0 to 7
+/// k := j*2
+/// i := k*16
+/// m := j*32
+/// dst[m+31:m] := Convert_BF16_To_FP32(MEM[__A+i+15:__A+i])
+/// ENDFOR
+/// dst[MAX:256] := 0
+/// \endcode
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_cvtneebf16_ps(const __m256bh *__A) {
+ return (__m256)__builtin_ia32_vcvtneebf162ps256((const __v16bf *)__A);
+}
+
+/// Convert packed half-precision (16-bit) floating-point even-indexed elements
+/// stored at memory locations starting at location \a __A to packed
+/// single-precision (32-bit) floating-point elements, and store the results in
+/// \a dst.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// _mm_cvtneeph_ps(const __m128h *__A);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c VCVTNEEPH2PS instruction.
+///
+/// \param __A
+/// A pointer to a 128-bit memory location containing 8 consecutive
+/// half-precision (16-bit) floating-point values.
+/// \returns
+/// A 128-bit vector of [4 x float].
+///
+/// \code{.operation}
+/// FOR j := 0 to 3
+/// k := j*2
+/// i := k*16
+/// m := j*32
+/// dst[m+31:m] := Convert_FP16_To_FP32(MEM[__A+i+15:__A+i])
+/// ENDFOR
+/// dst[MAX:128] := 0
+/// \endcode
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_cvtneeph_ps(const __m128h *__A) {
+ return (__m128)__builtin_ia32_vcvtneeph2ps128((const __v8hf *)__A);
+}
+
+/// Convert packed half-precision (16-bit) floating-point even-indexed elements
+/// stored at memory locations starting at location \a __A to packed
+/// single-precision (32-bit) floating-point elements, and store the results in
+/// \a dst.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// _mm256_cvtneeph_ps(const __m256h *__A);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c VCVTNEEPH2PS instruction.
+///
+/// \param __A
+/// A pointer to a 256-bit memory location containing 16 consecutive
+/// half-precision (16-bit) floating-point values.
+/// \returns
+/// A 256-bit vector of [8 x float].
+///
+/// \code{.operation}
+/// FOR j := 0 to 7
+/// k := j*2
+/// i := k*16
+/// m := j*32
+/// dst[m+31:m] := Convert_FP16_To_FP32(MEM[__A+i+15:__A+i])
+/// ENDFOR
+/// dst[MAX:256] := 0
+/// \endcode
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_cvtneeph_ps(const __m256h *__A) {
+ return (__m256)__builtin_ia32_vcvtneeph2ps256((const __v16hf *)__A);
+}
+
+/// Convert packed BF16 (16-bit) floating-point odd-indexed elements
+/// stored at memory locations starting at location \a __A to packed
+/// single-precision (32-bit) floating-point elements, and store the results in
+/// \a dst.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// _mm_cvtneobf16_ps(const __m128bh *__A);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c VCVTNEOBF162PS instruction.
+///
+/// \param __A
+/// A pointer to a 128-bit memory location containing 8 consecutive
+/// BF16 (16-bit) floating-point values.
+/// \returns
+/// A 128-bit vector of [4 x float].
+///
+/// \code{.operation}
+/// FOR j := 0 to 3
+/// k := j*2+1
+/// i := k*16
+/// m := j*32
+/// dst[m+31:m] := Convert_BF16_To_FP32(MEM[__A+i+15:__A+i])
+/// ENDFOR
+/// dst[MAX:128] := 0
+/// \endcode
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_cvtneobf16_ps(const __m128bh *__A) {
+ return (__m128)__builtin_ia32_vcvtneobf162ps128((const __v8bf *)__A);
+}
+
+/// Convert packed BF16 (16-bit) floating-point odd-indexed elements
+/// stored at memory locations starting at location \a __A to packed
+/// single-precision (32-bit) floating-point elements, and store the results in
+/// \a dst.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// _mm256_cvtneobf16_ps(const __m256bh *__A);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c VCVTNEOBF162PS instruction.
+///
+/// \param __A
+/// A pointer to a 256-bit memory location containing 16 consecutive
+/// BF16 (16-bit) floating-point values.
+/// \returns
+/// A 256-bit vector of [8 x float].
+///
+/// \code{.operation}
+/// FOR j := 0 to 7
+/// k := j*2+1
+/// i := k*16
+/// m := j*32
+/// dst[m+31:m] := Convert_BF16_To_FP32(MEM[__A+i+15:__A+i])
+/// ENDFOR
+/// dst[MAX:256] := 0
+/// \endcode
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_cvtneobf16_ps(const __m256bh *__A) {
+ return (__m256)__builtin_ia32_vcvtneobf162ps256((const __v16bf *)__A);
+}
+
+/// Convert packed half-precision (16-bit) floating-point odd-indexed elements
+/// stored at memory locations starting at location \a __A to packed
+/// single-precision (32-bit) floating-point elements, and store the results in
+/// \a dst.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// _mm_cvtneoph_ps(const __m128h *__A);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c VCVTNEOPH2PS instruction.
+///
+/// \param __A
+/// A pointer to a 128-bit memory location containing 8 consecutive
+/// half-precision (16-bit) floating-point values.
+/// \returns
+/// A 128-bit vector of [4 x float].
+///
+/// \code{.operation}
+/// FOR j := 0 to 3
+/// k := j*2+1
+/// i := k*16
+/// m := j*32
+/// dst[m+31:m] := Convert_FP16_To_FP32(MEM[__A+i+15:__A+i])
+/// ENDFOR
+/// dst[MAX:128] := 0
+/// \endcode
+static __inline__ __m128 __DEFAULT_FN_ATTRS128
+_mm_cvtneoph_ps(const __m128h *__A) {
+ return (__m128)__builtin_ia32_vcvtneoph2ps128((const __v8hf *)__A);
+}
+
+/// Convert packed half-precision (16-bit) floating-point odd-indexed elements
+/// stored at memory locations starting at location \a __A to packed
+/// single-precision (32-bit) floating-point elements, and store the results in
+/// \a dst.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// _mm256_cvtneoph_ps(const __m256h *__A);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c VCVTNEOPH2PS instruction.
+///
+/// \param __A
+/// A pointer to a 256-bit memory location containing 16 consecutive
+/// half-precision (16-bit) floating-point values.
+/// \returns
+/// A 256-bit vector of [8 x float].
+///
+/// \code{.operation}
+/// FOR j := 0 to 7
+/// k := j*2+1
+/// i := k*16
+/// m := j*32
+/// dst[m+31:m] := Convert_FP16_To_FP32(MEM[__A+i+15:__A+i])
+/// ENDFOR
+/// dst[MAX:256] := 0
+/// \endcode
+static __inline__ __m256 __DEFAULT_FN_ATTRS256
+_mm256_cvtneoph_ps(const __m256h *__A) {
+ return (__m256)__builtin_ia32_vcvtneoph2ps256((const __v16hf *)__A);
+}
+
+/// Convert packed single-precision (32-bit) floating-point elements in \a __A
+/// to packed BF16 (16-bit) floating-point elements, and store the results in \a
+/// dst.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// _mm_cvtneps_avx_pbh(__m128 __A);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c VCVTNEPS2BF16 instruction.
+///
+/// \param __A
+/// A 128-bit vector of [4 x float].
+/// \returns
+/// A 128-bit vector of [8 x bfloat].
+///
+/// \code{.operation}
+/// FOR j := 0 to 3
+/// dst.word[j] := Convert_FP32_To_BF16(__A.fp32[j])
+/// ENDFOR
+/// dst[MAX:128] := 0
+/// \endcode
+static __inline__ __m128bh __DEFAULT_FN_ATTRS128
+_mm_cvtneps_avx_pbh(__m128 __A) {
+ return (__m128bh)__builtin_ia32_vcvtneps2bf16128((__v4sf)__A);
+}
+
+/// Convert packed single-precision (32-bit) floating-point elements in \a __A
+/// to packed BF16 (16-bit) floating-point elements, and store the results in \a
+/// dst.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// _mm256_cvtneps_avx_pbh(__m256 __A);
+/// \endcode
+///
+/// This intrinsic corresponds to the \c VCVTNEPS2BF16 instruction.
+///
+/// \param __A
+/// A 256-bit vector of [8 x float].
+/// \returns
+/// A 128-bit vector of [8 x bfloat].
+///
+/// \code{.operation}
+/// FOR j := 0 to 7
+/// dst.word[j] := Convert_FP32_To_BF16(a.fp32[j])
+/// ENDFOR
+/// dst[MAX:128] := 0
+/// \endcode
+static __inline__ __m128bh __DEFAULT_FN_ATTRS256
+_mm256_cvtneps_avx_pbh(__m256 __A) {
+ return (__m128bh)__builtin_ia32_vcvtneps2bf16256((__v8sf)__A);
+}
+
+#undef __DEFAULT_FN_ATTRS128
+#undef __DEFAULT_FN_ATTRS256
+
+#endif // __AVXNECONVERTINTRIN_H
+#endif // __SSE2__
/* Features in %edx for leaf 7 sub-leaf 1 */
#define bit_AVXVNNIINT8 0x00000010
+#define bit_AVXNECONVERT 0x00000020
#define bit_PREFETCHI 0x00004000
/* Features in %eax for leaf 13 sub-leaf 1 */
#endif
#if !(defined(_MSC_VER) || defined(__SCE__)) || __has_feature(modules) || \
+ defined(__AVXNECONVERT__)
+#include <avxneconvertintrin.h>
+#endif
+
+#if !(defined(_MSC_VER) || defined(__SCE__)) || __has_feature(modules) || \
defined(__RDPID__)
/// Returns the value of the IA32_TSC_AUX MSR (0xc0000103).
///
__m128bh test_mm_cvtneps2bf16(__m128 A) {
// CHECK-LABEL: @test_mm_cvtneps2bf16
- // CHECK: @llvm.x86.avx512bf16.mask.cvtneps2bf16.128
+ // CHECK: @llvm.x86.vcvtneps2bf16128
// CHECK: ret <8 x bfloat> %{{.*}}
return _mm_cvtneps_pbh(A);
}
__m128bh test_mm256_cvtneps2bf16(__m256 A) {
// CHECK-LABEL: @test_mm256_cvtneps2bf16
- // CHECK: @llvm.x86.avx512bf16.cvtneps2bf16.256
+ // CHECK: @llvm.x86.vcvtneps2bf16256
// CHECK: ret <8 x bfloat> %{{.*}}
return _mm256_cvtneps_pbh(A);
}
--- /dev/null
+// RUN: %clang_cc1 %s -ffreestanding -triple=x86_64-unknown-unknown -target-feature +avx2 -target-feature +avxneconvert \
+// RUN: -emit-llvm -o - -Wall -Werror -pedantic -Wno-gnu-statement-expression | FileCheck %s
+// RUN: %clang_cc1 %s -ffreestanding -triple=i386-unknown-unknown -target-feature +avx2 -target-feature +avxneconvert \
+// RUN: -emit-llvm -o - -Wall -Werror -pedantic -Wno-gnu-statement-expression | FileCheck %s
+
+#include <immintrin.h>
+#include <stddef.h>
+
+__m128 test_mm_bcstnebf16_ps(const void *__A) {
+ // CHECK-LABEL: @test_mm_bcstnebf16_ps(
+ // CHECK: call <4 x float> @llvm.x86.vbcstnebf162ps128(ptr %{{.*}})
+ return _mm_bcstnebf16_ps(__A);
+}
+
+__m256 test_mm256_bcstnebf16_ps(const void *__A) {
+ // CHECK-LABEL: @test_mm256_bcstnebf16_ps(
+ // CHECK: call <8 x float> @llvm.x86.vbcstnebf162ps256(ptr %{{.*}})
+ return _mm256_bcstnebf16_ps(__A);
+}
+
+__m128 test_mm_bcstnesh_ps(const void *__A) {
+ // CHECK-LABEL: @test_mm_bcstnesh_ps(
+ // CHECK: call <4 x float> @llvm.x86.vbcstnesh2ps128(ptr %{{.*}})
+ return _mm_bcstnesh_ps(__A);
+}
+
+__m256 test_mm256_bcstnesh_ps(const void *__A) {
+ // CHECK-LABEL: @test_mm256_bcstnesh_ps(
+ // CHECK: call <8 x float> @llvm.x86.vbcstnesh2ps256(ptr %{{.*}})
+ return _mm256_bcstnesh_ps(__A);
+}
+
+__m128 test_mm_cvtneebf16_ps(const __m128bh *__A) {
+ // CHECK-LABEL: @test_mm_cvtneebf16_ps(
+ // CHECK: call <4 x float> @llvm.x86.vcvtneebf162ps128(ptr %{{.*}})
+ return _mm_cvtneebf16_ps(__A);
+}
+
+__m256 test_mm256_cvtneebf16_ps(const __m256bh *__A) {
+ // CHECK-LABEL: @test_mm256_cvtneebf16_ps(
+ // CHECK: call <8 x float> @llvm.x86.vcvtneebf162ps256(ptr %{{.*}})
+ return _mm256_cvtneebf16_ps(__A);
+}
+
+__m128 test_mm_cvtneeph_ps(const __m128h *__A) {
+ // CHECK-LABEL: @test_mm_cvtneeph_ps(
+ // CHECK: call <4 x float> @llvm.x86.vcvtneeph2ps128(ptr %{{.*}})
+ return _mm_cvtneeph_ps(__A);
+}
+
+__m256 test_mm256_cvtneeph_ps(const __m256h *__A) {
+ // CHECK-LABEL: @test_mm256_cvtneeph_ps(
+ // CHECK: call <8 x float> @llvm.x86.vcvtneeph2ps256(ptr %{{.*}})
+ return _mm256_cvtneeph_ps(__A);
+}
+
+__m128 test_mm_cvtneobf16_ps(const __m128bh *__A) {
+ // CHECK-LABEL: @test_mm_cvtneobf16_ps(
+ // CHECK: call <4 x float> @llvm.x86.vcvtneobf162ps128(ptr %{{.*}})
+ return _mm_cvtneobf16_ps(__A);
+}
+
+__m256 test_mm256_cvtneobf16_ps(const __m256bh *__A) {
+ // CHECK-LABEL: @test_mm256_cvtneobf16_ps(
+ // CHECK: call <8 x float> @llvm.x86.vcvtneobf162ps256(ptr %{{.*}})
+ return _mm256_cvtneobf16_ps(__A);
+}
+
+__m128 test_mm_cvtneoph_ps(const __m128h *__A) {
+ // CHECK-LABEL: @test_mm_cvtneoph_ps(
+ // CHECK: call <4 x float> @llvm.x86.vcvtneoph2ps128(ptr %{{.*}})
+ return _mm_cvtneoph_ps(__A);
+}
+
+__m256 test_mm256_cvtneoph_ps(const __m256h *__A) {
+ // CHECK-LABEL: @test_mm256_cvtneoph_ps(
+ // CHECK: call <8 x float> @llvm.x86.vcvtneoph2ps256(ptr %{{.*}})
+ return _mm256_cvtneoph_ps(__A);
+}
+
+__m128bh test_mm_cvtneps_avx_pbh(__m128 __A) {
+ // CHECK-LABEL: @test_mm_cvtneps_avx_pbh(
+ // CHECK: call <8 x bfloat> @llvm.x86.vcvtneps2bf16128(<4 x float> %{{.*}})
+ return _mm_cvtneps_avx_pbh(__A);
+}
+
+__m128bh test_mm256_cvtneps_avx_pbh(__m256 __A) {
+ // CHECK-LABEL: @test_mm256_cvtneps_avx_pbh(
+ // CHECK: call <8 x bfloat> @llvm.x86.vcvtneps2bf16256(<8 x float> %{{.*}})
+ return _mm256_cvtneps_avx_pbh(__A);
+}
// CHECK: #0 = {{.*}}"target-cpu"="i686" "target-features"="+cx8,+x87" "tune-cpu"="i686"
// CHECK: #1 = {{.*}}"target-cpu"="ivybridge" "target-features"="+avx,+crc32,+cx16,+cx8,+f16c,+fsgsbase,+fxsr,+mmx,+pclmul,+popcnt,+rdrnd,+sahf,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave,+xsaveopt"
// CHECK-NOT: tune-cpu
-// CHECK: #2 = {{.*}}"target-cpu"="i686" "target-features"="+cx8,+x87,-aes,-avx,-avx2,-avx512bf16,-avx512bitalg,-avx512bw,-avx512cd,-avx512dq,-avx512er,-avx512f,-avx512fp16,-avx512ifma,-avx512pf,-avx512vbmi,-avx512vbmi2,-avx512vl,-avx512vnni,-avx512vp2intersect,-avx512vpopcntdq,-avxifma,-avxvnni,-avxvnniint8,-f16c,-fma,-fma4,-gfni,-kl,-pclmul,-sha,-sse2,-sse3,-sse4.1,-sse4.2,-sse4a,-ssse3,-vaes,-vpclmulqdq,-widekl,-xop" "tune-cpu"="i686"
+// CHECK: #2 = {{.*}}"target-cpu"="i686" "target-features"="+cx8,+x87,-aes,-avx,-avx2,-avx512bf16,-avx512bitalg,-avx512bw,-avx512cd,-avx512dq,-avx512er,-avx512f,-avx512fp16,-avx512ifma,-avx512pf,-avx512vbmi,-avx512vbmi2,-avx512vl,-avx512vnni,-avx512vp2intersect,-avx512vpopcntdq,-avxifma,-avxneconvert,-avxvnni,-avxvnniint8,-f16c,-fma,-fma4,-gfni,-kl,-pclmul,-sha,-sse2,-sse3,-sse4.1,-sse4.2,-sse4a,-ssse3,-vaes,-vpclmulqdq,-widekl,-xop" "tune-cpu"="i686"
// CHECK: #3 = {{.*}}"target-cpu"="i686" "target-features"="+crc32,+cx8,+mmx,+popcnt,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87" "tune-cpu"="i686"
-// CHECK: #4 = {{.*}}"target-cpu"="i686" "target-features"="+cx8,+x87,-avx,-avx2,-avx512bf16,-avx512bitalg,-avx512bw,-avx512cd,-avx512dq,-avx512er,-avx512f,-avx512fp16,-avx512ifma,-avx512pf,-avx512vbmi,-avx512vbmi2,-avx512vl,-avx512vnni,-avx512vp2intersect,-avx512vpopcntdq,-avxifma,-avxvnni,-avxvnniint8,-f16c,-fma,-fma4,-sse4.1,-sse4.2,-vaes,-vpclmulqdq,-xop" "tune-cpu"="i686"
+// CHECK: #4 = {{.*}}"target-cpu"="i686" "target-features"="+cx8,+x87,-avx,-avx2,-avx512bf16,-avx512bitalg,-avx512bw,-avx512cd,-avx512dq,-avx512er,-avx512f,-avx512fp16,-avx512ifma,-avx512pf,-avx512vbmi,-avx512vbmi2,-avx512vl,-avx512vnni,-avx512vp2intersect,-avx512vpopcntdq,-avxifma,-avxneconvert,-avxvnni,-avxvnniint8,-f16c,-fma,-fma4,-sse4.1,-sse4.2,-vaes,-vpclmulqdq,-xop" "tune-cpu"="i686"
// CHECK: #5 = {{.*}}"target-cpu"="ivybridge" "target-features"="+avx,+crc32,+cx16,+cx8,+f16c,+fsgsbase,+fxsr,+mmx,+pclmul,+popcnt,+rdrnd,+sahf,+sse,+sse2,+sse3,+sse4.1,+sse4.2,+ssse3,+x87,+xsave,+xsaveopt,-aes,-vaes"
// CHECK-NOT: tune-cpu
// CHECK: #6 = {{.*}}"target-cpu"="i686" "target-features"="+cx8,+x87,-3dnow,-3dnowa,-mmx"
// AVX-VNNIINT8: "-target-feature" "+avxvnniint8"
// NO-AVX-VNNIINT8: "-target-feature" "-avxvnniint8"
+// RUN: %clang --target=i386 -mavxneconvert %s -### -o %t.o 2>&1 | FileCheck -check-prefix=AVXNECONVERT %s
+// RUN: %clang --target=i386 -mno-avxneconvert %s -### -o %t.o 2>&1 | FileCheck -check-prefix=NO-AVXNECONVERT %s
+// AVXNECONVERT: "-target-feature" "+avxneconvert"
+// NO-AVXNECONVERT: "-target-feature" "-avxneconvert"
+
// RUN: %clang --target=i386 -march=i386 -mcrc32 %s -### 2>&1 | FileCheck -check-prefix=CRC32 %s
// RUN: %clang --target=i386 -march=i386 -mno-crc32 %s -### 2>&1 | FileCheck -check-prefix=NO-CRC32 %s
// CRC32: "-target-feature" "+crc32"
// AVXVNNIINT8NOAVX2-NOT: #define __AVX2__ 1
// AVXVNNIINT8NOAVX2-NOT: #define __AVXVNNIINT8__ 1
+// RUN: %clang -target i386-unknown-unknown -march=atom -mavxneconvert -x c -E -dM -o - %s | FileCheck -match-full-lines --check-prefix=AVXNECONVERT %s
+
+// AVXNECONVERT: #define __AVX2__ 1
+// AVXNECONVERT: #define __AVXNECONVERT__ 1
+
+// RUN: %clang -target i386-unknown-unknown -march=atom -mno-avxneconvert -x c -E -dM -o - %s | FileCheck -match-full-lines --check-prefix=NOAVXNECONVERT %s
+
+// NOAVXNECONVERT-NOT: #define __AVXNECONVERT__ 1
+
+// RUN: %clang -target i386-unknown-unknown -march=atom -mavxneconvert -mno-avx2 -x c -E -dM -o - %s | FileCheck -match-full-lines --check-prefix=AVXNECONVERTNOAVX2 %s
+
+// AVXNECONVERTNOAVX2-NOT: #define __AVX2__ 1
+// AVXNECONVERTNOAVX2-NOT: #define __AVXNECONVERT__ 1
+
// RUN: %clang -target i386-unknown-linux-gnu -march=i386 -mcrc32 -x c -E -dM -o - %s | FileCheck -check-prefix=CRC32 %s
// CRC32: #define __CRC32__ 1
Changes to the X86 Backend
--------------------------
-* Support ISA of ``AVX-IFMA``.
* Add support for the ``RDMSRLIST and WRMSRLIST`` instructions.
* Add support for the ``WRMSRNS`` instruction.
* Support ISA of ``AMX-FP16`` which contains ``tdpfp16ps`` instruction.
* Support ISA of ``CMPCCXADD``.
+* Support ISA of ``AVX-IFMA``.
* Support ISA of ``AVX-VNNI-INT8``.
+* Support ISA of ``AVX-NE-CONVERT``.
Changes to the OCaml bindings
-----------------------------
Intrinsic<[], [llvm_i8_ty, llvm_i8_ty, llvm_i8_ty],
[ImmArg<ArgIndex<0>>,
ImmArg<ArgIndex<1>>, ImmArg<ArgIndex<2>>]>;
+def int_x86_vbcstnebf162ps128 : ClangBuiltin<"__builtin_ia32_vbcstnebf162ps128">,
+ Intrinsic<[llvm_v4f32_ty], [llvm_ptr_ty], [IntrReadMem]>;
+def int_x86_vbcstnebf162ps256 : ClangBuiltin<"__builtin_ia32_vbcstnebf162ps256">,
+ Intrinsic<[llvm_v8f32_ty], [llvm_ptr_ty], [IntrReadMem]>;
+def int_x86_vbcstnesh2ps128 : ClangBuiltin<"__builtin_ia32_vbcstnesh2ps128">,
+ Intrinsic<[llvm_v4f32_ty], [llvm_ptr_ty], [IntrReadMem]>;
+def int_x86_vbcstnesh2ps256 : ClangBuiltin<"__builtin_ia32_vbcstnesh2ps256">,
+ Intrinsic<[llvm_v8f32_ty], [llvm_ptr_ty], [IntrReadMem]>;
+def int_x86_vcvtneebf162ps128 : ClangBuiltin<"__builtin_ia32_vcvtneebf162ps128">,
+ Intrinsic<[llvm_v4f32_ty], [llvm_ptr_ty], [IntrReadMem]>;
+def int_x86_vcvtneebf162ps256 : ClangBuiltin<"__builtin_ia32_vcvtneebf162ps256">,
+ Intrinsic<[llvm_v8f32_ty], [llvm_ptr_ty], [IntrReadMem]>;
+def int_x86_vcvtneeph2ps128 : ClangBuiltin<"__builtin_ia32_vcvtneeph2ps128">,
+ Intrinsic<[llvm_v4f32_ty], [llvm_ptr_ty], [IntrReadMem]>;
+def int_x86_vcvtneeph2ps256 : ClangBuiltin<"__builtin_ia32_vcvtneeph2ps256">,
+ Intrinsic<[llvm_v8f32_ty], [llvm_ptr_ty], [IntrReadMem]>;
+def int_x86_vcvtneobf162ps128 : ClangBuiltin<"__builtin_ia32_vcvtneobf162ps128">,
+ Intrinsic<[llvm_v4f32_ty], [llvm_ptr_ty], [IntrReadMem]>;
+def int_x86_vcvtneobf162ps256 : ClangBuiltin<"__builtin_ia32_vcvtneobf162ps256">,
+ Intrinsic<[llvm_v8f32_ty], [llvm_ptr_ty], [IntrReadMem]>;
+def int_x86_vcvtneoph2ps128 : ClangBuiltin<"__builtin_ia32_vcvtneoph2ps128">,
+ Intrinsic<[llvm_v4f32_ty], [llvm_ptr_ty], [IntrReadMem]>;
+def int_x86_vcvtneoph2ps256 : ClangBuiltin<"__builtin_ia32_vcvtneoph2ps256">,
+ Intrinsic<[llvm_v8f32_ty], [llvm_ptr_ty], [IntrReadMem]>;
+def int_x86_vcvtneps2bf16128 : ClangBuiltin<"__builtin_ia32_vcvtneps2bf16128">,
+ Intrinsic<[llvm_v8bf16_ty], [llvm_v4f32_ty], [ IntrNoMem ]>;
+def int_x86_vcvtneps2bf16256 : ClangBuiltin<"__builtin_ia32_vcvtneps2bf16256">,
+ Intrinsic<[llvm_v8bf16_ty], [llvm_v8f32_ty], [ IntrNoMem ]>;
}
//===----------------------------------------------------------------------===//
// RAO-INT intrinsics
X86_FEATURE (AVX512FP16, "avx512fp16")
X86_FEATURE (AMX_FP16, "amx-fp16")
X86_FEATURE (CMPCCXADD, "cmpccxadd")
+X86_FEATURE (AVXNECONVERT, "avxneconvert")
X86_FEATURE (AVXVNNI, "avxvnni")
X86_FEATURE (AVXIFMA, "avxifma")
X86_FEATURE (AVXVNNIINT8, "avxvnniint8")
Features["hreset"] = HasLeaf7Subleaf1 && ((EAX >> 22) & 1);
Features["avxifma"] = HasLeaf7Subleaf1 && ((EAX >> 23) & 1) && HasAVXSave;
Features["avxvnniint8"] = HasLeaf7Subleaf1 && ((EDX >> 4) & 1) && HasAVXSave;
+ Features["avxneconvert"] = HasLeaf7Subleaf1 && ((EDX >> 5) & 1) && HasAVXSave;
Features["prefetchi"] = HasLeaf7Subleaf1 && ((EDX >> 14) & 1);
bool HasLeafD = MaxLevel >= 0xd &&
constexpr FeatureBitset ImpliedFeaturesAMX_INT8 = FeatureAMX_TILE;
constexpr FeatureBitset ImpliedFeaturesHRESET = {};
-constexpr FeatureBitset ImpliedFeaturesAVXVNNIINT8 = FeatureAVX2;
constexpr FeatureBitset ImpliedFeaturesPREFETCHI = {};
constexpr FeatureBitset ImpliedFeaturesCMPCCXADD = {};
constexpr FeatureBitset ImpliedFeaturesRAOINT = {};
+constexpr FeatureBitset ImpliedFeaturesAVXVNNIINT8 = FeatureAVX2;
constexpr FeatureBitset ImpliedFeaturesAVXIFMA = FeatureAVX2;
+constexpr FeatureBitset ImpliedFeaturesAVXNECONVERT = FeatureAVX2;
constexpr FeatureBitset ImpliedFeaturesAVX512FP16 =
FeatureAVX512BW | FeatureAVX512DQ | FeatureAVX512VL;
// Key Locker Features
def FeatureRAOINT : SubtargetFeature<"raoint", "HasRAOINT", "true",
"Support RAO-INT instructions",
[]>;
+def FeatureAVXNECONVERT : SubtargetFeature<"avxneconvert", "HasAVXNECONVERT", "true",
+ "Support AVX-NE-CONVERT instructions",
+ [FeatureAVX2]>;
def FeatureINVPCID : SubtargetFeature<"invpcid", "HasINVPCID", "true",
"Invalidate Process-Context Identifier">;
def FeatureSGX : SubtargetFeature<"sgx", "HasSGX", "true",
}
}
- if (!Subtarget.useSoftFloat() && Subtarget.hasBF16()) {
+ if (!Subtarget.useSoftFloat() &&
+ (Subtarget.hasAVXNECONVERT() || Subtarget.hasBF16())) {
addRegisterClass(MVT::v8bf16, &X86::VR128XRegClass);
addRegisterClass(MVT::v16bf16, &X86::VR256XRegClass);
- addRegisterClass(MVT::v32bf16, &X86::VR512RegClass);
// We set the type action of bf16 to TypeSoftPromoteHalf, but we don't
// provide the method to promote BUILD_VECTOR. Set the operation action
// Custom to do the customization later.
setOperationAction(ISD::BUILD_VECTOR, MVT::bf16, Custom);
- for (auto VT : { MVT::v8bf16, MVT::v16bf16, MVT::v32bf16 }) {
+ for (auto VT : {MVT::v8bf16, MVT::v16bf16}) {
setF16Action(VT, Expand);
setOperationAction(ISD::FADD, VT, Expand);
setOperationAction(ISD::FSUB, VT, Expand);
addLegalFPImmediate(APFloat::getZero(APFloat::BFloat()));
}
+ if (!Subtarget.useSoftFloat() && Subtarget.hasBF16()) {
+ addRegisterClass(MVT::v32bf16, &X86::VR512RegClass);
+ setF16Action(MVT::v32bf16, Expand);
+ setOperationAction(ISD::FADD, MVT::v32bf16, Expand);
+ setOperationAction(ISD::FSUB, MVT::v32bf16, Expand);
+ setOperationAction(ISD::FMUL, MVT::v32bf16, Expand);
+ setOperationAction(ISD::FDIV, MVT::v32bf16, Expand);
+ setOperationAction(ISD::BUILD_VECTOR, MVT::v32bf16, Custom);
+ }
+
if (!Subtarget.useSoftFloat() && Subtarget.hasVLX()) {
setTruncStoreAction(MVT::v4i64, MVT::v4i8, Legal);
setTruncStoreAction(MVT::v4i64, MVT::v4i16, Legal);
def : Pat<(X86mcvtneps2bf16 (v4f32 (X86VBroadcastld32 addr:$src)),
v8bf16x_info.ImmAllZerosV, VK4WM:$mask),
(VCVTNEPS2BF16Z128rmbkz VK4WM:$mask, addr:$src)>;
+
+ def : Pat<(v8bf16 (int_x86_vcvtneps2bf16128 (v4f32 VR128X:$src))),
+ (VCVTNEPS2BF16Z128rr VR128X:$src)>;
+ def : Pat<(v8bf16 (int_x86_vcvtneps2bf16128 (loadv4f32 addr:$src))),
+ (VCVTNEPS2BF16Z128rm addr:$src)>;
+
+ def : Pat<(v8bf16 (int_x86_vcvtneps2bf16256 (v8f32 VR256X:$src))),
+ (VCVTNEPS2BF16Z256rr VR256X:$src)>;
+ def : Pat<(v8bf16 (int_x86_vcvtneps2bf16256 (loadv8f32 addr:$src))),
+ (VCVTNEPS2BF16Z256rm addr:$src)>;
}
let Constraints = "$src1 = $dst" in {
def HasENQCMD : Predicate<"Subtarget->hasENQCMD()">;
def HasAMXFP16 : Predicate<"Subtarget->hasAMXFP16()">;
def HasCMPCCXADD : Predicate<"Subtarget->hasCMPCCXADD()">;
+def HasAVXNECONVERT : Predicate<"Subtarget->hasAVXNECONVERT()">;
def HasKL : Predicate<"Subtarget->hasKL()">;
def HasRAOINT : Predicate<"Subtarget->hasRAOINT()">;
def HasWIDEKL : Predicate<"Subtarget->hasWIDEKL()">;
X86GF2P8affineqb>, TAPD;
}
+// AVX-IFMA
let Predicates = [HasAVXIFMA, NoVLX_Or_NoIFMA], Constraints = "$src1 = $dst",
checkVEXPredicate = 1 in
multiclass avx_ifma_rm<bits<8> opc, string OpcodeStr, SDNode OpNode> {
defm VPMADD52HUQ : avx_ifma_rm<0xb5, "vpmadd52huq", x86vpmadd52h>, VEX_W, ExplicitVEXPrefix;
defm VPMADD52LUQ : avx_ifma_rm<0xb4, "vpmadd52luq", x86vpmadd52l>, VEX_W, ExplicitVEXPrefix;
+// AVX-VNNI-INT8
let Constraints = "$src1 = $dst" in
multiclass avx_dotprod_rm<bits<8> Opc, string OpcodeStr, ValueType OpVT,
RegisterClass RC, PatFrag MemOpFrag,
i256mem, X86vpdpbsuds, SchedWriteVecIMul.YMM,
0>, VEX_L, T8XS;
}
+
+// AVX-NE-CONVERT
+multiclass AVX_NE_CONVERT_BASE<bits<8> Opcode, string OpcodeStr,
+ X86MemOperand MemOp128, X86MemOperand MemOp256> {
+ def rm : I<Opcode, MRMSrcMem, (outs VR128:$dst), (ins MemOp128:$src),
+ !strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
+ [(set VR128:$dst,
+ (!cast<Intrinsic>("int_x86_"#OpcodeStr#"128") addr:$src))]>,
+ Sched<[WriteCvtPH2PS]>, VEX;
+ def Yrm : I<Opcode, MRMSrcMem, (outs VR256:$dst), (ins MemOp256:$src),
+ !strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
+ [(set VR256:$dst,
+ (!cast<Intrinsic>("int_x86_"#OpcodeStr#"256") addr:$src))]>,
+ Sched<[WriteCvtPH2PSY]>, VEX, VEX_L;
+}
+
+multiclass VCVTNEPS2BF16_BASE {
+ def rr : I<0x72, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
+ "vcvtneps2bf16\t{$src, $dst|$dst, $src}",
+ [(set VR128:$dst, (int_x86_vcvtneps2bf16128 VR128:$src))]>,
+ Sched<[WriteCvtPH2PS]>;
+ def rm : I<0x72, MRMSrcMem, (outs VR128:$dst), (ins f128mem:$src),
+ "vcvtneps2bf16{x}\t{$src, $dst|$dst, $src}",
+ [(set VR128:$dst, (int_x86_vcvtneps2bf16128 (loadv4f32 addr:$src)))]>,
+ Sched<[WriteCvtPH2PS]>;
+ def Yrr : I<0x72, MRMSrcReg, (outs VR128:$dst), (ins VR256:$src),
+ "vcvtneps2bf16\t{$src, $dst|$dst, $src}",
+ [(set VR128:$dst, (int_x86_vcvtneps2bf16256 VR256:$src))]>,
+ Sched<[WriteCvtPH2PSY]>, VEX_L;
+ def Yrm : I<0x72, MRMSrcMem, (outs VR128:$dst), (ins f256mem:$src),
+ "vcvtneps2bf16{y}\t{$src, $dst|$dst, $src}",
+ [(set VR128:$dst, (int_x86_vcvtneps2bf16256 (loadv8f32 addr:$src)))]>,
+ Sched<[WriteCvtPH2PSY]>, VEX_L;
+}
+
+let Predicates = [HasAVXNECONVERT] in {
+ defm VBCSTNEBF162PS : AVX_NE_CONVERT_BASE<0xb1, "vbcstnebf162ps", f16mem,
+ f16mem>, T8XS;
+ defm VBCSTNESH2PS : AVX_NE_CONVERT_BASE<0xb1, "vbcstnesh2ps", f16mem, f16mem>,
+ T8PD;
+ defm VCVTNEEBF162PS : AVX_NE_CONVERT_BASE<0xb0, "vcvtneebf162ps", f128mem,
+ f256mem>, T8XS;
+ defm VCVTNEEPH2PS : AVX_NE_CONVERT_BASE<0xb0, "vcvtneeph2ps", f128mem,
+ f256mem>, T8PD;
+ defm VCVTNEOBF162PS : AVX_NE_CONVERT_BASE<0xb0, "vcvtneobf162ps", f128mem,
+ f256mem>, T8XD;
+ defm VCVTNEOPH2PS : AVX_NE_CONVERT_BASE<0xb0, "vcvtneoph2ps", f128mem,
+ f256mem>, T8PS;
+ let checkVEXPredicate = 1 in
+ defm VCVTNEPS2BF16 : VCVTNEPS2BF16_BASE, VEX, T8XS, ExplicitVEXPrefix;
+}
+
+def : InstAlias<"vcvtneps2bf16x\t{$src, $dst|$dst, $src}",
+ (VCVTNEPS2BF16rr VR128:$dst, VR128:$src), 0, "att">;
+def : InstAlias<"vcvtneps2bf16y\t{$src, $dst|$dst, $src}",
+ (VCVTNEPS2BF16Yrr VR128:$dst, VR256:$src), 0, "att">;
--- /dev/null
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -O0 -verify-machineinstrs -mtriple=x86_64-unknown-unknown --show-mc-encoding -mattr=+avxneconvert,+avx512bf16,+avx512vl | FileCheck %s --check-prefix=AVX512BF16-COMMON
+; RUN: llc < %s -O0 -verify-machineinstrs -mtriple=i686-unknown-unknown --show-mc-encoding -mattr=+avxneconvert,+avx512bf16,+avx512vl | FileCheck %s --check-prefix=AVX512BF16-COMMON
+; RUN: llc < %s -O0 -verify-machineinstrs -mtriple=x86_64-unknown-unknown --show-mc-encoding -mattr=+avx512bf16,+avx512vl | FileCheck %s --check-prefix=AVX512BF16
+; RUN: llc < %s -O0 -verify-machineinstrs -mtriple=i686-unknown-unknown --show-mc-encoding -mattr=+avx512bf16,+avx512vl | FileCheck %s --check-prefix=AVX512BF16
+
+define <8 x bfloat> @test_int_x86_vcvtneps2bf16128(<4 x float> %A) {
+; AVX512BF16-COMMON-LABEL: test_int_x86_vcvtneps2bf16128:
+; AVX512BF16-COMMON: # %bb.0:
+; AVX512BF16-COMMON-NEXT: {vex} vcvtneps2bf16 %xmm0, %xmm0 # encoding: [0xc4,0xe2,0x7a,0x72,0xc0]
+; AVX512BF16-COMMON-NEXT: # kill: def $xmm1 killed $xmm0
+; AVX512BF16-COMMON-NEXT: ret{{[l|q]}} # encoding: [0xc3]
+;
+; AVX512BF16-LABEL: test_int_x86_vcvtneps2bf16128:
+; AVX512BF16: # %bb.0:
+; AVX512BF16-NEXT: vcvtneps2bf16 %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7e,0x08,0x72,0xc0]
+; AVX512BF16-NEXT: ret{{[l|q]}} # encoding: [0xc3]
+ %ret = call <8 x bfloat> @llvm.x86.vcvtneps2bf16128(<4 x float> %A)
+ ret <8 x bfloat> %ret
+}
+declare <8 x bfloat> @llvm.x86.vcvtneps2bf16128(<4 x float> %A)
+
+define <8 x bfloat> @test_int_x86_vcvtneps2bf16256(<8 x float> %A) {
+; AVX512BF16-COMMON-LABEL: test_int_x86_vcvtneps2bf16256:
+; AVX512BF16-COMMON: # %bb.0:
+; AVX512BF16-COMMON-NEXT: {vex} vcvtneps2bf16 %ymm0, %xmm0 # encoding: [0xc4,0xe2,0x7e,0x72,0xc0]
+; AVX512BF16-COMMON-NEXT: # kill: def $xmm1 killed $xmm0
+; AVX512BF16-COMMON-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
+; AVX512BF16-COMMON-NEXT: ret{{[l|q]}} # encoding: [0xc3]
+;
+; AVX512BF16-LABEL: test_int_x86_vcvtneps2bf16256:
+; AVX512BF16: # %bb.0:
+; AVX512BF16-NEXT: vcvtneps2bf16 %ymm0, %xmm0 # encoding: [0x62,0xf2,0x7e,0x28,0x72,0xc0]
+; AVX512BF16-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
+; AVX512BF16-NEXT: ret{{[l|q]}} # encoding: [0xc3]
+ %ret = call <8 x bfloat> @llvm.x86.vcvtneps2bf16256(<8 x float> %A)
+ ret <8 x bfloat> %ret
+}
+declare <8 x bfloat> @llvm.x86.vcvtneps2bf16256(<8 x float> %A)
+
--- /dev/null
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -O0 -verify-machineinstrs -mtriple=x86_64-unknown-unknown --show-mc-encoding -mattr=+avxneconvert | FileCheck %s --check-prefixes=CHECK,X64
+; RUN: llc < %s -O0 -verify-machineinstrs -mtriple=i686-unknown-unknown --show-mc-encoding -mattr=+avxneconvert | FileCheck %s --check-prefixes=CHECK,X86
+
+define <4 x float> @test_int_x86_vbcstnebf162ps128(i8* %A) {
+; X64-LABEL: test_int_x86_vbcstnebf162ps128:
+; X64: # %bb.0:
+; X64-NEXT: vbcstnebf162ps (%rdi), %xmm0 # encoding: [0xc4,0xe2,0x7a,0xb1,0x07]
+; X64-NEXT: retq # encoding: [0xc3]
+;
+; X86-LABEL: test_int_x86_vbcstnebf162ps128:
+; X86: # %bb.0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
+; X86-NEXT: vbcstnebf162ps (%eax), %xmm0 # encoding: [0xc4,0xe2,0x7a,0xb1,0x00]
+; X86-NEXT: retl # encoding: [0xc3]
+ %ret = call <4 x float> @llvm.x86.vbcstnebf162ps128(i8* %A)
+ ret <4 x float> %ret
+}
+declare <4 x float> @llvm.x86.vbcstnebf162ps128(i8* %A)
+
+define <8 x float> @test_int_x86_vbcstnebf162ps256(i8* %A) {
+; X64-LABEL: test_int_x86_vbcstnebf162ps256:
+; X64: # %bb.0:
+; X64-NEXT: vbcstnebf162ps (%rdi), %ymm0 # encoding: [0xc4,0xe2,0x7e,0xb1,0x07]
+; X64-NEXT: retq # encoding: [0xc3]
+;
+; X86-LABEL: test_int_x86_vbcstnebf162ps256:
+; X86: # %bb.0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
+; X86-NEXT: vbcstnebf162ps (%eax), %ymm0 # encoding: [0xc4,0xe2,0x7e,0xb1,0x00]
+; X86-NEXT: retl # encoding: [0xc3]
+ %ret = call <8 x float> @llvm.x86.vbcstnebf162ps256(i8* %A)
+ ret <8 x float> %ret
+}
+declare <8 x float> @llvm.x86.vbcstnebf162ps256(i8* %A)
+
+define <4 x float> @test_int_x86_vbcstnesh2ps128(i8* %A) {
+; X64-LABEL: test_int_x86_vbcstnesh2ps128:
+; X64: # %bb.0:
+; X64-NEXT: vbcstnesh2ps (%rdi), %xmm0 # encoding: [0xc4,0xe2,0x79,0xb1,0x07]
+; X64-NEXT: retq # encoding: [0xc3]
+;
+; X86-LABEL: test_int_x86_vbcstnesh2ps128:
+; X86: # %bb.0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
+; X86-NEXT: vbcstnesh2ps (%eax), %xmm0 # encoding: [0xc4,0xe2,0x79,0xb1,0x00]
+; X86-NEXT: retl # encoding: [0xc3]
+ %ret = call <4 x float> @llvm.x86.vbcstnesh2ps128(i8* %A)
+ ret <4 x float> %ret
+}
+declare <4 x float> @llvm.x86.vbcstnesh2ps128(i8* %A)
+
+define <8 x float> @test_int_x86_vbcstnesh2ps256(i8* %A) {
+; X64-LABEL: test_int_x86_vbcstnesh2ps256:
+; X64: # %bb.0:
+; X64-NEXT: vbcstnesh2ps (%rdi), %ymm0 # encoding: [0xc4,0xe2,0x7d,0xb1,0x07]
+; X64-NEXT: retq # encoding: [0xc3]
+;
+; X86-LABEL: test_int_x86_vbcstnesh2ps256:
+; X86: # %bb.0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
+; X86-NEXT: vbcstnesh2ps (%eax), %ymm0 # encoding: [0xc4,0xe2,0x7d,0xb1,0x00]
+; X86-NEXT: retl # encoding: [0xc3]
+ %ret = call <8 x float> @llvm.x86.vbcstnesh2ps256(i8* %A)
+ ret <8 x float> %ret
+}
+declare <8 x float> @llvm.x86.vbcstnesh2ps256(i8* %A)
+
+define <4 x float> @test_int_x86_vcvtneebf162ps128(i8* %A) {
+; X64-LABEL: test_int_x86_vcvtneebf162ps128:
+; X64: # %bb.0:
+; X64-NEXT: vcvtneebf162ps (%rdi), %xmm0 # encoding: [0xc4,0xe2,0x7a,0xb0,0x07]
+; X64-NEXT: retq # encoding: [0xc3]
+;
+; X86-LABEL: test_int_x86_vcvtneebf162ps128:
+; X86: # %bb.0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
+; X86-NEXT: vcvtneebf162ps (%eax), %xmm0 # encoding: [0xc4,0xe2,0x7a,0xb0,0x00]
+; X86-NEXT: retl # encoding: [0xc3]
+ %ret = call <4 x float> @llvm.x86.vcvtneebf162ps128(i8* %A)
+ ret <4 x float> %ret
+}
+declare <4 x float> @llvm.x86.vcvtneebf162ps128(i8* %A)
+
+define <8 x float> @test_int_x86_vcvtneebf162ps256(i8* %A) {
+; X64-LABEL: test_int_x86_vcvtneebf162ps256:
+; X64: # %bb.0:
+; X64-NEXT: vcvtneebf162ps (%rdi), %ymm0 # encoding: [0xc4,0xe2,0x7e,0xb0,0x07]
+; X64-NEXT: retq # encoding: [0xc3]
+;
+; X86-LABEL: test_int_x86_vcvtneebf162ps256:
+; X86: # %bb.0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
+; X86-NEXT: vcvtneebf162ps (%eax), %ymm0 # encoding: [0xc4,0xe2,0x7e,0xb0,0x00]
+; X86-NEXT: retl # encoding: [0xc3]
+ %ret = call <8 x float> @llvm.x86.vcvtneebf162ps256(i8* %A)
+ ret <8 x float> %ret
+}
+declare <8 x float> @llvm.x86.vcvtneebf162ps256(i8* %A)
+
+define <4 x float> @test_int_x86_vcvtneeph2ps128(i8* %A) {
+; X64-LABEL: test_int_x86_vcvtneeph2ps128:
+; X64: # %bb.0:
+; X64-NEXT: vcvtneeph2ps (%rdi), %xmm0 # encoding: [0xc4,0xe2,0x79,0xb0,0x07]
+; X64-NEXT: retq # encoding: [0xc3]
+;
+; X86-LABEL: test_int_x86_vcvtneeph2ps128:
+; X86: # %bb.0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
+; X86-NEXT: vcvtneeph2ps (%eax), %xmm0 # encoding: [0xc4,0xe2,0x79,0xb0,0x00]
+; X86-NEXT: retl # encoding: [0xc3]
+ %ret = call <4 x float> @llvm.x86.vcvtneeph2ps128(i8* %A)
+ ret <4 x float> %ret
+}
+declare <4 x float> @llvm.x86.vcvtneeph2ps128(i8* %A)
+
+define <8 x float> @test_int_x86_vcvtneeph2ps256(i8* %A) {
+; X64-LABEL: test_int_x86_vcvtneeph2ps256:
+; X64: # %bb.0:
+; X64-NEXT: vcvtneeph2ps (%rdi), %ymm0 # encoding: [0xc4,0xe2,0x7d,0xb0,0x07]
+; X64-NEXT: retq # encoding: [0xc3]
+;
+; X86-LABEL: test_int_x86_vcvtneeph2ps256:
+; X86: # %bb.0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
+; X86-NEXT: vcvtneeph2ps (%eax), %ymm0 # encoding: [0xc4,0xe2,0x7d,0xb0,0x00]
+; X86-NEXT: retl # encoding: [0xc3]
+ %ret = call <8 x float> @llvm.x86.vcvtneeph2ps256(i8* %A)
+ ret <8 x float> %ret
+}
+declare <8 x float> @llvm.x86.vcvtneeph2ps256(i8* %A)
+
+define <4 x float> @test_int_x86_vcvtneobf162ps128(i8* %A) {
+; X64-LABEL: test_int_x86_vcvtneobf162ps128:
+; X64: # %bb.0:
+; X64-NEXT: vcvtneobf162ps (%rdi), %xmm0 # encoding: [0xc4,0xe2,0x7b,0xb0,0x07]
+; X64-NEXT: retq # encoding: [0xc3]
+;
+; X86-LABEL: test_int_x86_vcvtneobf162ps128:
+; X86: # %bb.0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
+; X86-NEXT: vcvtneobf162ps (%eax), %xmm0 # encoding: [0xc4,0xe2,0x7b,0xb0,0x00]
+; X86-NEXT: retl # encoding: [0xc3]
+ %ret = call <4 x float> @llvm.x86.vcvtneobf162ps128(i8* %A)
+ ret <4 x float> %ret
+}
+declare <4 x float> @llvm.x86.vcvtneobf162ps128(i8* %A)
+
+define <8 x float> @test_int_x86_vcvtneobf162ps256(i8* %A) {
+; X64-LABEL: test_int_x86_vcvtneobf162ps256:
+; X64: # %bb.0:
+; X64-NEXT: vcvtneobf162ps (%rdi), %ymm0 # encoding: [0xc4,0xe2,0x7f,0xb0,0x07]
+; X64-NEXT: retq # encoding: [0xc3]
+;
+; X86-LABEL: test_int_x86_vcvtneobf162ps256:
+; X86: # %bb.0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
+; X86-NEXT: vcvtneobf162ps (%eax), %ymm0 # encoding: [0xc4,0xe2,0x7f,0xb0,0x00]
+; X86-NEXT: retl # encoding: [0xc3]
+ %ret = call <8 x float> @llvm.x86.vcvtneobf162ps256(i8* %A)
+ ret <8 x float> %ret
+}
+declare <8 x float> @llvm.x86.vcvtneobf162ps256(i8* %A)
+
+define <4 x float> @test_int_x86_vcvtneoph2ps128(i8* %A) {
+; X64-LABEL: test_int_x86_vcvtneoph2ps128:
+; X64: # %bb.0:
+; X64-NEXT: vcvtneoph2ps (%rdi), %xmm0 # encoding: [0xc4,0xe2,0x78,0xb0,0x07]
+; X64-NEXT: retq # encoding: [0xc3]
+;
+; X86-LABEL: test_int_x86_vcvtneoph2ps128:
+; X86: # %bb.0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
+; X86-NEXT: vcvtneoph2ps (%eax), %xmm0 # encoding: [0xc4,0xe2,0x78,0xb0,0x00]
+; X86-NEXT: retl # encoding: [0xc3]
+ %ret = call <4 x float> @llvm.x86.vcvtneoph2ps128(i8* %A)
+ ret <4 x float> %ret
+}
+declare <4 x float> @llvm.x86.vcvtneoph2ps128(i8* %A)
+
+define <8 x float> @test_int_x86_vcvtneoph2ps256(i8* %A) {
+; X64-LABEL: test_int_x86_vcvtneoph2ps256:
+; X64: # %bb.0:
+; X64-NEXT: vcvtneoph2ps (%rdi), %ymm0 # encoding: [0xc4,0xe2,0x7c,0xb0,0x07]
+; X64-NEXT: retq # encoding: [0xc3]
+;
+; X86-LABEL: test_int_x86_vcvtneoph2ps256:
+; X86: # %bb.0:
+; X86-NEXT: movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
+; X86-NEXT: vcvtneoph2ps (%eax), %ymm0 # encoding: [0xc4,0xe2,0x7c,0xb0,0x00]
+; X86-NEXT: retl # encoding: [0xc3]
+ %ret = call <8 x float> @llvm.x86.vcvtneoph2ps256(i8* %A)
+ ret <8 x float> %ret
+}
+declare <8 x float> @llvm.x86.vcvtneoph2ps256(i8* %A)
+
+define <8 x bfloat> @test_int_x86_vcvtneps2bf16128(<4 x float> %A) {
+; CHECK-LABEL: test_int_x86_vcvtneps2bf16128:
+; CHECK: # %bb.0:
+; CHECK-NEXT: {vex} vcvtneps2bf16 %xmm0, %xmm0 # encoding: [0xc4,0xe2,0x7a,0x72,0xc0]
+; CHECK-NEXT: # kill: def $xmm1 killed $xmm0
+; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
+ %ret = call <8 x bfloat> @llvm.x86.vcvtneps2bf16128(<4 x float> %A)
+ ret <8 x bfloat> %ret
+}
+declare <8 x bfloat> @llvm.x86.vcvtneps2bf16128(<4 x float> %A)
+
+define <8 x bfloat> @test_int_x86_vcvtneps2bf16256(<8 x float> %A) {
+; CHECK-LABEL: test_int_x86_vcvtneps2bf16256:
+; CHECK: # %bb.0:
+; CHECK-NEXT: {vex} vcvtneps2bf16 %ymm0, %xmm0 # encoding: [0xc4,0xe2,0x7e,0x72,0xc0]
+; CHECK-NEXT: # kill: def $xmm1 killed $xmm0
+; CHECK-NEXT: vzeroupper # encoding: [0xc5,0xf8,0x77]
+; CHECK-NEXT: ret{{[l|q]}} # encoding: [0xc3]
+ %ret = call <8 x bfloat> @llvm.x86.vcvtneps2bf16256(<8 x float> %A)
+ ret <8 x bfloat> %ret
+}
+declare <8 x bfloat> @llvm.x86.vcvtneps2bf16256(<8 x float> %A)
+
--- /dev/null
+# RUN: llvm-mc --disassemble %s -triple=i386-unknown-unknown | FileCheck %s --check-prefixes=ATT
+# RUN: llvm-mc --disassemble %s -triple=i386-unknown-unknown -x86-asm-syntax=intel --output-asm-variant=1 | FileCheck %s --check-prefixes=INTEL
+
+# ATT: vbcstnebf162ps 268435456(%esp,%esi,8), %xmm2
+# INTEL: vbcstnebf162ps xmm2, word ptr [esp + 8*esi + 268435456]
+0xc4,0xe2,0x7a,0xb1,0x94,0xf4,0x00,0x00,0x00,0x10
+
+# ATT: vbcstnebf162ps 291(%edi,%eax,4), %xmm2
+# INTEL: vbcstnebf162ps xmm2, word ptr [edi + 4*eax + 291]
+0xc4,0xe2,0x7a,0xb1,0x94,0x87,0x23,0x01,0x00,0x00
+
+# ATT: vbcstnebf162ps (%eax), %xmm2
+# INTEL: vbcstnebf162ps xmm2, word ptr [eax]
+0xc4,0xe2,0x7a,0xb1,0x10
+
+# ATT: vbcstnebf162ps -64(,%ebp,2), %xmm2
+# INTEL: vbcstnebf162ps xmm2, word ptr [2*ebp - 64]
+0xc4,0xe2,0x7a,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff
+
+# ATT: vbcstnebf162ps 254(%ecx), %xmm2
+# INTEL: vbcstnebf162ps xmm2, word ptr [ecx + 254]
+0xc4,0xe2,0x7a,0xb1,0x91,0xfe,0x00,0x00,0x00
+
+# ATT: vbcstnebf162ps -256(%edx), %xmm2
+# INTEL: vbcstnebf162ps xmm2, word ptr [edx - 256]
+0xc4,0xe2,0x7a,0xb1,0x92,0x00,0xff,0xff,0xff
+
+# ATT: vbcstnebf162ps 268435456(%esp,%esi,8), %ymm2
+# INTEL: vbcstnebf162ps ymm2, word ptr [esp + 8*esi + 268435456]
+0xc4,0xe2,0x7e,0xb1,0x94,0xf4,0x00,0x00,0x00,0x10
+
+# ATT: vbcstnebf162ps 291(%edi,%eax,4), %ymm2
+# INTEL: vbcstnebf162ps ymm2, word ptr [edi + 4*eax + 291]
+0xc4,0xe2,0x7e,0xb1,0x94,0x87,0x23,0x01,0x00,0x00
+
+# ATT: vbcstnebf162ps (%eax), %ymm2
+# INTEL: vbcstnebf162ps ymm2, word ptr [eax]
+0xc4,0xe2,0x7e,0xb1,0x10
+
+# ATT: vbcstnebf162ps -64(,%ebp,2), %ymm2
+# INTEL: vbcstnebf162ps ymm2, word ptr [2*ebp - 64]
+0xc4,0xe2,0x7e,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff
+
+# ATT: vbcstnebf162ps 254(%ecx), %ymm2
+# INTEL: vbcstnebf162ps ymm2, word ptr [ecx + 254]
+0xc4,0xe2,0x7e,0xb1,0x91,0xfe,0x00,0x00,0x00
+
+# ATT: vbcstnebf162ps -256(%edx), %ymm2
+# INTEL: vbcstnebf162ps ymm2, word ptr [edx - 256]
+0xc4,0xe2,0x7e,0xb1,0x92,0x00,0xff,0xff,0xff
+
+# ATT: vbcstnesh2ps 268435456(%esp,%esi,8), %xmm2
+# INTEL: vbcstnesh2ps xmm2, word ptr [esp + 8*esi + 268435456]
+0xc4,0xe2,0x79,0xb1,0x94,0xf4,0x00,0x00,0x00,0x10
+
+# ATT: vbcstnesh2ps 291(%edi,%eax,4), %xmm2
+# INTEL: vbcstnesh2ps xmm2, word ptr [edi + 4*eax + 291]
+0xc4,0xe2,0x79,0xb1,0x94,0x87,0x23,0x01,0x00,0x00
+
+# ATT: vbcstnesh2ps (%eax), %xmm2
+# INTEL: vbcstnesh2ps xmm2, word ptr [eax]
+0xc4,0xe2,0x79,0xb1,0x10
+
+# ATT: vbcstnesh2ps -64(,%ebp,2), %xmm2
+# INTEL: vbcstnesh2ps xmm2, word ptr [2*ebp - 64]
+0xc4,0xe2,0x79,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff
+
+# ATT: vbcstnesh2ps 254(%ecx), %xmm2
+# INTEL: vbcstnesh2ps xmm2, word ptr [ecx + 254]
+0xc4,0xe2,0x79,0xb1,0x91,0xfe,0x00,0x00,0x00
+
+# ATT: vbcstnesh2ps -256(%edx), %xmm2
+# INTEL: vbcstnesh2ps xmm2, word ptr [edx - 256]
+0xc4,0xe2,0x79,0xb1,0x92,0x00,0xff,0xff,0xff
+
+# ATT: vbcstnesh2ps 268435456(%esp,%esi,8), %ymm2
+# INTEL: vbcstnesh2ps ymm2, word ptr [esp + 8*esi + 268435456]
+0xc4,0xe2,0x7d,0xb1,0x94,0xf4,0x00,0x00,0x00,0x10
+
+# ATT: vbcstnesh2ps 291(%edi,%eax,4), %ymm2
+# INTEL: vbcstnesh2ps ymm2, word ptr [edi + 4*eax + 291]
+0xc4,0xe2,0x7d,0xb1,0x94,0x87,0x23,0x01,0x00,0x00
+
+# ATT: vbcstnesh2ps (%eax), %ymm2
+# INTEL: vbcstnesh2ps ymm2, word ptr [eax]
+0xc4,0xe2,0x7d,0xb1,0x10
+
+# ATT: vbcstnesh2ps -64(,%ebp,2), %ymm2
+# INTEL: vbcstnesh2ps ymm2, word ptr [2*ebp - 64]
+0xc4,0xe2,0x7d,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff
+
+# ATT: vbcstnesh2ps 254(%ecx), %ymm2
+# INTEL: vbcstnesh2ps ymm2, word ptr [ecx + 254]
+0xc4,0xe2,0x7d,0xb1,0x91,0xfe,0x00,0x00,0x00
+
+# ATT: vbcstnesh2ps -256(%edx), %ymm2
+# INTEL: vbcstnesh2ps ymm2, word ptr [edx - 256]
+0xc4,0xe2,0x7d,0xb1,0x92,0x00,0xff,0xff,0xff
+
+# ATT: vcvtneebf162ps 268435456(%esp,%esi,8), %xmm2
+# INTEL: vcvtneebf162ps xmm2, xmmword ptr [esp + 8*esi + 268435456]
+0xc4,0xe2,0x7a,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10
+
+# ATT: vcvtneebf162ps 291(%edi,%eax,4), %xmm2
+# INTEL: vcvtneebf162ps xmm2, xmmword ptr [edi + 4*eax + 291]
+0xc4,0xe2,0x7a,0xb0,0x94,0x87,0x23,0x01,0x00,0x00
+
+# ATT: vcvtneebf162ps (%eax), %xmm2
+# INTEL: vcvtneebf162ps xmm2, xmmword ptr [eax]
+0xc4,0xe2,0x7a,0xb0,0x10
+
+# ATT: vcvtneebf162ps -512(,%ebp,2), %xmm2
+# INTEL: vcvtneebf162ps xmm2, xmmword ptr [2*ebp - 512]
+0xc4,0xe2,0x7a,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff
+
+# ATT: vcvtneebf162ps 2032(%ecx), %xmm2
+# INTEL: vcvtneebf162ps xmm2, xmmword ptr [ecx + 2032]
+0xc4,0xe2,0x7a,0xb0,0x91,0xf0,0x07,0x00,0x00
+
+# ATT: vcvtneebf162ps -2048(%edx), %xmm2
+# INTEL: vcvtneebf162ps xmm2, xmmword ptr [edx - 2048]
+0xc4,0xe2,0x7a,0xb0,0x92,0x00,0xf8,0xff,0xff
+
+# ATT: vcvtneebf162ps 268435456(%esp,%esi,8), %ymm2
+# INTEL: vcvtneebf162ps ymm2, ymmword ptr [esp + 8*esi + 268435456]
+0xc4,0xe2,0x7e,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10
+
+# ATT: vcvtneebf162ps 291(%edi,%eax,4), %ymm2
+# INTEL: vcvtneebf162ps ymm2, ymmword ptr [edi + 4*eax + 291]
+0xc4,0xe2,0x7e,0xb0,0x94,0x87,0x23,0x01,0x00,0x00
+
+# ATT: vcvtneebf162ps (%eax), %ymm2
+# INTEL: vcvtneebf162ps ymm2, ymmword ptr [eax]
+0xc4,0xe2,0x7e,0xb0,0x10
+
+# ATT: vcvtneebf162ps -1024(,%ebp,2), %ymm2
+# INTEL: vcvtneebf162ps ymm2, ymmword ptr [2*ebp - 1024]
+0xc4,0xe2,0x7e,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff
+
+# ATT: vcvtneebf162ps 4064(%ecx), %ymm2
+# INTEL: vcvtneebf162ps ymm2, ymmword ptr [ecx + 4064]
+0xc4,0xe2,0x7e,0xb0,0x91,0xe0,0x0f,0x00,0x00
+
+# ATT: vcvtneebf162ps -4096(%edx), %ymm2
+# INTEL: vcvtneebf162ps ymm2, ymmword ptr [edx - 4096]
+0xc4,0xe2,0x7e,0xb0,0x92,0x00,0xf0,0xff,0xff
+
+# ATT: vcvtneeph2ps 268435456(%esp,%esi,8), %xmm2
+# INTEL: vcvtneeph2ps xmm2, xmmword ptr [esp + 8*esi + 268435456]
+0xc4,0xe2,0x79,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10
+
+# ATT: vcvtneeph2ps 291(%edi,%eax,4), %xmm2
+# INTEL: vcvtneeph2ps xmm2, xmmword ptr [edi + 4*eax + 291]
+0xc4,0xe2,0x79,0xb0,0x94,0x87,0x23,0x01,0x00,0x00
+
+# ATT: vcvtneeph2ps (%eax), %xmm2
+# INTEL: vcvtneeph2ps xmm2, xmmword ptr [eax]
+0xc4,0xe2,0x79,0xb0,0x10
+
+# ATT: vcvtneeph2ps -512(,%ebp,2), %xmm2
+# INTEL: vcvtneeph2ps xmm2, xmmword ptr [2*ebp - 512]
+0xc4,0xe2,0x79,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff
+
+# ATT: vcvtneeph2ps 2032(%ecx), %xmm2
+# INTEL: vcvtneeph2ps xmm2, xmmword ptr [ecx + 2032]
+0xc4,0xe2,0x79,0xb0,0x91,0xf0,0x07,0x00,0x00
+
+# ATT: vcvtneeph2ps -2048(%edx), %xmm2
+# INTEL: vcvtneeph2ps xmm2, xmmword ptr [edx - 2048]
+0xc4,0xe2,0x79,0xb0,0x92,0x00,0xf8,0xff,0xff
+
+# ATT: vcvtneeph2ps 268435456(%esp,%esi,8), %ymm2
+# INTEL: vcvtneeph2ps ymm2, ymmword ptr [esp + 8*esi + 268435456]
+0xc4,0xe2,0x7d,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10
+
+# ATT: vcvtneeph2ps 291(%edi,%eax,4), %ymm2
+# INTEL: vcvtneeph2ps ymm2, ymmword ptr [edi + 4*eax + 291]
+0xc4,0xe2,0x7d,0xb0,0x94,0x87,0x23,0x01,0x00,0x00
+
+# ATT: vcvtneeph2ps (%eax), %ymm2
+# INTEL: vcvtneeph2ps ymm2, ymmword ptr [eax]
+0xc4,0xe2,0x7d,0xb0,0x10
+
+# ATT: vcvtneeph2ps -1024(,%ebp,2), %ymm2
+# INTEL: vcvtneeph2ps ymm2, ymmword ptr [2*ebp - 1024]
+0xc4,0xe2,0x7d,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff
+
+# ATT: vcvtneeph2ps 4064(%ecx), %ymm2
+# INTEL: vcvtneeph2ps ymm2, ymmword ptr [ecx + 4064]
+0xc4,0xe2,0x7d,0xb0,0x91,0xe0,0x0f,0x00,0x00
+
+# ATT: vcvtneeph2ps -4096(%edx), %ymm2
+# INTEL: vcvtneeph2ps ymm2, ymmword ptr [edx - 4096]
+0xc4,0xe2,0x7d,0xb0,0x92,0x00,0xf0,0xff,0xff
+
+# ATT: vcvtneobf162ps 268435456(%esp,%esi,8), %xmm2
+# INTEL: vcvtneobf162ps xmm2, xmmword ptr [esp + 8*esi + 268435456]
+0xc4,0xe2,0x7b,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10
+
+# ATT: vcvtneobf162ps 291(%edi,%eax,4), %xmm2
+# INTEL: vcvtneobf162ps xmm2, xmmword ptr [edi + 4*eax + 291]
+0xc4,0xe2,0x7b,0xb0,0x94,0x87,0x23,0x01,0x00,0x00
+
+# ATT: vcvtneobf162ps (%eax), %xmm2
+# INTEL: vcvtneobf162ps xmm2, xmmword ptr [eax]
+0xc4,0xe2,0x7b,0xb0,0x10
+
+# ATT: vcvtneobf162ps -512(,%ebp,2), %xmm2
+# INTEL: vcvtneobf162ps xmm2, xmmword ptr [2*ebp - 512]
+0xc4,0xe2,0x7b,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff
+
+# ATT: vcvtneobf162ps 2032(%ecx), %xmm2
+# INTEL: vcvtneobf162ps xmm2, xmmword ptr [ecx + 2032]
+0xc4,0xe2,0x7b,0xb0,0x91,0xf0,0x07,0x00,0x00
+
+# ATT: vcvtneobf162ps -2048(%edx), %xmm2
+# INTEL: vcvtneobf162ps xmm2, xmmword ptr [edx - 2048]
+0xc4,0xe2,0x7b,0xb0,0x92,0x00,0xf8,0xff,0xff
+
+# ATT: vcvtneobf162ps 268435456(%esp,%esi,8), %ymm2
+# INTEL: vcvtneobf162ps ymm2, ymmword ptr [esp + 8*esi + 268435456]
+0xc4,0xe2,0x7f,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10
+
+# ATT: vcvtneobf162ps 291(%edi,%eax,4), %ymm2
+# INTEL: vcvtneobf162ps ymm2, ymmword ptr [edi + 4*eax + 291]
+0xc4,0xe2,0x7f,0xb0,0x94,0x87,0x23,0x01,0x00,0x00
+
+# ATT: vcvtneobf162ps (%eax), %ymm2
+# INTEL: vcvtneobf162ps ymm2, ymmword ptr [eax]
+0xc4,0xe2,0x7f,0xb0,0x10
+
+# ATT: vcvtneobf162ps -1024(,%ebp,2), %ymm2
+# INTEL: vcvtneobf162ps ymm2, ymmword ptr [2*ebp - 1024]
+0xc4,0xe2,0x7f,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff
+
+# ATT: vcvtneobf162ps 4064(%ecx), %ymm2
+# INTEL: vcvtneobf162ps ymm2, ymmword ptr [ecx + 4064]
+0xc4,0xe2,0x7f,0xb0,0x91,0xe0,0x0f,0x00,0x00
+
+# ATT: vcvtneobf162ps -4096(%edx), %ymm2
+# INTEL: vcvtneobf162ps ymm2, ymmword ptr [edx - 4096]
+0xc4,0xe2,0x7f,0xb0,0x92,0x00,0xf0,0xff,0xff
+
+# ATT: vcvtneoph2ps 268435456(%esp,%esi,8), %xmm2
+# INTEL: vcvtneoph2ps xmm2, xmmword ptr [esp + 8*esi + 268435456]
+0xc4,0xe2,0x78,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10
+
+# ATT: vcvtneoph2ps 291(%edi,%eax,4), %xmm2
+# INTEL: vcvtneoph2ps xmm2, xmmword ptr [edi + 4*eax + 291]
+0xc4,0xe2,0x78,0xb0,0x94,0x87,0x23,0x01,0x00,0x00
+
+# ATT: vcvtneoph2ps (%eax), %xmm2
+# INTEL: vcvtneoph2ps xmm2, xmmword ptr [eax]
+0xc4,0xe2,0x78,0xb0,0x10
+
+# ATT: vcvtneoph2ps -512(,%ebp,2), %xmm2
+# INTEL: vcvtneoph2ps xmm2, xmmword ptr [2*ebp - 512]
+0xc4,0xe2,0x78,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff
+
+# ATT: vcvtneoph2ps 2032(%ecx), %xmm2
+# INTEL: vcvtneoph2ps xmm2, xmmword ptr [ecx + 2032]
+0xc4,0xe2,0x78,0xb0,0x91,0xf0,0x07,0x00,0x00
+
+# ATT: vcvtneoph2ps -2048(%edx), %xmm2
+# INTEL: vcvtneoph2ps xmm2, xmmword ptr [edx - 2048]
+0xc4,0xe2,0x78,0xb0,0x92,0x00,0xf8,0xff,0xff
+
+# ATT: vcvtneoph2ps 268435456(%esp,%esi,8), %ymm2
+# INTEL: vcvtneoph2ps ymm2, ymmword ptr [esp + 8*esi + 268435456]
+0xc4,0xe2,0x7c,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10
+
+# ATT: vcvtneoph2ps 291(%edi,%eax,4), %ymm2
+# INTEL: vcvtneoph2ps ymm2, ymmword ptr [edi + 4*eax + 291]
+0xc4,0xe2,0x7c,0xb0,0x94,0x87,0x23,0x01,0x00,0x00
+
+# ATT: vcvtneoph2ps (%eax), %ymm2
+# INTEL: vcvtneoph2ps ymm2, ymmword ptr [eax]
+0xc4,0xe2,0x7c,0xb0,0x10
+
+# ATT: vcvtneoph2ps -1024(,%ebp,2), %ymm2
+# INTEL: vcvtneoph2ps ymm2, ymmword ptr [2*ebp - 1024]
+0xc4,0xe2,0x7c,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff
+
+# ATT: vcvtneoph2ps 4064(%ecx), %ymm2
+# INTEL: vcvtneoph2ps ymm2, ymmword ptr [ecx + 4064]
+0xc4,0xe2,0x7c,0xb0,0x91,0xe0,0x0f,0x00,0x00
+
+# ATT: vcvtneoph2ps -4096(%edx), %ymm2
+# INTEL: vcvtneoph2ps ymm2, ymmword ptr [edx - 4096]
+0xc4,0xe2,0x7c,0xb0,0x92,0x00,0xf0,0xff,0xff
+
+# ATT: {vex} vcvtneps2bf16 %xmm3, %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, xmm3
+0xc4,0xe2,0x7a,0x72,0xd3
+
+# ATT: {vex} vcvtneps2bf16 %ymm3, %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, ymm3
+0xc4,0xe2,0x7e,0x72,0xd3
+
+# ATT: {vex} vcvtneps2bf16x 268435456(%esp,%esi,8), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, xmmword ptr [esp + 8*esi + 268435456]
+0xc4,0xe2,0x7a,0x72,0x94,0xf4,0x00,0x00,0x00,0x10
+
+# ATT: {vex} vcvtneps2bf16x 291(%edi,%eax,4), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, xmmword ptr [edi + 4*eax + 291]
+0xc4,0xe2,0x7a,0x72,0x94,0x87,0x23,0x01,0x00,0x00
+
+# ATT: {vex} vcvtneps2bf16x (%eax), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, xmmword ptr [eax]
+0xc4,0xe2,0x7a,0x72,0x10
+
+# ATT: {vex} vcvtneps2bf16x -512(,%ebp,2), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, xmmword ptr [2*ebp - 512]
+0xc4,0xe2,0x7a,0x72,0x14,0x6d,0x00,0xfe,0xff,0xff
+
+# ATT: {vex} vcvtneps2bf16x 2032(%ecx), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, xmmword ptr [ecx + 2032]
+0xc4,0xe2,0x7a,0x72,0x91,0xf0,0x07,0x00,0x00
+
+# ATT: {vex} vcvtneps2bf16x -2048(%edx), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, xmmword ptr [edx - 2048]
+0xc4,0xe2,0x7a,0x72,0x92,0x00,0xf8,0xff,0xff
+
+# ATT: {vex} vcvtneps2bf16y -1024(,%ebp,2), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, ymmword ptr [2*ebp - 1024]
+0xc4,0xe2,0x7e,0x72,0x14,0x6d,0x00,0xfc,0xff,0xff
+
+# ATT: {vex} vcvtneps2bf16y 4064(%ecx), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, ymmword ptr [ecx + 4064]
+0xc4,0xe2,0x7e,0x72,0x91,0xe0,0x0f,0x00,0x00
+
+# ATT: {vex} vcvtneps2bf16y -4096(%edx), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, ymmword ptr [edx - 4096]
+0xc4,0xe2,0x7e,0x72,0x92,0x00,0xf0,0xff,0xff
+
--- /dev/null
+# RUN: llvm-mc --disassemble %s -triple=x86_64 | FileCheck %s --check-prefixes=ATT
+# RUN: llvm-mc --disassemble %s -triple=x86_64 -x86-asm-syntax=intel --output-asm-variant=1 | FileCheck %s --check-prefixes=INTEL
+
+# ATT: vbcstnebf162ps 268435456(%rbp,%r14,8), %xmm2
+# INTEL: vbcstnebf162ps xmm2, word ptr [rbp + 8*r14 + 268435456]
+0xc4,0xa2,0x7a,0xb1,0x94,0xf5,0x00,0x00,0x00,0x10
+
+# ATT: vbcstnebf162ps 291(%r8,%rax,4), %xmm2
+# INTEL: vbcstnebf162ps xmm2, word ptr [r8 + 4*rax + 291]
+0xc4,0xc2,0x7a,0xb1,0x94,0x80,0x23,0x01,0x00,0x00
+
+# ATT: vbcstnebf162ps (%rip), %xmm2
+# INTEL: vbcstnebf162ps xmm2, word ptr [rip]
+0xc4,0xe2,0x7a,0xb1,0x15,0x00,0x00,0x00,0x00
+
+# ATT: vbcstnebf162ps -64(,%rbp,2), %xmm2
+# INTEL: vbcstnebf162ps xmm2, word ptr [2*rbp - 64]
+0xc4,0xe2,0x7a,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff
+
+# ATT: vbcstnebf162ps 254(%rcx), %xmm2
+# INTEL: vbcstnebf162ps xmm2, word ptr [rcx + 254]
+0xc4,0xe2,0x7a,0xb1,0x91,0xfe,0x00,0x00,0x00
+
+# ATT: vbcstnebf162ps -256(%rdx), %xmm2
+# INTEL: vbcstnebf162ps xmm2, word ptr [rdx - 256]
+0xc4,0xe2,0x7a,0xb1,0x92,0x00,0xff,0xff,0xff
+
+# ATT: vbcstnebf162ps 268435456(%rbp,%r14,8), %ymm2
+# INTEL: vbcstnebf162ps ymm2, word ptr [rbp + 8*r14 + 268435456]
+0xc4,0xa2,0x7e,0xb1,0x94,0xf5,0x00,0x00,0x00,0x10
+
+# ATT: vbcstnebf162ps 291(%r8,%rax,4), %ymm2
+# INTEL: vbcstnebf162ps ymm2, word ptr [r8 + 4*rax + 291]
+0xc4,0xc2,0x7e,0xb1,0x94,0x80,0x23,0x01,0x00,0x00
+
+# ATT: vbcstnebf162ps (%rip), %ymm2
+# INTEL: vbcstnebf162ps ymm2, word ptr [rip]
+0xc4,0xe2,0x7e,0xb1,0x15,0x00,0x00,0x00,0x00
+
+# ATT: vbcstnebf162ps -64(,%rbp,2), %ymm2
+# INTEL: vbcstnebf162ps ymm2, word ptr [2*rbp - 64]
+0xc4,0xe2,0x7e,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff
+
+# ATT: vbcstnebf162ps 254(%rcx), %ymm2
+# INTEL: vbcstnebf162ps ymm2, word ptr [rcx + 254]
+0xc4,0xe2,0x7e,0xb1,0x91,0xfe,0x00,0x00,0x00
+
+# ATT: vbcstnebf162ps -256(%rdx), %ymm2
+# INTEL: vbcstnebf162ps ymm2, word ptr [rdx - 256]
+0xc4,0xe2,0x7e,0xb1,0x92,0x00,0xff,0xff,0xff
+
+# ATT: vbcstnesh2ps 268435456(%rbp,%r14,8), %xmm2
+# INTEL: vbcstnesh2ps xmm2, word ptr [rbp + 8*r14 + 268435456]
+0xc4,0xa2,0x79,0xb1,0x94,0xf5,0x00,0x00,0x00,0x10
+
+# ATT: vbcstnesh2ps 291(%r8,%rax,4), %xmm2
+# INTEL: vbcstnesh2ps xmm2, word ptr [r8 + 4*rax + 291]
+0xc4,0xc2,0x79,0xb1,0x94,0x80,0x23,0x01,0x00,0x00
+
+# ATT: vbcstnesh2ps (%rip), %xmm2
+# INTEL: vbcstnesh2ps xmm2, word ptr [rip]
+0xc4,0xe2,0x79,0xb1,0x15,0x00,0x00,0x00,0x00
+
+# ATT: vbcstnesh2ps -64(,%rbp,2), %xmm2
+# INTEL: vbcstnesh2ps xmm2, word ptr [2*rbp - 64]
+0xc4,0xe2,0x79,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff
+
+# ATT: vbcstnesh2ps 254(%rcx), %xmm2
+# INTEL: vbcstnesh2ps xmm2, word ptr [rcx + 254]
+0xc4,0xe2,0x79,0xb1,0x91,0xfe,0x00,0x00,0x00
+
+# ATT: vbcstnesh2ps -256(%rdx), %xmm2
+# INTEL: vbcstnesh2ps xmm2, word ptr [rdx - 256]
+0xc4,0xe2,0x79,0xb1,0x92,0x00,0xff,0xff,0xff
+
+# ATT: vbcstnesh2ps 268435456(%rbp,%r14,8), %ymm2
+# INTEL: vbcstnesh2ps ymm2, word ptr [rbp + 8*r14 + 268435456]
+0xc4,0xa2,0x7d,0xb1,0x94,0xf5,0x00,0x00,0x00,0x10
+
+# ATT: vbcstnesh2ps 291(%r8,%rax,4), %ymm2
+# INTEL: vbcstnesh2ps ymm2, word ptr [r8 + 4*rax + 291]
+0xc4,0xc2,0x7d,0xb1,0x94,0x80,0x23,0x01,0x00,0x00
+
+# ATT: vbcstnesh2ps (%rip), %ymm2
+# INTEL: vbcstnesh2ps ymm2, word ptr [rip]
+0xc4,0xe2,0x7d,0xb1,0x15,0x00,0x00,0x00,0x00
+
+# ATT: vbcstnesh2ps -64(,%rbp,2), %ymm2
+# INTEL: vbcstnesh2ps ymm2, word ptr [2*rbp - 64]
+0xc4,0xe2,0x7d,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff
+
+# ATT: vbcstnesh2ps 254(%rcx), %ymm2
+# INTEL: vbcstnesh2ps ymm2, word ptr [rcx + 254]
+0xc4,0xe2,0x7d,0xb1,0x91,0xfe,0x00,0x00,0x00
+
+# ATT: vbcstnesh2ps -256(%rdx), %ymm2
+# INTEL: vbcstnesh2ps ymm2, word ptr [rdx - 256]
+0xc4,0xe2,0x7d,0xb1,0x92,0x00,0xff,0xff,0xff
+
+# ATT: vcvtneebf162ps 268435456(%rbp,%r14,8), %xmm2
+# INTEL: vcvtneebf162ps xmm2, xmmword ptr [rbp + 8*r14 + 268435456]
+0xc4,0xa2,0x7a,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10
+
+# ATT: vcvtneebf162ps 291(%r8,%rax,4), %xmm2
+# INTEL: vcvtneebf162ps xmm2, xmmword ptr [r8 + 4*rax + 291]
+0xc4,0xc2,0x7a,0xb0,0x94,0x80,0x23,0x01,0x00,0x00
+
+# ATT: vcvtneebf162ps (%rip), %xmm2
+# INTEL: vcvtneebf162ps xmm2, xmmword ptr [rip]
+0xc4,0xe2,0x7a,0xb0,0x15,0x00,0x00,0x00,0x00
+
+# ATT: vcvtneebf162ps -512(,%rbp,2), %xmm2
+# INTEL: vcvtneebf162ps xmm2, xmmword ptr [2*rbp - 512]
+0xc4,0xe2,0x7a,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff
+
+# ATT: vcvtneebf162ps 2032(%rcx), %xmm2
+# INTEL: vcvtneebf162ps xmm2, xmmword ptr [rcx + 2032]
+0xc4,0xe2,0x7a,0xb0,0x91,0xf0,0x07,0x00,0x00
+
+# ATT: vcvtneebf162ps -2048(%rdx), %xmm2
+# INTEL: vcvtneebf162ps xmm2, xmmword ptr [rdx - 2048]
+0xc4,0xe2,0x7a,0xb0,0x92,0x00,0xf8,0xff,0xff
+
+# ATT: vcvtneebf162ps 268435456(%rbp,%r14,8), %ymm2
+# INTEL: vcvtneebf162ps ymm2, ymmword ptr [rbp + 8*r14 + 268435456]
+0xc4,0xa2,0x7e,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10
+
+# ATT: vcvtneebf162ps 291(%r8,%rax,4), %ymm2
+# INTEL: vcvtneebf162ps ymm2, ymmword ptr [r8 + 4*rax + 291]
+0xc4,0xc2,0x7e,0xb0,0x94,0x80,0x23,0x01,0x00,0x00
+
+# ATT: vcvtneebf162ps (%rip), %ymm2
+# INTEL: vcvtneebf162ps ymm2, ymmword ptr [rip]
+0xc4,0xe2,0x7e,0xb0,0x15,0x00,0x00,0x00,0x00
+
+# ATT: vcvtneebf162ps -1024(,%rbp,2), %ymm2
+# INTEL: vcvtneebf162ps ymm2, ymmword ptr [2*rbp - 1024]
+0xc4,0xe2,0x7e,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff
+
+# ATT: vcvtneebf162ps 4064(%rcx), %ymm2
+# INTEL: vcvtneebf162ps ymm2, ymmword ptr [rcx + 4064]
+0xc4,0xe2,0x7e,0xb0,0x91,0xe0,0x0f,0x00,0x00
+
+# ATT: vcvtneebf162ps -4096(%rdx), %ymm2
+# INTEL: vcvtneebf162ps ymm2, ymmword ptr [rdx - 4096]
+0xc4,0xe2,0x7e,0xb0,0x92,0x00,0xf0,0xff,0xff
+
+# ATT: vcvtneeph2ps 268435456(%rbp,%r14,8), %xmm2
+# INTEL: vcvtneeph2ps xmm2, xmmword ptr [rbp + 8*r14 + 268435456]
+0xc4,0xa2,0x79,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10
+
+# ATT: vcvtneeph2ps 291(%r8,%rax,4), %xmm2
+# INTEL: vcvtneeph2ps xmm2, xmmword ptr [r8 + 4*rax + 291]
+0xc4,0xc2,0x79,0xb0,0x94,0x80,0x23,0x01,0x00,0x00
+
+# ATT: vcvtneeph2ps (%rip), %xmm2
+# INTEL: vcvtneeph2ps xmm2, xmmword ptr [rip]
+0xc4,0xe2,0x79,0xb0,0x15,0x00,0x00,0x00,0x00
+
+# ATT: vcvtneeph2ps -512(,%rbp,2), %xmm2
+# INTEL: vcvtneeph2ps xmm2, xmmword ptr [2*rbp - 512]
+0xc4,0xe2,0x79,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff
+
+# ATT: vcvtneeph2ps 2032(%rcx), %xmm2
+# INTEL: vcvtneeph2ps xmm2, xmmword ptr [rcx + 2032]
+0xc4,0xe2,0x79,0xb0,0x91,0xf0,0x07,0x00,0x00
+
+# ATT: vcvtneeph2ps -2048(%rdx), %xmm2
+# INTEL: vcvtneeph2ps xmm2, xmmword ptr [rdx - 2048]
+0xc4,0xe2,0x79,0xb0,0x92,0x00,0xf8,0xff,0xff
+
+# ATT: vcvtneeph2ps 268435456(%rbp,%r14,8), %ymm2
+# INTEL: vcvtneeph2ps ymm2, ymmword ptr [rbp + 8*r14 + 268435456]
+0xc4,0xa2,0x7d,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10
+
+# ATT: vcvtneeph2ps 291(%r8,%rax,4), %ymm2
+# INTEL: vcvtneeph2ps ymm2, ymmword ptr [r8 + 4*rax + 291]
+0xc4,0xc2,0x7d,0xb0,0x94,0x80,0x23,0x01,0x00,0x00
+
+# ATT: vcvtneeph2ps (%rip), %ymm2
+# INTEL: vcvtneeph2ps ymm2, ymmword ptr [rip]
+0xc4,0xe2,0x7d,0xb0,0x15,0x00,0x00,0x00,0x00
+
+# ATT: vcvtneeph2ps -1024(,%rbp,2), %ymm2
+# INTEL: vcvtneeph2ps ymm2, ymmword ptr [2*rbp - 1024]
+0xc4,0xe2,0x7d,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff
+
+# ATT: vcvtneeph2ps 4064(%rcx), %ymm2
+# INTEL: vcvtneeph2ps ymm2, ymmword ptr [rcx + 4064]
+0xc4,0xe2,0x7d,0xb0,0x91,0xe0,0x0f,0x00,0x00
+
+# ATT: vcvtneeph2ps -4096(%rdx), %ymm2
+# INTEL: vcvtneeph2ps ymm2, ymmword ptr [rdx - 4096]
+0xc4,0xe2,0x7d,0xb0,0x92,0x00,0xf0,0xff,0xff
+
+# ATT: vcvtneobf162ps 268435456(%rbp,%r14,8), %xmm2
+# INTEL: vcvtneobf162ps xmm2, xmmword ptr [rbp + 8*r14 + 268435456]
+0xc4,0xa2,0x7b,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10
+
+# ATT: vcvtneobf162ps 291(%r8,%rax,4), %xmm2
+# INTEL: vcvtneobf162ps xmm2, xmmword ptr [r8 + 4*rax + 291]
+0xc4,0xc2,0x7b,0xb0,0x94,0x80,0x23,0x01,0x00,0x00
+
+# ATT: vcvtneobf162ps (%rip), %xmm2
+# INTEL: vcvtneobf162ps xmm2, xmmword ptr [rip]
+0xc4,0xe2,0x7b,0xb0,0x15,0x00,0x00,0x00,0x00
+
+# ATT: vcvtneobf162ps -512(,%rbp,2), %xmm2
+# INTEL: vcvtneobf162ps xmm2, xmmword ptr [2*rbp - 512]
+0xc4,0xe2,0x7b,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff
+
+# ATT: vcvtneobf162ps 2032(%rcx), %xmm2
+# INTEL: vcvtneobf162ps xmm2, xmmword ptr [rcx + 2032]
+0xc4,0xe2,0x7b,0xb0,0x91,0xf0,0x07,0x00,0x00
+
+# ATT: vcvtneobf162ps -2048(%rdx), %xmm2
+# INTEL: vcvtneobf162ps xmm2, xmmword ptr [rdx - 2048]
+0xc4,0xe2,0x7b,0xb0,0x92,0x00,0xf8,0xff,0xff
+
+# ATT: vcvtneobf162ps 268435456(%rbp,%r14,8), %ymm2
+# INTEL: vcvtneobf162ps ymm2, ymmword ptr [rbp + 8*r14 + 268435456]
+0xc4,0xa2,0x7f,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10
+
+# ATT: vcvtneobf162ps 291(%r8,%rax,4), %ymm2
+# INTEL: vcvtneobf162ps ymm2, ymmword ptr [r8 + 4*rax + 291]
+0xc4,0xc2,0x7f,0xb0,0x94,0x80,0x23,0x01,0x00,0x00
+
+# ATT: vcvtneobf162ps (%rip), %ymm2
+# INTEL: vcvtneobf162ps ymm2, ymmword ptr [rip]
+0xc4,0xe2,0x7f,0xb0,0x15,0x00,0x00,0x00,0x00
+
+# ATT: vcvtneobf162ps -1024(,%rbp,2), %ymm2
+# INTEL: vcvtneobf162ps ymm2, ymmword ptr [2*rbp - 1024]
+0xc4,0xe2,0x7f,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff
+
+# ATT: vcvtneobf162ps 4064(%rcx), %ymm2
+# INTEL: vcvtneobf162ps ymm2, ymmword ptr [rcx + 4064]
+0xc4,0xe2,0x7f,0xb0,0x91,0xe0,0x0f,0x00,0x00
+
+# ATT: vcvtneobf162ps -4096(%rdx), %ymm2
+# INTEL: vcvtneobf162ps ymm2, ymmword ptr [rdx - 4096]
+0xc4,0xe2,0x7f,0xb0,0x92,0x00,0xf0,0xff,0xff
+
+# ATT: vcvtneoph2ps 268435456(%rbp,%r14,8), %xmm2
+# INTEL: vcvtneoph2ps xmm2, xmmword ptr [rbp + 8*r14 + 268435456]
+0xc4,0xa2,0x78,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10
+
+# ATT: vcvtneoph2ps 291(%r8,%rax,4), %xmm2
+# INTEL: vcvtneoph2ps xmm2, xmmword ptr [r8 + 4*rax + 291]
+0xc4,0xc2,0x78,0xb0,0x94,0x80,0x23,0x01,0x00,0x00
+
+# ATT: vcvtneoph2ps (%rip), %xmm2
+# INTEL: vcvtneoph2ps xmm2, xmmword ptr [rip]
+0xc4,0xe2,0x78,0xb0,0x15,0x00,0x00,0x00,0x00
+
+# ATT: vcvtneoph2ps -512(,%rbp,2), %xmm2
+# INTEL: vcvtneoph2ps xmm2, xmmword ptr [2*rbp - 512]
+0xc4,0xe2,0x78,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff
+
+# ATT: vcvtneoph2ps 2032(%rcx), %xmm2
+# INTEL: vcvtneoph2ps xmm2, xmmword ptr [rcx + 2032]
+0xc4,0xe2,0x78,0xb0,0x91,0xf0,0x07,0x00,0x00
+
+# ATT: vcvtneoph2ps -2048(%rdx), %xmm2
+# INTEL: vcvtneoph2ps xmm2, xmmword ptr [rdx - 2048]
+0xc4,0xe2,0x78,0xb0,0x92,0x00,0xf8,0xff,0xff
+
+# ATT: vcvtneoph2ps 268435456(%rbp,%r14,8), %ymm2
+# INTEL: vcvtneoph2ps ymm2, ymmword ptr [rbp + 8*r14 + 268435456]
+0xc4,0xa2,0x7c,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10
+
+# ATT: vcvtneoph2ps 291(%r8,%rax,4), %ymm2
+# INTEL: vcvtneoph2ps ymm2, ymmword ptr [r8 + 4*rax + 291]
+0xc4,0xc2,0x7c,0xb0,0x94,0x80,0x23,0x01,0x00,0x00
+
+# ATT: vcvtneoph2ps (%rip), %ymm2
+# INTEL: vcvtneoph2ps ymm2, ymmword ptr [rip]
+0xc4,0xe2,0x7c,0xb0,0x15,0x00,0x00,0x00,0x00
+
+# ATT: vcvtneoph2ps -1024(,%rbp,2), %ymm2
+# INTEL: vcvtneoph2ps ymm2, ymmword ptr [2*rbp - 1024]
+0xc4,0xe2,0x7c,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff
+
+# ATT: vcvtneoph2ps 4064(%rcx), %ymm2
+# INTEL: vcvtneoph2ps ymm2, ymmword ptr [rcx + 4064]
+0xc4,0xe2,0x7c,0xb0,0x91,0xe0,0x0f,0x00,0x00
+
+# ATT: vcvtneoph2ps -4096(%rdx), %ymm2
+# INTEL: vcvtneoph2ps ymm2, ymmword ptr [rdx - 4096]
+0xc4,0xe2,0x7c,0xb0,0x92,0x00,0xf0,0xff,0xff
+
+# ATT: {vex} vcvtneps2bf16 %xmm3, %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, xmm3
+0xc4,0xe2,0x7a,0x72,0xd3
+
+# ATT: {vex} vcvtneps2bf16 %ymm3, %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, ymm3
+0xc4,0xe2,0x7e,0x72,0xd3
+
+# ATT: {vex} vcvtneps2bf16x 268435456(%rbp,%r14,8), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, xmmword ptr [rbp + 8*r14 + 268435456]
+0xc4,0xa2,0x7a,0x72,0x94,0xf5,0x00,0x00,0x00,0x10
+
+# ATT: {vex} vcvtneps2bf16x 291(%r8,%rax,4), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, xmmword ptr [r8 + 4*rax + 291]
+0xc4,0xc2,0x7a,0x72,0x94,0x80,0x23,0x01,0x00,0x00
+
+# ATT: {vex} vcvtneps2bf16x (%rip), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, xmmword ptr [rip]
+0xc4,0xe2,0x7a,0x72,0x15,0x00,0x00,0x00,0x00
+
+# ATT: {vex} vcvtneps2bf16x -512(,%rbp,2), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, xmmword ptr [2*rbp - 512]
+0xc4,0xe2,0x7a,0x72,0x14,0x6d,0x00,0xfe,0xff,0xff
+
+# ATT: {vex} vcvtneps2bf16x 2032(%rcx), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, xmmword ptr [rcx + 2032]
+0xc4,0xe2,0x7a,0x72,0x91,0xf0,0x07,0x00,0x00
+
+# ATT: {vex} vcvtneps2bf16x -2048(%rdx), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, xmmword ptr [rdx - 2048]
+0xc4,0xe2,0x7a,0x72,0x92,0x00,0xf8,0xff,0xff
+
+# ATT: {vex} vcvtneps2bf16y -1024(,%rbp,2), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, ymmword ptr [2*rbp - 1024]
+0xc4,0xe2,0x7e,0x72,0x14,0x6d,0x00,0xfc,0xff,0xff
+
+# ATT: {vex} vcvtneps2bf16y 4064(%rcx), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, ymmword ptr [rcx + 4064]
+0xc4,0xe2,0x7e,0x72,0x91,0xe0,0x0f,0x00,0x00
+
+# ATT: {vex} vcvtneps2bf16y -4096(%rdx), %xmm2
+# INTEL: {vex} vcvtneps2bf16 xmm2, ymmword ptr [rdx - 4096]
+0xc4,0xe2,0x7e,0x72,0x92,0x00,0xf0,0xff,0xff
+
--- /dev/null
+// RUN: llvm-mc -triple i686-unknown-unknown --show-encoding %s | FileCheck %s
+
+// CHECK: vbcstnebf162ps 268435456(%esp,%esi,8), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vbcstnebf162ps 268435456(%esp,%esi,8), %xmm2
+
+// CHECK: vbcstnebf162ps 291(%edi,%eax,4), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x94,0x87,0x23,0x01,0x00,0x00]
+ vbcstnebf162ps 291(%edi,%eax,4), %xmm2
+
+// CHECK: vbcstnebf162ps (%eax), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x10]
+ vbcstnebf162ps (%eax), %xmm2
+
+// CHECK: vbcstnebf162ps -64(,%ebp,2), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff]
+ vbcstnebf162ps -64(,%ebp,2), %xmm2
+
+// CHECK: vbcstnebf162ps 254(%ecx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x91,0xfe,0x00,0x00,0x00]
+ vbcstnebf162ps 254(%ecx), %xmm2
+
+// CHECK: vbcstnebf162ps -256(%edx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x92,0x00,0xff,0xff,0xff]
+ vbcstnebf162ps -256(%edx), %xmm2
+
+// CHECK: vbcstnebf162ps 268435456(%esp,%esi,8), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vbcstnebf162ps 268435456(%esp,%esi,8), %ymm2
+
+// CHECK: vbcstnebf162ps 291(%edi,%eax,4), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x94,0x87,0x23,0x01,0x00,0x00]
+ vbcstnebf162ps 291(%edi,%eax,4), %ymm2
+
+// CHECK: vbcstnebf162ps (%eax), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x10]
+ vbcstnebf162ps (%eax), %ymm2
+
+// CHECK: vbcstnebf162ps -64(,%ebp,2), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff]
+ vbcstnebf162ps -64(,%ebp,2), %ymm2
+
+// CHECK: vbcstnebf162ps 254(%ecx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x91,0xfe,0x00,0x00,0x00]
+ vbcstnebf162ps 254(%ecx), %ymm2
+
+// CHECK: vbcstnebf162ps -256(%edx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x92,0x00,0xff,0xff,0xff]
+ vbcstnebf162ps -256(%edx), %ymm2
+
+// CHECK: vbcstnesh2ps 268435456(%esp,%esi,8), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vbcstnesh2ps 268435456(%esp,%esi,8), %xmm2
+
+// CHECK: vbcstnesh2ps 291(%edi,%eax,4), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x94,0x87,0x23,0x01,0x00,0x00]
+ vbcstnesh2ps 291(%edi,%eax,4), %xmm2
+
+// CHECK: vbcstnesh2ps (%eax), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x10]
+ vbcstnesh2ps (%eax), %xmm2
+
+// CHECK: vbcstnesh2ps -64(,%ebp,2), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff]
+ vbcstnesh2ps -64(,%ebp,2), %xmm2
+
+// CHECK: vbcstnesh2ps 254(%ecx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x91,0xfe,0x00,0x00,0x00]
+ vbcstnesh2ps 254(%ecx), %xmm2
+
+// CHECK: vbcstnesh2ps -256(%edx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x92,0x00,0xff,0xff,0xff]
+ vbcstnesh2ps -256(%edx), %xmm2
+
+// CHECK: vbcstnesh2ps 268435456(%esp,%esi,8), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vbcstnesh2ps 268435456(%esp,%esi,8), %ymm2
+
+// CHECK: vbcstnesh2ps 291(%edi,%eax,4), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x94,0x87,0x23,0x01,0x00,0x00]
+ vbcstnesh2ps 291(%edi,%eax,4), %ymm2
+
+// CHECK: vbcstnesh2ps (%eax), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x10]
+ vbcstnesh2ps (%eax), %ymm2
+
+// CHECK: vbcstnesh2ps -64(,%ebp,2), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff]
+ vbcstnesh2ps -64(,%ebp,2), %ymm2
+
+// CHECK: vbcstnesh2ps 254(%ecx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x91,0xfe,0x00,0x00,0x00]
+ vbcstnesh2ps 254(%ecx), %ymm2
+
+// CHECK: vbcstnesh2ps -256(%edx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x92,0x00,0xff,0xff,0xff]
+ vbcstnesh2ps -256(%edx), %ymm2
+
+// CHECK: vcvtneebf162ps 268435456(%esp,%esi,8), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vcvtneebf162ps 268435456(%esp,%esi,8), %xmm2
+
+// CHECK: vcvtneebf162ps 291(%edi,%eax,4), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x94,0x87,0x23,0x01,0x00,0x00]
+ vcvtneebf162ps 291(%edi,%eax,4), %xmm2
+
+// CHECK: vcvtneebf162ps (%eax), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x10]
+ vcvtneebf162ps (%eax), %xmm2
+
+// CHECK: vcvtneebf162ps -512(,%ebp,2), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ vcvtneebf162ps -512(,%ebp,2), %xmm2
+
+// CHECK: vcvtneebf162ps 2032(%ecx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x91,0xf0,0x07,0x00,0x00]
+ vcvtneebf162ps 2032(%ecx), %xmm2
+
+// CHECK: vcvtneebf162ps -2048(%edx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x92,0x00,0xf8,0xff,0xff]
+ vcvtneebf162ps -2048(%edx), %xmm2
+
+// CHECK: vcvtneebf162ps 268435456(%esp,%esi,8), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vcvtneebf162ps 268435456(%esp,%esi,8), %ymm2
+
+// CHECK: vcvtneebf162ps 291(%edi,%eax,4), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x94,0x87,0x23,0x01,0x00,0x00]
+ vcvtneebf162ps 291(%edi,%eax,4), %ymm2
+
+// CHECK: vcvtneebf162ps (%eax), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x10]
+ vcvtneebf162ps (%eax), %ymm2
+
+// CHECK: vcvtneebf162ps -1024(,%ebp,2), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ vcvtneebf162ps -1024(,%ebp,2), %ymm2
+
+// CHECK: vcvtneebf162ps 4064(%ecx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x91,0xe0,0x0f,0x00,0x00]
+ vcvtneebf162ps 4064(%ecx), %ymm2
+
+// CHECK: vcvtneebf162ps -4096(%edx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x92,0x00,0xf0,0xff,0xff]
+ vcvtneebf162ps -4096(%edx), %ymm2
+
+// CHECK: vcvtneeph2ps 268435456(%esp,%esi,8), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vcvtneeph2ps 268435456(%esp,%esi,8), %xmm2
+
+// CHECK: vcvtneeph2ps 291(%edi,%eax,4), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x94,0x87,0x23,0x01,0x00,0x00]
+ vcvtneeph2ps 291(%edi,%eax,4), %xmm2
+
+// CHECK: vcvtneeph2ps (%eax), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x10]
+ vcvtneeph2ps (%eax), %xmm2
+
+// CHECK: vcvtneeph2ps -512(,%ebp,2), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ vcvtneeph2ps -512(,%ebp,2), %xmm2
+
+// CHECK: vcvtneeph2ps 2032(%ecx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x91,0xf0,0x07,0x00,0x00]
+ vcvtneeph2ps 2032(%ecx), %xmm2
+
+// CHECK: vcvtneeph2ps -2048(%edx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x92,0x00,0xf8,0xff,0xff]
+ vcvtneeph2ps -2048(%edx), %xmm2
+
+// CHECK: vcvtneeph2ps 268435456(%esp,%esi,8), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vcvtneeph2ps 268435456(%esp,%esi,8), %ymm2
+
+// CHECK: vcvtneeph2ps 291(%edi,%eax,4), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x94,0x87,0x23,0x01,0x00,0x00]
+ vcvtneeph2ps 291(%edi,%eax,4), %ymm2
+
+// CHECK: vcvtneeph2ps (%eax), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x10]
+ vcvtneeph2ps (%eax), %ymm2
+
+// CHECK: vcvtneeph2ps -1024(,%ebp,2), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ vcvtneeph2ps -1024(,%ebp,2), %ymm2
+
+// CHECK: vcvtneeph2ps 4064(%ecx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x91,0xe0,0x0f,0x00,0x00]
+ vcvtneeph2ps 4064(%ecx), %ymm2
+
+// CHECK: vcvtneeph2ps -4096(%edx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x92,0x00,0xf0,0xff,0xff]
+ vcvtneeph2ps -4096(%edx), %ymm2
+
+// CHECK: vcvtneobf162ps 268435456(%esp,%esi,8), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vcvtneobf162ps 268435456(%esp,%esi,8), %xmm2
+
+// CHECK: vcvtneobf162ps 291(%edi,%eax,4), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x94,0x87,0x23,0x01,0x00,0x00]
+ vcvtneobf162ps 291(%edi,%eax,4), %xmm2
+
+// CHECK: vcvtneobf162ps (%eax), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x10]
+ vcvtneobf162ps (%eax), %xmm2
+
+// CHECK: vcvtneobf162ps -512(,%ebp,2), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ vcvtneobf162ps -512(,%ebp,2), %xmm2
+
+// CHECK: vcvtneobf162ps 2032(%ecx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x91,0xf0,0x07,0x00,0x00]
+ vcvtneobf162ps 2032(%ecx), %xmm2
+
+// CHECK: vcvtneobf162ps -2048(%edx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x92,0x00,0xf8,0xff,0xff]
+ vcvtneobf162ps -2048(%edx), %xmm2
+
+// CHECK: vcvtneobf162ps 268435456(%esp,%esi,8), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vcvtneobf162ps 268435456(%esp,%esi,8), %ymm2
+
+// CHECK: vcvtneobf162ps 291(%edi,%eax,4), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x94,0x87,0x23,0x01,0x00,0x00]
+ vcvtneobf162ps 291(%edi,%eax,4), %ymm2
+
+// CHECK: vcvtneobf162ps (%eax), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x10]
+ vcvtneobf162ps (%eax), %ymm2
+
+// CHECK: vcvtneobf162ps -1024(,%ebp,2), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ vcvtneobf162ps -1024(,%ebp,2), %ymm2
+
+// CHECK: vcvtneobf162ps 4064(%ecx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x91,0xe0,0x0f,0x00,0x00]
+ vcvtneobf162ps 4064(%ecx), %ymm2
+
+// CHECK: vcvtneobf162ps -4096(%edx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x92,0x00,0xf0,0xff,0xff]
+ vcvtneobf162ps -4096(%edx), %ymm2
+
+// CHECK: vcvtneoph2ps 268435456(%esp,%esi,8), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vcvtneoph2ps 268435456(%esp,%esi,8), %xmm2
+
+// CHECK: vcvtneoph2ps 291(%edi,%eax,4), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x94,0x87,0x23,0x01,0x00,0x00]
+ vcvtneoph2ps 291(%edi,%eax,4), %xmm2
+
+// CHECK: vcvtneoph2ps (%eax), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x10]
+ vcvtneoph2ps (%eax), %xmm2
+
+// CHECK: vcvtneoph2ps -512(,%ebp,2), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ vcvtneoph2ps -512(,%ebp,2), %xmm2
+
+// CHECK: vcvtneoph2ps 2032(%ecx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x91,0xf0,0x07,0x00,0x00]
+ vcvtneoph2ps 2032(%ecx), %xmm2
+
+// CHECK: vcvtneoph2ps -2048(%edx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x92,0x00,0xf8,0xff,0xff]
+ vcvtneoph2ps -2048(%edx), %xmm2
+
+// CHECK: vcvtneoph2ps 268435456(%esp,%esi,8), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vcvtneoph2ps 268435456(%esp,%esi,8), %ymm2
+
+// CHECK: vcvtneoph2ps 291(%edi,%eax,4), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x94,0x87,0x23,0x01,0x00,0x00]
+ vcvtneoph2ps 291(%edi,%eax,4), %ymm2
+
+// CHECK: vcvtneoph2ps (%eax), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x10]
+ vcvtneoph2ps (%eax), %ymm2
+
+// CHECK: vcvtneoph2ps -1024(,%ebp,2), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ vcvtneoph2ps -1024(,%ebp,2), %ymm2
+
+// CHECK: vcvtneoph2ps 4064(%ecx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x91,0xe0,0x0f,0x00,0x00]
+ vcvtneoph2ps 4064(%ecx), %ymm2
+
+// CHECK: vcvtneoph2ps -4096(%edx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x92,0x00,0xf0,0xff,0xff]
+ vcvtneoph2ps -4096(%edx), %ymm2
+
+// CHECK: {vex} vcvtneps2bf16 %xmm3, %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0xd3]
+ {vex} vcvtneps2bf16 %xmm3, %xmm2
+
+// CHECK: {vex} vcvtneps2bf16 %ymm3, %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0x72,0xd3]
+ {vex} vcvtneps2bf16 %ymm3, %xmm2
+
+// CHECK: {vex} vcvtneps2bf16x 268435456(%esp,%esi,8), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x94,0xf4,0x00,0x00,0x00,0x10]
+ {vex} vcvtneps2bf16x 268435456(%esp,%esi,8), %xmm2
+
+// CHECK: {vex} vcvtneps2bf16x 291(%edi,%eax,4), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x94,0x87,0x23,0x01,0x00,0x00]
+ {vex} vcvtneps2bf16x 291(%edi,%eax,4), %xmm2
+
+// CHECK: {vex} vcvtneps2bf16x (%eax), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x10]
+ {vex} vcvtneps2bf16x (%eax), %xmm2
+
+// CHECK: {vex} vcvtneps2bf16x -512(,%ebp,2), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ {vex} vcvtneps2bf16x -512(,%ebp,2), %xmm2
+
+// CHECK: {vex} vcvtneps2bf16x 2032(%ecx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x91,0xf0,0x07,0x00,0x00]
+ {vex} vcvtneps2bf16x 2032(%ecx), %xmm2
+
+// CHECK: {vex} vcvtneps2bf16x -2048(%edx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x92,0x00,0xf8,0xff,0xff]
+ {vex} vcvtneps2bf16x -2048(%edx), %xmm2
+
+// CHECK: {vex} vcvtneps2bf16y -1024(,%ebp,2), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0x72,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ {vex} vcvtneps2bf16y -1024(,%ebp,2), %xmm2
+
+// CHECK: {vex} vcvtneps2bf16y 4064(%ecx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0x72,0x91,0xe0,0x0f,0x00,0x00]
+ {vex} vcvtneps2bf16y 4064(%ecx), %xmm2
+
+// CHECK: {vex} vcvtneps2bf16y -4096(%edx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0x72,0x92,0x00,0xf0,0xff,0xff]
+ {vex} vcvtneps2bf16y -4096(%edx), %xmm2
+
--- /dev/null
+// RUN: llvm-mc -triple i686-unknown-unknown -x86-asm-syntax=intel -output-asm-variant=1 --show-encoding %s | FileCheck %s
+
+// CHECK: vbcstnebf162ps xmm2, word ptr [esp + 8*esi + 268435456]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vbcstnebf162ps xmm2, word ptr [esp + 8*esi + 268435456]
+
+// CHECK: vbcstnebf162ps xmm2, word ptr [edi + 4*eax + 291]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x94,0x87,0x23,0x01,0x00,0x00]
+ vbcstnebf162ps xmm2, word ptr [edi + 4*eax + 291]
+
+// CHECK: vbcstnebf162ps xmm2, word ptr [eax]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x10]
+ vbcstnebf162ps xmm2, word ptr [eax]
+
+// CHECK: vbcstnebf162ps xmm2, word ptr [2*ebp - 64]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff]
+ vbcstnebf162ps xmm2, word ptr [2*ebp - 64]
+
+// CHECK: vbcstnebf162ps xmm2, word ptr [ecx + 254]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x91,0xfe,0x00,0x00,0x00]
+ vbcstnebf162ps xmm2, word ptr [ecx + 254]
+
+// CHECK: vbcstnebf162ps xmm2, word ptr [edx - 256]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x92,0x00,0xff,0xff,0xff]
+ vbcstnebf162ps xmm2, word ptr [edx - 256]
+
+// CHECK: vbcstnebf162ps ymm2, word ptr [esp + 8*esi + 268435456]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vbcstnebf162ps ymm2, word ptr [esp + 8*esi + 268435456]
+
+// CHECK: vbcstnebf162ps ymm2, word ptr [edi + 4*eax + 291]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x94,0x87,0x23,0x01,0x00,0x00]
+ vbcstnebf162ps ymm2, word ptr [edi + 4*eax + 291]
+
+// CHECK: vbcstnebf162ps ymm2, word ptr [eax]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x10]
+ vbcstnebf162ps ymm2, word ptr [eax]
+
+// CHECK: vbcstnebf162ps ymm2, word ptr [2*ebp - 64]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff]
+ vbcstnebf162ps ymm2, word ptr [2*ebp - 64]
+
+// CHECK: vbcstnebf162ps ymm2, word ptr [ecx + 254]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x91,0xfe,0x00,0x00,0x00]
+ vbcstnebf162ps ymm2, word ptr [ecx + 254]
+
+// CHECK: vbcstnebf162ps ymm2, word ptr [edx - 256]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x92,0x00,0xff,0xff,0xff]
+ vbcstnebf162ps ymm2, word ptr [edx - 256]
+
+// CHECK: vbcstnesh2ps xmm2, word ptr [esp + 8*esi + 268435456]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vbcstnesh2ps xmm2, word ptr [esp + 8*esi + 268435456]
+
+// CHECK: vbcstnesh2ps xmm2, word ptr [edi + 4*eax + 291]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x94,0x87,0x23,0x01,0x00,0x00]
+ vbcstnesh2ps xmm2, word ptr [edi + 4*eax + 291]
+
+// CHECK: vbcstnesh2ps xmm2, word ptr [eax]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x10]
+ vbcstnesh2ps xmm2, word ptr [eax]
+
+// CHECK: vbcstnesh2ps xmm2, word ptr [2*ebp - 64]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff]
+ vbcstnesh2ps xmm2, word ptr [2*ebp - 64]
+
+// CHECK: vbcstnesh2ps xmm2, word ptr [ecx + 254]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x91,0xfe,0x00,0x00,0x00]
+ vbcstnesh2ps xmm2, word ptr [ecx + 254]
+
+// CHECK: vbcstnesh2ps xmm2, word ptr [edx - 256]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x92,0x00,0xff,0xff,0xff]
+ vbcstnesh2ps xmm2, word ptr [edx - 256]
+
+// CHECK: vbcstnesh2ps ymm2, word ptr [esp + 8*esi + 268435456]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vbcstnesh2ps ymm2, word ptr [esp + 8*esi + 268435456]
+
+// CHECK: vbcstnesh2ps ymm2, word ptr [edi + 4*eax + 291]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x94,0x87,0x23,0x01,0x00,0x00]
+ vbcstnesh2ps ymm2, word ptr [edi + 4*eax + 291]
+
+// CHECK: vbcstnesh2ps ymm2, word ptr [eax]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x10]
+ vbcstnesh2ps ymm2, word ptr [eax]
+
+// CHECK: vbcstnesh2ps ymm2, word ptr [2*ebp - 64]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff]
+ vbcstnesh2ps ymm2, word ptr [2*ebp - 64]
+
+// CHECK: vbcstnesh2ps ymm2, word ptr [ecx + 254]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x91,0xfe,0x00,0x00,0x00]
+ vbcstnesh2ps ymm2, word ptr [ecx + 254]
+
+// CHECK: vbcstnesh2ps ymm2, word ptr [edx - 256]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x92,0x00,0xff,0xff,0xff]
+ vbcstnesh2ps ymm2, word ptr [edx - 256]
+
+// CHECK: vcvtneebf162ps xmm2, xmmword ptr [esp + 8*esi + 268435456]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vcvtneebf162ps xmm2, xmmword ptr [esp + 8*esi + 268435456]
+
+// CHECK: vcvtneebf162ps xmm2, xmmword ptr [edi + 4*eax + 291]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x94,0x87,0x23,0x01,0x00,0x00]
+ vcvtneebf162ps xmm2, xmmword ptr [edi + 4*eax + 291]
+
+// CHECK: vcvtneebf162ps xmm2, xmmword ptr [eax]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x10]
+ vcvtneebf162ps xmm2, xmmword ptr [eax]
+
+// CHECK: vcvtneebf162ps xmm2, xmmword ptr [2*ebp - 512]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ vcvtneebf162ps xmm2, xmmword ptr [2*ebp - 512]
+
+// CHECK: vcvtneebf162ps xmm2, xmmword ptr [ecx + 2032]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x91,0xf0,0x07,0x00,0x00]
+ vcvtneebf162ps xmm2, xmmword ptr [ecx + 2032]
+
+// CHECK: vcvtneebf162ps xmm2, xmmword ptr [edx - 2048]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x92,0x00,0xf8,0xff,0xff]
+ vcvtneebf162ps xmm2, xmmword ptr [edx - 2048]
+
+// CHECK: vcvtneebf162ps ymm2, ymmword ptr [esp + 8*esi + 268435456]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vcvtneebf162ps ymm2, ymmword ptr [esp + 8*esi + 268435456]
+
+// CHECK: vcvtneebf162ps ymm2, ymmword ptr [edi + 4*eax + 291]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x94,0x87,0x23,0x01,0x00,0x00]
+ vcvtneebf162ps ymm2, ymmword ptr [edi + 4*eax + 291]
+
+// CHECK: vcvtneebf162ps ymm2, ymmword ptr [eax]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x10]
+ vcvtneebf162ps ymm2, ymmword ptr [eax]
+
+// CHECK: vcvtneebf162ps ymm2, ymmword ptr [2*ebp - 1024]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ vcvtneebf162ps ymm2, ymmword ptr [2*ebp - 1024]
+
+// CHECK: vcvtneebf162ps ymm2, ymmword ptr [ecx + 4064]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x91,0xe0,0x0f,0x00,0x00]
+ vcvtneebf162ps ymm2, ymmword ptr [ecx + 4064]
+
+// CHECK: vcvtneebf162ps ymm2, ymmword ptr [edx - 4096]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x92,0x00,0xf0,0xff,0xff]
+ vcvtneebf162ps ymm2, ymmword ptr [edx - 4096]
+
+// CHECK: vcvtneeph2ps xmm2, xmmword ptr [esp + 8*esi + 268435456]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vcvtneeph2ps xmm2, xmmword ptr [esp + 8*esi + 268435456]
+
+// CHECK: vcvtneeph2ps xmm2, xmmword ptr [edi + 4*eax + 291]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x94,0x87,0x23,0x01,0x00,0x00]
+ vcvtneeph2ps xmm2, xmmword ptr [edi + 4*eax + 291]
+
+// CHECK: vcvtneeph2ps xmm2, xmmword ptr [eax]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x10]
+ vcvtneeph2ps xmm2, xmmword ptr [eax]
+
+// CHECK: vcvtneeph2ps xmm2, xmmword ptr [2*ebp - 512]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ vcvtneeph2ps xmm2, xmmword ptr [2*ebp - 512]
+
+// CHECK: vcvtneeph2ps xmm2, xmmword ptr [ecx + 2032]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x91,0xf0,0x07,0x00,0x00]
+ vcvtneeph2ps xmm2, xmmword ptr [ecx + 2032]
+
+// CHECK: vcvtneeph2ps xmm2, xmmword ptr [edx - 2048]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x92,0x00,0xf8,0xff,0xff]
+ vcvtneeph2ps xmm2, xmmword ptr [edx - 2048]
+
+// CHECK: vcvtneeph2ps ymm2, ymmword ptr [esp + 8*esi + 268435456]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vcvtneeph2ps ymm2, ymmword ptr [esp + 8*esi + 268435456]
+
+// CHECK: vcvtneeph2ps ymm2, ymmword ptr [edi + 4*eax + 291]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x94,0x87,0x23,0x01,0x00,0x00]
+ vcvtneeph2ps ymm2, ymmword ptr [edi + 4*eax + 291]
+
+// CHECK: vcvtneeph2ps ymm2, ymmword ptr [eax]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x10]
+ vcvtneeph2ps ymm2, ymmword ptr [eax]
+
+// CHECK: vcvtneeph2ps ymm2, ymmword ptr [2*ebp - 1024]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ vcvtneeph2ps ymm2, ymmword ptr [2*ebp - 1024]
+
+// CHECK: vcvtneeph2ps ymm2, ymmword ptr [ecx + 4064]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x91,0xe0,0x0f,0x00,0x00]
+ vcvtneeph2ps ymm2, ymmword ptr [ecx + 4064]
+
+// CHECK: vcvtneeph2ps ymm2, ymmword ptr [edx - 4096]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x92,0x00,0xf0,0xff,0xff]
+ vcvtneeph2ps ymm2, ymmword ptr [edx - 4096]
+
+// CHECK: vcvtneobf162ps xmm2, xmmword ptr [esp + 8*esi + 268435456]
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vcvtneobf162ps xmm2, xmmword ptr [esp + 8*esi + 268435456]
+
+// CHECK: vcvtneobf162ps xmm2, xmmword ptr [edi + 4*eax + 291]
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x94,0x87,0x23,0x01,0x00,0x00]
+ vcvtneobf162ps xmm2, xmmword ptr [edi + 4*eax + 291]
+
+// CHECK: vcvtneobf162ps xmm2, xmmword ptr [eax]
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x10]
+ vcvtneobf162ps xmm2, xmmword ptr [eax]
+
+// CHECK: vcvtneobf162ps xmm2, xmmword ptr [2*ebp - 512]
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ vcvtneobf162ps xmm2, xmmword ptr [2*ebp - 512]
+
+// CHECK: vcvtneobf162ps xmm2, xmmword ptr [ecx + 2032]
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x91,0xf0,0x07,0x00,0x00]
+ vcvtneobf162ps xmm2, xmmword ptr [ecx + 2032]
+
+// CHECK: vcvtneobf162ps xmm2, xmmword ptr [edx - 2048]
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x92,0x00,0xf8,0xff,0xff]
+ vcvtneobf162ps xmm2, xmmword ptr [edx - 2048]
+
+// CHECK: vcvtneobf162ps ymm2, ymmword ptr [esp + 8*esi + 268435456]
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vcvtneobf162ps ymm2, ymmword ptr [esp + 8*esi + 268435456]
+
+// CHECK: vcvtneobf162ps ymm2, ymmword ptr [edi + 4*eax + 291]
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x94,0x87,0x23,0x01,0x00,0x00]
+ vcvtneobf162ps ymm2, ymmword ptr [edi + 4*eax + 291]
+
+// CHECK: vcvtneobf162ps ymm2, ymmword ptr [eax]
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x10]
+ vcvtneobf162ps ymm2, ymmword ptr [eax]
+
+// CHECK: vcvtneobf162ps ymm2, ymmword ptr [2*ebp - 1024]
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ vcvtneobf162ps ymm2, ymmword ptr [2*ebp - 1024]
+
+// CHECK: vcvtneobf162ps ymm2, ymmword ptr [ecx + 4064]
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x91,0xe0,0x0f,0x00,0x00]
+ vcvtneobf162ps ymm2, ymmword ptr [ecx + 4064]
+
+// CHECK: vcvtneobf162ps ymm2, ymmword ptr [edx - 4096]
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x92,0x00,0xf0,0xff,0xff]
+ vcvtneobf162ps ymm2, ymmword ptr [edx - 4096]
+
+// CHECK: vcvtneoph2ps xmm2, xmmword ptr [esp + 8*esi + 268435456]
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vcvtneoph2ps xmm2, xmmword ptr [esp + 8*esi + 268435456]
+
+// CHECK: vcvtneoph2ps xmm2, xmmword ptr [edi + 4*eax + 291]
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x94,0x87,0x23,0x01,0x00,0x00]
+ vcvtneoph2ps xmm2, xmmword ptr [edi + 4*eax + 291]
+
+// CHECK: vcvtneoph2ps xmm2, xmmword ptr [eax]
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x10]
+ vcvtneoph2ps xmm2, xmmword ptr [eax]
+
+// CHECK: vcvtneoph2ps xmm2, xmmword ptr [2*ebp - 512]
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ vcvtneoph2ps xmm2, xmmword ptr [2*ebp - 512]
+
+// CHECK: vcvtneoph2ps xmm2, xmmword ptr [ecx + 2032]
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x91,0xf0,0x07,0x00,0x00]
+ vcvtneoph2ps xmm2, xmmword ptr [ecx + 2032]
+
+// CHECK: vcvtneoph2ps xmm2, xmmword ptr [edx - 2048]
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x92,0x00,0xf8,0xff,0xff]
+ vcvtneoph2ps xmm2, xmmword ptr [edx - 2048]
+
+// CHECK: vcvtneoph2ps ymm2, ymmword ptr [esp + 8*esi + 268435456]
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x94,0xf4,0x00,0x00,0x00,0x10]
+ vcvtneoph2ps ymm2, ymmword ptr [esp + 8*esi + 268435456]
+
+// CHECK: vcvtneoph2ps ymm2, ymmword ptr [edi + 4*eax + 291]
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x94,0x87,0x23,0x01,0x00,0x00]
+ vcvtneoph2ps ymm2, ymmword ptr [edi + 4*eax + 291]
+
+// CHECK: vcvtneoph2ps ymm2, ymmword ptr [eax]
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x10]
+ vcvtneoph2ps ymm2, ymmword ptr [eax]
+
+// CHECK: vcvtneoph2ps ymm2, ymmword ptr [2*ebp - 1024]
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ vcvtneoph2ps ymm2, ymmword ptr [2*ebp - 1024]
+
+// CHECK: vcvtneoph2ps ymm2, ymmword ptr [ecx + 4064]
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x91,0xe0,0x0f,0x00,0x00]
+ vcvtneoph2ps ymm2, ymmword ptr [ecx + 4064]
+
+// CHECK: vcvtneoph2ps ymm2, ymmword ptr [edx - 4096]
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x92,0x00,0xf0,0xff,0xff]
+ vcvtneoph2ps ymm2, ymmword ptr [edx - 4096]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, xmm3
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0xd3]
+ {vex} vcvtneps2bf16 xmm2, xmm3
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, ymm3
+// CHECK: encoding: [0xc4,0xe2,0x7e,0x72,0xd3]
+ {vex} vcvtneps2bf16 xmm2, ymm3
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, xmmword ptr [esp + 8*esi + 268435456]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x94,0xf4,0x00,0x00,0x00,0x10]
+ {vex} vcvtneps2bf16 xmm2, xmmword ptr [esp + 8*esi + 268435456]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, xmmword ptr [edi + 4*eax + 291]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x94,0x87,0x23,0x01,0x00,0x00]
+ {vex} vcvtneps2bf16 xmm2, xmmword ptr [edi + 4*eax + 291]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, xmmword ptr [eax]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x10]
+ {vex} vcvtneps2bf16 xmm2, xmmword ptr [eax]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, xmmword ptr [2*ebp - 512]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ {vex} vcvtneps2bf16 xmm2, xmmword ptr [2*ebp - 512]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, xmmword ptr [ecx + 2032]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x91,0xf0,0x07,0x00,0x00]
+ {vex} vcvtneps2bf16 xmm2, xmmword ptr [ecx + 2032]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, xmmword ptr [edx - 2048]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x92,0x00,0xf8,0xff,0xff]
+ {vex} vcvtneps2bf16 xmm2, xmmword ptr [edx - 2048]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, ymmword ptr [2*ebp - 1024]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0x72,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ {vex} vcvtneps2bf16 xmm2, ymmword ptr [2*ebp - 1024]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, ymmword ptr [ecx + 4064]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0x72,0x91,0xe0,0x0f,0x00,0x00]
+ {vex} vcvtneps2bf16 xmm2, ymmword ptr [ecx + 4064]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, ymmword ptr [edx - 4096]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0x72,0x92,0x00,0xf0,0xff,0xff]
+ {vex} vcvtneps2bf16 xmm2, ymmword ptr [edx - 4096]
+
--- /dev/null
+// RUN: llvm-mc -triple x86_64-unknown-unknown --show-encoding %s | FileCheck %s
+
+// CHECK: vbcstnebf162ps 268435456(%rbp,%r14,8), %xmm2
+// CHECK: encoding: [0xc4,0xa2,0x7a,0xb1,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vbcstnebf162ps 268435456(%rbp,%r14,8), %xmm2
+
+// CHECK: vbcstnebf162ps 291(%r8,%rax,4), %xmm2
+// CHECK: encoding: [0xc4,0xc2,0x7a,0xb1,0x94,0x80,0x23,0x01,0x00,0x00]
+ vbcstnebf162ps 291(%r8,%rax,4), %xmm2
+
+// CHECK: vbcstnebf162ps (%rip), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x15,0x00,0x00,0x00,0x00]
+ vbcstnebf162ps (%rip), %xmm2
+
+// CHECK: vbcstnebf162ps -64(,%rbp,2), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff]
+ vbcstnebf162ps -64(,%rbp,2), %xmm2
+
+// CHECK: vbcstnebf162ps 254(%rcx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x91,0xfe,0x00,0x00,0x00]
+ vbcstnebf162ps 254(%rcx), %xmm2
+
+// CHECK: vbcstnebf162ps -256(%rdx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x92,0x00,0xff,0xff,0xff]
+ vbcstnebf162ps -256(%rdx), %xmm2
+
+// CHECK: vbcstnebf162ps 268435456(%rbp,%r14,8), %ymm2
+// CHECK: encoding: [0xc4,0xa2,0x7e,0xb1,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vbcstnebf162ps 268435456(%rbp,%r14,8), %ymm2
+
+// CHECK: vbcstnebf162ps 291(%r8,%rax,4), %ymm2
+// CHECK: encoding: [0xc4,0xc2,0x7e,0xb1,0x94,0x80,0x23,0x01,0x00,0x00]
+ vbcstnebf162ps 291(%r8,%rax,4), %ymm2
+
+// CHECK: vbcstnebf162ps (%rip), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x15,0x00,0x00,0x00,0x00]
+ vbcstnebf162ps (%rip), %ymm2
+
+// CHECK: vbcstnebf162ps -64(,%rbp,2), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff]
+ vbcstnebf162ps -64(,%rbp,2), %ymm2
+
+// CHECK: vbcstnebf162ps 254(%rcx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x91,0xfe,0x00,0x00,0x00]
+ vbcstnebf162ps 254(%rcx), %ymm2
+
+// CHECK: vbcstnebf162ps -256(%rdx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x92,0x00,0xff,0xff,0xff]
+ vbcstnebf162ps -256(%rdx), %ymm2
+
+// CHECK: vbcstnesh2ps 268435456(%rbp,%r14,8), %xmm2
+// CHECK: encoding: [0xc4,0xa2,0x79,0xb1,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vbcstnesh2ps 268435456(%rbp,%r14,8), %xmm2
+
+// CHECK: vbcstnesh2ps 291(%r8,%rax,4), %xmm2
+// CHECK: encoding: [0xc4,0xc2,0x79,0xb1,0x94,0x80,0x23,0x01,0x00,0x00]
+ vbcstnesh2ps 291(%r8,%rax,4), %xmm2
+
+// CHECK: vbcstnesh2ps (%rip), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x15,0x00,0x00,0x00,0x00]
+ vbcstnesh2ps (%rip), %xmm2
+
+// CHECK: vbcstnesh2ps -64(,%rbp,2), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff]
+ vbcstnesh2ps -64(,%rbp,2), %xmm2
+
+// CHECK: vbcstnesh2ps 254(%rcx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x91,0xfe,0x00,0x00,0x00]
+ vbcstnesh2ps 254(%rcx), %xmm2
+
+// CHECK: vbcstnesh2ps -256(%rdx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x92,0x00,0xff,0xff,0xff]
+ vbcstnesh2ps -256(%rdx), %xmm2
+
+// CHECK: vbcstnesh2ps 268435456(%rbp,%r14,8), %ymm2
+// CHECK: encoding: [0xc4,0xa2,0x7d,0xb1,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vbcstnesh2ps 268435456(%rbp,%r14,8), %ymm2
+
+// CHECK: vbcstnesh2ps 291(%r8,%rax,4), %ymm2
+// CHECK: encoding: [0xc4,0xc2,0x7d,0xb1,0x94,0x80,0x23,0x01,0x00,0x00]
+ vbcstnesh2ps 291(%r8,%rax,4), %ymm2
+
+// CHECK: vbcstnesh2ps (%rip), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x15,0x00,0x00,0x00,0x00]
+ vbcstnesh2ps (%rip), %ymm2
+
+// CHECK: vbcstnesh2ps -64(,%rbp,2), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff]
+ vbcstnesh2ps -64(,%rbp,2), %ymm2
+
+// CHECK: vbcstnesh2ps 254(%rcx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x91,0xfe,0x00,0x00,0x00]
+ vbcstnesh2ps 254(%rcx), %ymm2
+
+// CHECK: vbcstnesh2ps -256(%rdx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x92,0x00,0xff,0xff,0xff]
+ vbcstnesh2ps -256(%rdx), %ymm2
+
+// CHECK: vcvtneebf162ps 268435456(%rbp,%r14,8), %xmm2
+// CHECK: encoding: [0xc4,0xa2,0x7a,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vcvtneebf162ps 268435456(%rbp,%r14,8), %xmm2
+
+// CHECK: vcvtneebf162ps 291(%r8,%rax,4), %xmm2
+// CHECK: encoding: [0xc4,0xc2,0x7a,0xb0,0x94,0x80,0x23,0x01,0x00,0x00]
+ vcvtneebf162ps 291(%r8,%rax,4), %xmm2
+
+// CHECK: vcvtneebf162ps (%rip), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x15,0x00,0x00,0x00,0x00]
+ vcvtneebf162ps (%rip), %xmm2
+
+// CHECK: vcvtneebf162ps -512(,%rbp,2), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ vcvtneebf162ps -512(,%rbp,2), %xmm2
+
+// CHECK: vcvtneebf162ps 2032(%rcx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x91,0xf0,0x07,0x00,0x00]
+ vcvtneebf162ps 2032(%rcx), %xmm2
+
+// CHECK: vcvtneebf162ps -2048(%rdx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x92,0x00,0xf8,0xff,0xff]
+ vcvtneebf162ps -2048(%rdx), %xmm2
+
+// CHECK: vcvtneebf162ps 268435456(%rbp,%r14,8), %ymm2
+// CHECK: encoding: [0xc4,0xa2,0x7e,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vcvtneebf162ps 268435456(%rbp,%r14,8), %ymm2
+
+// CHECK: vcvtneebf162ps 291(%r8,%rax,4), %ymm2
+// CHECK: encoding: [0xc4,0xc2,0x7e,0xb0,0x94,0x80,0x23,0x01,0x00,0x00]
+ vcvtneebf162ps 291(%r8,%rax,4), %ymm2
+
+// CHECK: vcvtneebf162ps (%rip), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x15,0x00,0x00,0x00,0x00]
+ vcvtneebf162ps (%rip), %ymm2
+
+// CHECK: vcvtneebf162ps -1024(,%rbp,2), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ vcvtneebf162ps -1024(,%rbp,2), %ymm2
+
+// CHECK: vcvtneebf162ps 4064(%rcx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x91,0xe0,0x0f,0x00,0x00]
+ vcvtneebf162ps 4064(%rcx), %ymm2
+
+// CHECK: vcvtneebf162ps -4096(%rdx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x92,0x00,0xf0,0xff,0xff]
+ vcvtneebf162ps -4096(%rdx), %ymm2
+
+// CHECK: vcvtneeph2ps 268435456(%rbp,%r14,8), %xmm2
+// CHECK: encoding: [0xc4,0xa2,0x79,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vcvtneeph2ps 268435456(%rbp,%r14,8), %xmm2
+
+// CHECK: vcvtneeph2ps 291(%r8,%rax,4), %xmm2
+// CHECK: encoding: [0xc4,0xc2,0x79,0xb0,0x94,0x80,0x23,0x01,0x00,0x00]
+ vcvtneeph2ps 291(%r8,%rax,4), %xmm2
+
+// CHECK: vcvtneeph2ps (%rip), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x15,0x00,0x00,0x00,0x00]
+ vcvtneeph2ps (%rip), %xmm2
+
+// CHECK: vcvtneeph2ps -512(,%rbp,2), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ vcvtneeph2ps -512(,%rbp,2), %xmm2
+
+// CHECK: vcvtneeph2ps 2032(%rcx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x91,0xf0,0x07,0x00,0x00]
+ vcvtneeph2ps 2032(%rcx), %xmm2
+
+// CHECK: vcvtneeph2ps -2048(%rdx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x92,0x00,0xf8,0xff,0xff]
+ vcvtneeph2ps -2048(%rdx), %xmm2
+
+// CHECK: vcvtneeph2ps 268435456(%rbp,%r14,8), %ymm2
+// CHECK: encoding: [0xc4,0xa2,0x7d,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vcvtneeph2ps 268435456(%rbp,%r14,8), %ymm2
+
+// CHECK: vcvtneeph2ps 291(%r8,%rax,4), %ymm2
+// CHECK: encoding: [0xc4,0xc2,0x7d,0xb0,0x94,0x80,0x23,0x01,0x00,0x00]
+ vcvtneeph2ps 291(%r8,%rax,4), %ymm2
+
+// CHECK: vcvtneeph2ps (%rip), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x15,0x00,0x00,0x00,0x00]
+ vcvtneeph2ps (%rip), %ymm2
+
+// CHECK: vcvtneeph2ps -1024(,%rbp,2), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ vcvtneeph2ps -1024(,%rbp,2), %ymm2
+
+// CHECK: vcvtneeph2ps 4064(%rcx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x91,0xe0,0x0f,0x00,0x00]
+ vcvtneeph2ps 4064(%rcx), %ymm2
+
+// CHECK: vcvtneeph2ps -4096(%rdx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x92,0x00,0xf0,0xff,0xff]
+ vcvtneeph2ps -4096(%rdx), %ymm2
+
+// CHECK: vcvtneobf162ps 268435456(%rbp,%r14,8), %xmm2
+// CHECK: encoding: [0xc4,0xa2,0x7b,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vcvtneobf162ps 268435456(%rbp,%r14,8), %xmm2
+
+// CHECK: vcvtneobf162ps 291(%r8,%rax,4), %xmm2
+// CHECK: encoding: [0xc4,0xc2,0x7b,0xb0,0x94,0x80,0x23,0x01,0x00,0x00]
+ vcvtneobf162ps 291(%r8,%rax,4), %xmm2
+
+// CHECK: vcvtneobf162ps (%rip), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x15,0x00,0x00,0x00,0x00]
+ vcvtneobf162ps (%rip), %xmm2
+
+// CHECK: vcvtneobf162ps -512(,%rbp,2), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ vcvtneobf162ps -512(,%rbp,2), %xmm2
+
+// CHECK: vcvtneobf162ps 2032(%rcx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x91,0xf0,0x07,0x00,0x00]
+ vcvtneobf162ps 2032(%rcx), %xmm2
+
+// CHECK: vcvtneobf162ps -2048(%rdx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x92,0x00,0xf8,0xff,0xff]
+ vcvtneobf162ps -2048(%rdx), %xmm2
+
+// CHECK: vcvtneobf162ps 268435456(%rbp,%r14,8), %ymm2
+// CHECK: encoding: [0xc4,0xa2,0x7f,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vcvtneobf162ps 268435456(%rbp,%r14,8), %ymm2
+
+// CHECK: vcvtneobf162ps 291(%r8,%rax,4), %ymm2
+// CHECK: encoding: [0xc4,0xc2,0x7f,0xb0,0x94,0x80,0x23,0x01,0x00,0x00]
+ vcvtneobf162ps 291(%r8,%rax,4), %ymm2
+
+// CHECK: vcvtneobf162ps (%rip), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x15,0x00,0x00,0x00,0x00]
+ vcvtneobf162ps (%rip), %ymm2
+
+// CHECK: vcvtneobf162ps -1024(,%rbp,2), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ vcvtneobf162ps -1024(,%rbp,2), %ymm2
+
+// CHECK: vcvtneobf162ps 4064(%rcx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x91,0xe0,0x0f,0x00,0x00]
+ vcvtneobf162ps 4064(%rcx), %ymm2
+
+// CHECK: vcvtneobf162ps -4096(%rdx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x92,0x00,0xf0,0xff,0xff]
+ vcvtneobf162ps -4096(%rdx), %ymm2
+
+// CHECK: vcvtneoph2ps 268435456(%rbp,%r14,8), %xmm2
+// CHECK: encoding: [0xc4,0xa2,0x78,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vcvtneoph2ps 268435456(%rbp,%r14,8), %xmm2
+
+// CHECK: vcvtneoph2ps 291(%r8,%rax,4), %xmm2
+// CHECK: encoding: [0xc4,0xc2,0x78,0xb0,0x94,0x80,0x23,0x01,0x00,0x00]
+ vcvtneoph2ps 291(%r8,%rax,4), %xmm2
+
+// CHECK: vcvtneoph2ps (%rip), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x15,0x00,0x00,0x00,0x00]
+ vcvtneoph2ps (%rip), %xmm2
+
+// CHECK: vcvtneoph2ps -512(,%rbp,2), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ vcvtneoph2ps -512(,%rbp,2), %xmm2
+
+// CHECK: vcvtneoph2ps 2032(%rcx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x91,0xf0,0x07,0x00,0x00]
+ vcvtneoph2ps 2032(%rcx), %xmm2
+
+// CHECK: vcvtneoph2ps -2048(%rdx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x92,0x00,0xf8,0xff,0xff]
+ vcvtneoph2ps -2048(%rdx), %xmm2
+
+// CHECK: vcvtneoph2ps 268435456(%rbp,%r14,8), %ymm2
+// CHECK: encoding: [0xc4,0xa2,0x7c,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vcvtneoph2ps 268435456(%rbp,%r14,8), %ymm2
+
+// CHECK: vcvtneoph2ps 291(%r8,%rax,4), %ymm2
+// CHECK: encoding: [0xc4,0xc2,0x7c,0xb0,0x94,0x80,0x23,0x01,0x00,0x00]
+ vcvtneoph2ps 291(%r8,%rax,4), %ymm2
+
+// CHECK: vcvtneoph2ps (%rip), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x15,0x00,0x00,0x00,0x00]
+ vcvtneoph2ps (%rip), %ymm2
+
+// CHECK: vcvtneoph2ps -1024(,%rbp,2), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ vcvtneoph2ps -1024(,%rbp,2), %ymm2
+
+// CHECK: vcvtneoph2ps 4064(%rcx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x91,0xe0,0x0f,0x00,0x00]
+ vcvtneoph2ps 4064(%rcx), %ymm2
+
+// CHECK: vcvtneoph2ps -4096(%rdx), %ymm2
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x92,0x00,0xf0,0xff,0xff]
+ vcvtneoph2ps -4096(%rdx), %ymm2
+
+// CHECK: {vex} vcvtneps2bf16 %xmm3, %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0xd3]
+ {vex} vcvtneps2bf16 %xmm3, %xmm2
+
+// CHECK: {vex} vcvtneps2bf16 %ymm3, %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0x72,0xd3]
+ {vex} vcvtneps2bf16 %ymm3, %xmm2
+
+// CHECK: {vex} vcvtneps2bf16x 268435456(%rbp,%r14,8), %xmm2
+// CHECK: encoding: [0xc4,0xa2,0x7a,0x72,0x94,0xf5,0x00,0x00,0x00,0x10]
+ {vex} vcvtneps2bf16x 268435456(%rbp,%r14,8), %xmm2
+
+// CHECK: {vex} vcvtneps2bf16x 291(%r8,%rax,4), %xmm2
+// CHECK: encoding: [0xc4,0xc2,0x7a,0x72,0x94,0x80,0x23,0x01,0x00,0x00]
+ {vex} vcvtneps2bf16x 291(%r8,%rax,4), %xmm2
+
+// CHECK: {vex} vcvtneps2bf16x (%rip), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x15,0x00,0x00,0x00,0x00]
+ {vex} vcvtneps2bf16x (%rip), %xmm2
+
+// CHECK: {vex} vcvtneps2bf16x -512(,%rbp,2), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ {vex} vcvtneps2bf16x -512(,%rbp,2), %xmm2
+
+// CHECK: {vex} vcvtneps2bf16x 2032(%rcx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x91,0xf0,0x07,0x00,0x00]
+ {vex} vcvtneps2bf16x 2032(%rcx), %xmm2
+
+// CHECK: {vex} vcvtneps2bf16x -2048(%rdx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x92,0x00,0xf8,0xff,0xff]
+ {vex} vcvtneps2bf16x -2048(%rdx), %xmm2
+
+// CHECK: {vex} vcvtneps2bf16y -1024(,%rbp,2), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0x72,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ {vex} vcvtneps2bf16y -1024(,%rbp,2), %xmm2
+
+// CHECK: {vex} vcvtneps2bf16y 4064(%rcx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0x72,0x91,0xe0,0x0f,0x00,0x00]
+ {vex} vcvtneps2bf16y 4064(%rcx), %xmm2
+
+// CHECK: {vex} vcvtneps2bf16y -4096(%rdx), %xmm2
+// CHECK: encoding: [0xc4,0xe2,0x7e,0x72,0x92,0x00,0xf0,0xff,0xff]
+ {vex} vcvtneps2bf16y -4096(%rdx), %xmm2
+
--- /dev/null
+// RUN: llvm-mc -triple x86_64-unknown-unknown -x86-asm-syntax=intel -output-asm-variant=1 --show-encoding %s | FileCheck %s
+
+// CHECK: vbcstnebf162ps xmm2, word ptr [rbp + 8*r14 + 268435456]
+// CHECK: encoding: [0xc4,0xa2,0x7a,0xb1,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vbcstnebf162ps xmm2, word ptr [rbp + 8*r14 + 268435456]
+
+// CHECK: vbcstnebf162ps xmm2, word ptr [r8 + 4*rax + 291]
+// CHECK: encoding: [0xc4,0xc2,0x7a,0xb1,0x94,0x80,0x23,0x01,0x00,0x00]
+ vbcstnebf162ps xmm2, word ptr [r8 + 4*rax + 291]
+
+// CHECK: vbcstnebf162ps xmm2, word ptr [rip]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x15,0x00,0x00,0x00,0x00]
+ vbcstnebf162ps xmm2, word ptr [rip]
+
+// CHECK: vbcstnebf162ps xmm2, word ptr [2*rbp - 64]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff]
+ vbcstnebf162ps xmm2, word ptr [2*rbp - 64]
+
+// CHECK: vbcstnebf162ps xmm2, word ptr [rcx + 254]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x91,0xfe,0x00,0x00,0x00]
+ vbcstnebf162ps xmm2, word ptr [rcx + 254]
+
+// CHECK: vbcstnebf162ps xmm2, word ptr [rdx - 256]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb1,0x92,0x00,0xff,0xff,0xff]
+ vbcstnebf162ps xmm2, word ptr [rdx - 256]
+
+// CHECK: vbcstnebf162ps ymm2, word ptr [rbp + 8*r14 + 268435456]
+// CHECK: encoding: [0xc4,0xa2,0x7e,0xb1,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vbcstnebf162ps ymm2, word ptr [rbp + 8*r14 + 268435456]
+
+// CHECK: vbcstnebf162ps ymm2, word ptr [r8 + 4*rax + 291]
+// CHECK: encoding: [0xc4,0xc2,0x7e,0xb1,0x94,0x80,0x23,0x01,0x00,0x00]
+ vbcstnebf162ps ymm2, word ptr [r8 + 4*rax + 291]
+
+// CHECK: vbcstnebf162ps ymm2, word ptr [rip]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x15,0x00,0x00,0x00,0x00]
+ vbcstnebf162ps ymm2, word ptr [rip]
+
+// CHECK: vbcstnebf162ps ymm2, word ptr [2*rbp - 64]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff]
+ vbcstnebf162ps ymm2, word ptr [2*rbp - 64]
+
+// CHECK: vbcstnebf162ps ymm2, word ptr [rcx + 254]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x91,0xfe,0x00,0x00,0x00]
+ vbcstnebf162ps ymm2, word ptr [rcx + 254]
+
+// CHECK: vbcstnebf162ps ymm2, word ptr [rdx - 256]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb1,0x92,0x00,0xff,0xff,0xff]
+ vbcstnebf162ps ymm2, word ptr [rdx - 256]
+
+// CHECK: vbcstnesh2ps xmm2, word ptr [rbp + 8*r14 + 268435456]
+// CHECK: encoding: [0xc4,0xa2,0x79,0xb1,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vbcstnesh2ps xmm2, word ptr [rbp + 8*r14 + 268435456]
+
+// CHECK: vbcstnesh2ps xmm2, word ptr [r8 + 4*rax + 291]
+// CHECK: encoding: [0xc4,0xc2,0x79,0xb1,0x94,0x80,0x23,0x01,0x00,0x00]
+ vbcstnesh2ps xmm2, word ptr [r8 + 4*rax + 291]
+
+// CHECK: vbcstnesh2ps xmm2, word ptr [rip]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x15,0x00,0x00,0x00,0x00]
+ vbcstnesh2ps xmm2, word ptr [rip]
+
+// CHECK: vbcstnesh2ps xmm2, word ptr [2*rbp - 64]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff]
+ vbcstnesh2ps xmm2, word ptr [2*rbp - 64]
+
+// CHECK: vbcstnesh2ps xmm2, word ptr [rcx + 254]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x91,0xfe,0x00,0x00,0x00]
+ vbcstnesh2ps xmm2, word ptr [rcx + 254]
+
+// CHECK: vbcstnesh2ps xmm2, word ptr [rdx - 256]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb1,0x92,0x00,0xff,0xff,0xff]
+ vbcstnesh2ps xmm2, word ptr [rdx - 256]
+
+// CHECK: vbcstnesh2ps ymm2, word ptr [rbp + 8*r14 + 268435456]
+// CHECK: encoding: [0xc4,0xa2,0x7d,0xb1,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vbcstnesh2ps ymm2, word ptr [rbp + 8*r14 + 268435456]
+
+// CHECK: vbcstnesh2ps ymm2, word ptr [r8 + 4*rax + 291]
+// CHECK: encoding: [0xc4,0xc2,0x7d,0xb1,0x94,0x80,0x23,0x01,0x00,0x00]
+ vbcstnesh2ps ymm2, word ptr [r8 + 4*rax + 291]
+
+// CHECK: vbcstnesh2ps ymm2, word ptr [rip]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x15,0x00,0x00,0x00,0x00]
+ vbcstnesh2ps ymm2, word ptr [rip]
+
+// CHECK: vbcstnesh2ps ymm2, word ptr [2*rbp - 64]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x14,0x6d,0xc0,0xff,0xff,0xff]
+ vbcstnesh2ps ymm2, word ptr [2*rbp - 64]
+
+// CHECK: vbcstnesh2ps ymm2, word ptr [rcx + 254]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x91,0xfe,0x00,0x00,0x00]
+ vbcstnesh2ps ymm2, word ptr [rcx + 254]
+
+// CHECK: vbcstnesh2ps ymm2, word ptr [rdx - 256]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb1,0x92,0x00,0xff,0xff,0xff]
+ vbcstnesh2ps ymm2, word ptr [rdx - 256]
+
+// CHECK: vcvtneebf162ps xmm2, xmmword ptr [rbp + 8*r14 + 268435456]
+// CHECK: encoding: [0xc4,0xa2,0x7a,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vcvtneebf162ps xmm2, xmmword ptr [rbp + 8*r14 + 268435456]
+
+// CHECK: vcvtneebf162ps xmm2, xmmword ptr [r8 + 4*rax + 291]
+// CHECK: encoding: [0xc4,0xc2,0x7a,0xb0,0x94,0x80,0x23,0x01,0x00,0x00]
+ vcvtneebf162ps xmm2, xmmword ptr [r8 + 4*rax + 291]
+
+// CHECK: vcvtneebf162ps xmm2, xmmword ptr [rip]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x15,0x00,0x00,0x00,0x00]
+ vcvtneebf162ps xmm2, xmmword ptr [rip]
+
+// CHECK: vcvtneebf162ps xmm2, xmmword ptr [2*rbp - 512]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ vcvtneebf162ps xmm2, xmmword ptr [2*rbp - 512]
+
+// CHECK: vcvtneebf162ps xmm2, xmmword ptr [rcx + 2032]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x91,0xf0,0x07,0x00,0x00]
+ vcvtneebf162ps xmm2, xmmword ptr [rcx + 2032]
+
+// CHECK: vcvtneebf162ps xmm2, xmmword ptr [rdx - 2048]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0xb0,0x92,0x00,0xf8,0xff,0xff]
+ vcvtneebf162ps xmm2, xmmword ptr [rdx - 2048]
+
+// CHECK: vcvtneebf162ps ymm2, ymmword ptr [rbp + 8*r14 + 268435456]
+// CHECK: encoding: [0xc4,0xa2,0x7e,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vcvtneebf162ps ymm2, ymmword ptr [rbp + 8*r14 + 268435456]
+
+// CHECK: vcvtneebf162ps ymm2, ymmword ptr [r8 + 4*rax + 291]
+// CHECK: encoding: [0xc4,0xc2,0x7e,0xb0,0x94,0x80,0x23,0x01,0x00,0x00]
+ vcvtneebf162ps ymm2, ymmword ptr [r8 + 4*rax + 291]
+
+// CHECK: vcvtneebf162ps ymm2, ymmword ptr [rip]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x15,0x00,0x00,0x00,0x00]
+ vcvtneebf162ps ymm2, ymmword ptr [rip]
+
+// CHECK: vcvtneebf162ps ymm2, ymmword ptr [2*rbp - 1024]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ vcvtneebf162ps ymm2, ymmword ptr [2*rbp - 1024]
+
+// CHECK: vcvtneebf162ps ymm2, ymmword ptr [rcx + 4064]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x91,0xe0,0x0f,0x00,0x00]
+ vcvtneebf162ps ymm2, ymmword ptr [rcx + 4064]
+
+// CHECK: vcvtneebf162ps ymm2, ymmword ptr [rdx - 4096]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0xb0,0x92,0x00,0xf0,0xff,0xff]
+ vcvtneebf162ps ymm2, ymmword ptr [rdx - 4096]
+
+// CHECK: vcvtneeph2ps xmm2, xmmword ptr [rbp + 8*r14 + 268435456]
+// CHECK: encoding: [0xc4,0xa2,0x79,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vcvtneeph2ps xmm2, xmmword ptr [rbp + 8*r14 + 268435456]
+
+// CHECK: vcvtneeph2ps xmm2, xmmword ptr [r8 + 4*rax + 291]
+// CHECK: encoding: [0xc4,0xc2,0x79,0xb0,0x94,0x80,0x23,0x01,0x00,0x00]
+ vcvtneeph2ps xmm2, xmmword ptr [r8 + 4*rax + 291]
+
+// CHECK: vcvtneeph2ps xmm2, xmmword ptr [rip]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x15,0x00,0x00,0x00,0x00]
+ vcvtneeph2ps xmm2, xmmword ptr [rip]
+
+// CHECK: vcvtneeph2ps xmm2, xmmword ptr [2*rbp - 512]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ vcvtneeph2ps xmm2, xmmword ptr [2*rbp - 512]
+
+// CHECK: vcvtneeph2ps xmm2, xmmword ptr [rcx + 2032]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x91,0xf0,0x07,0x00,0x00]
+ vcvtneeph2ps xmm2, xmmword ptr [rcx + 2032]
+
+// CHECK: vcvtneeph2ps xmm2, xmmword ptr [rdx - 2048]
+// CHECK: encoding: [0xc4,0xe2,0x79,0xb0,0x92,0x00,0xf8,0xff,0xff]
+ vcvtneeph2ps xmm2, xmmword ptr [rdx - 2048]
+
+// CHECK: vcvtneeph2ps ymm2, ymmword ptr [rbp + 8*r14 + 268435456]
+// CHECK: encoding: [0xc4,0xa2,0x7d,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vcvtneeph2ps ymm2, ymmword ptr [rbp + 8*r14 + 268435456]
+
+// CHECK: vcvtneeph2ps ymm2, ymmword ptr [r8 + 4*rax + 291]
+// CHECK: encoding: [0xc4,0xc2,0x7d,0xb0,0x94,0x80,0x23,0x01,0x00,0x00]
+ vcvtneeph2ps ymm2, ymmword ptr [r8 + 4*rax + 291]
+
+// CHECK: vcvtneeph2ps ymm2, ymmword ptr [rip]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x15,0x00,0x00,0x00,0x00]
+ vcvtneeph2ps ymm2, ymmword ptr [rip]
+
+// CHECK: vcvtneeph2ps ymm2, ymmword ptr [2*rbp - 1024]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ vcvtneeph2ps ymm2, ymmword ptr [2*rbp - 1024]
+
+// CHECK: vcvtneeph2ps ymm2, ymmword ptr [rcx + 4064]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x91,0xe0,0x0f,0x00,0x00]
+ vcvtneeph2ps ymm2, ymmword ptr [rcx + 4064]
+
+// CHECK: vcvtneeph2ps ymm2, ymmword ptr [rdx - 4096]
+// CHECK: encoding: [0xc4,0xe2,0x7d,0xb0,0x92,0x00,0xf0,0xff,0xff]
+ vcvtneeph2ps ymm2, ymmword ptr [rdx - 4096]
+
+// CHECK: vcvtneobf162ps xmm2, xmmword ptr [rbp + 8*r14 + 268435456]
+// CHECK: encoding: [0xc4,0xa2,0x7b,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vcvtneobf162ps xmm2, xmmword ptr [rbp + 8*r14 + 268435456]
+
+// CHECK: vcvtneobf162ps xmm2, xmmword ptr [r8 + 4*rax + 291]
+// CHECK: encoding: [0xc4,0xc2,0x7b,0xb0,0x94,0x80,0x23,0x01,0x00,0x00]
+ vcvtneobf162ps xmm2, xmmword ptr [r8 + 4*rax + 291]
+
+// CHECK: vcvtneobf162ps xmm2, xmmword ptr [rip]
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x15,0x00,0x00,0x00,0x00]
+ vcvtneobf162ps xmm2, xmmword ptr [rip]
+
+// CHECK: vcvtneobf162ps xmm2, xmmword ptr [2*rbp - 512]
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ vcvtneobf162ps xmm2, xmmword ptr [2*rbp - 512]
+
+// CHECK: vcvtneobf162ps xmm2, xmmword ptr [rcx + 2032]
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x91,0xf0,0x07,0x00,0x00]
+ vcvtneobf162ps xmm2, xmmword ptr [rcx + 2032]
+
+// CHECK: vcvtneobf162ps xmm2, xmmword ptr [rdx - 2048]
+// CHECK: encoding: [0xc4,0xe2,0x7b,0xb0,0x92,0x00,0xf8,0xff,0xff]
+ vcvtneobf162ps xmm2, xmmword ptr [rdx - 2048]
+
+// CHECK: vcvtneobf162ps ymm2, ymmword ptr [rbp + 8*r14 + 268435456]
+// CHECK: encoding: [0xc4,0xa2,0x7f,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vcvtneobf162ps ymm2, ymmword ptr [rbp + 8*r14 + 268435456]
+
+// CHECK: vcvtneobf162ps ymm2, ymmword ptr [r8 + 4*rax + 291]
+// CHECK: encoding: [0xc4,0xc2,0x7f,0xb0,0x94,0x80,0x23,0x01,0x00,0x00]
+ vcvtneobf162ps ymm2, ymmword ptr [r8 + 4*rax + 291]
+
+// CHECK: vcvtneobf162ps ymm2, ymmword ptr [rip]
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x15,0x00,0x00,0x00,0x00]
+ vcvtneobf162ps ymm2, ymmword ptr [rip]
+
+// CHECK: vcvtneobf162ps ymm2, ymmword ptr [2*rbp - 1024]
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ vcvtneobf162ps ymm2, ymmword ptr [2*rbp - 1024]
+
+// CHECK: vcvtneobf162ps ymm2, ymmword ptr [rcx + 4064]
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x91,0xe0,0x0f,0x00,0x00]
+ vcvtneobf162ps ymm2, ymmword ptr [rcx + 4064]
+
+// CHECK: vcvtneobf162ps ymm2, ymmword ptr [rdx - 4096]
+// CHECK: encoding: [0xc4,0xe2,0x7f,0xb0,0x92,0x00,0xf0,0xff,0xff]
+ vcvtneobf162ps ymm2, ymmword ptr [rdx - 4096]
+
+// CHECK: vcvtneoph2ps xmm2, xmmword ptr [rbp + 8*r14 + 268435456]
+// CHECK: encoding: [0xc4,0xa2,0x78,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vcvtneoph2ps xmm2, xmmword ptr [rbp + 8*r14 + 268435456]
+
+// CHECK: vcvtneoph2ps xmm2, xmmword ptr [r8 + 4*rax + 291]
+// CHECK: encoding: [0xc4,0xc2,0x78,0xb0,0x94,0x80,0x23,0x01,0x00,0x00]
+ vcvtneoph2ps xmm2, xmmword ptr [r8 + 4*rax + 291]
+
+// CHECK: vcvtneoph2ps xmm2, xmmword ptr [rip]
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x15,0x00,0x00,0x00,0x00]
+ vcvtneoph2ps xmm2, xmmword ptr [rip]
+
+// CHECK: vcvtneoph2ps xmm2, xmmword ptr [2*rbp - 512]
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ vcvtneoph2ps xmm2, xmmword ptr [2*rbp - 512]
+
+// CHECK: vcvtneoph2ps xmm2, xmmword ptr [rcx + 2032]
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x91,0xf0,0x07,0x00,0x00]
+ vcvtneoph2ps xmm2, xmmword ptr [rcx + 2032]
+
+// CHECK: vcvtneoph2ps xmm2, xmmword ptr [rdx - 2048]
+// CHECK: encoding: [0xc4,0xe2,0x78,0xb0,0x92,0x00,0xf8,0xff,0xff]
+ vcvtneoph2ps xmm2, xmmword ptr [rdx - 2048]
+
+// CHECK: vcvtneoph2ps ymm2, ymmword ptr [rbp + 8*r14 + 268435456]
+// CHECK: encoding: [0xc4,0xa2,0x7c,0xb0,0x94,0xf5,0x00,0x00,0x00,0x10]
+ vcvtneoph2ps ymm2, ymmword ptr [rbp + 8*r14 + 268435456]
+
+// CHECK: vcvtneoph2ps ymm2, ymmword ptr [r8 + 4*rax + 291]
+// CHECK: encoding: [0xc4,0xc2,0x7c,0xb0,0x94,0x80,0x23,0x01,0x00,0x00]
+ vcvtneoph2ps ymm2, ymmword ptr [r8 + 4*rax + 291]
+
+// CHECK: vcvtneoph2ps ymm2, ymmword ptr [rip]
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x15,0x00,0x00,0x00,0x00]
+ vcvtneoph2ps ymm2, ymmword ptr [rip]
+
+// CHECK: vcvtneoph2ps ymm2, ymmword ptr [2*rbp - 1024]
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ vcvtneoph2ps ymm2, ymmword ptr [2*rbp - 1024]
+
+// CHECK: vcvtneoph2ps ymm2, ymmword ptr [rcx + 4064]
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x91,0xe0,0x0f,0x00,0x00]
+ vcvtneoph2ps ymm2, ymmword ptr [rcx + 4064]
+
+// CHECK: vcvtneoph2ps ymm2, ymmword ptr [rdx - 4096]
+// CHECK: encoding: [0xc4,0xe2,0x7c,0xb0,0x92,0x00,0xf0,0xff,0xff]
+ vcvtneoph2ps ymm2, ymmword ptr [rdx - 4096]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, xmm3
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0xd3]
+ {vex} vcvtneps2bf16 xmm2, xmm3
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, ymm3
+// CHECK: encoding: [0xc4,0xe2,0x7e,0x72,0xd3]
+ {vex} vcvtneps2bf16 xmm2, ymm3
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, xmmword ptr [rbp + 8*r14 + 268435456]
+// CHECK: encoding: [0xc4,0xa2,0x7a,0x72,0x94,0xf5,0x00,0x00,0x00,0x10]
+ {vex} vcvtneps2bf16 xmm2, xmmword ptr [rbp + 8*r14 + 268435456]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, xmmword ptr [r8 + 4*rax + 291]
+// CHECK: encoding: [0xc4,0xc2,0x7a,0x72,0x94,0x80,0x23,0x01,0x00,0x00]
+ {vex} vcvtneps2bf16 xmm2, xmmword ptr [r8 + 4*rax + 291]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, xmmword ptr [rip]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x15,0x00,0x00,0x00,0x00]
+ {vex} vcvtneps2bf16 xmm2, xmmword ptr [rip]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, xmmword ptr [2*rbp - 512]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x14,0x6d,0x00,0xfe,0xff,0xff]
+ {vex} vcvtneps2bf16 xmm2, xmmword ptr [2*rbp - 512]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, xmmword ptr [rcx + 2032]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x91,0xf0,0x07,0x00,0x00]
+ {vex} vcvtneps2bf16 xmm2, xmmword ptr [rcx + 2032]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, xmmword ptr [rdx - 2048]
+// CHECK: encoding: [0xc4,0xe2,0x7a,0x72,0x92,0x00,0xf8,0xff,0xff]
+ {vex} vcvtneps2bf16 xmm2, xmmword ptr [rdx - 2048]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, ymmword ptr [2*rbp - 1024]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0x72,0x14,0x6d,0x00,0xfc,0xff,0xff]
+ {vex} vcvtneps2bf16 xmm2, ymmword ptr [2*rbp - 1024]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, ymmword ptr [rcx + 4064]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0x72,0x91,0xe0,0x0f,0x00,0x00]
+ {vex} vcvtneps2bf16 xmm2, ymmword ptr [rcx + 4064]
+
+// CHECK: {vex} vcvtneps2bf16 xmm2, ymmword ptr [rdx - 4096]
+// CHECK: encoding: [0xc4,0xe2,0x7e,0x72,0x92,0x00,0xf0,0xff,0xff]
+ {vex} vcvtneps2bf16 xmm2, ymmword ptr [rdx - 4096]
+