dyung created this revision.
This is the result of several patches we made internally to update the
documentation that we would like to have reviewed for possible submission.
The changes include:
1. Fix inaccurate instruction listings.
2. Fix small issues in _mm_getcsr and _mm_setcsr.
3. Fix description of NaN handling in comparison intrinsics.
4. Fix inaccurate description of _mm_movemask_pi8.
5. Fix inaccurate instruction mappings.
6. Fix typos.
7. Clarify wording on some descriptions.
8. Fix bit ranges in return value.
9. Fix typo in _mm_move_ms intrinsic instruction since it operates on
singe-precision values, not double.
These patches were made by Craig Flores
https://reviews.llvm.org/D41523
Files:
lib/Headers/xmmintrin.h
Index: lib/Headers/xmmintrin.h
===================================================================
--- lib/Headers/xmmintrin.h
+++ lib/Headers/xmmintrin.h
@@ -1011,6 +1011,8 @@
/// \brief Compares two 32-bit float values in the low-order bits of both
/// operands for equality and returns the result of the comparison.
///
+/// If either of the two lower 32-bit values is NaN, 0 is returned.
+///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCOMISS / COMISS </c>
@@ -1022,7 +1024,8 @@
/// \param __b
/// A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
/// used in the comparison.
-/// \returns An integer containing the comparison results.
+/// \returns An integer containing the comparison results. If either of the
+/// two lower 32-bit values is NaN, 0 is returned.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_comieq_ss(__m128 __a, __m128 __b)
{
@@ -1033,6 +1036,8 @@
/// operands to determine if the first operand is less than the second
/// operand and returns the result of the comparison.
///
+/// If either of the two lower 32-bit values is NaN, 0 is returned.
+///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCOMISS / COMISS </c>
@@ -1044,7 +1049,8 @@
/// \param __b
/// A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
/// used in the comparison.
-/// \returns An integer containing the comparison results.
+/// \returns An integer containing the comparison results. If either of the two
+/// lower 32-bit values is NaN, 0 is returned.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_comilt_ss(__m128 __a, __m128 __b)
{
@@ -1055,6 +1061,8 @@
/// operands to determine if the first operand is less than or equal to the
/// second operand and returns the result of the comparison.
///
+/// If either of the two lower 32-bit values is NaN, 0 is returned.
+///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCOMISS / COMISS </c> instructions.
@@ -1065,7 +1073,8 @@
/// \param __b
/// A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
/// used in the comparison.
-/// \returns An integer containing the comparison results.
+/// \returns An integer containing the comparison results. If either of the two
+/// lower 32-bit values is NaN, 0 is returned.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_comile_ss(__m128 __a, __m128 __b)
{
@@ -1076,6 +1085,8 @@
/// operands to determine if the first operand is greater than the second
/// operand and returns the result of the comparison.
///
+/// If either of the two lower 32-bit values is NaN, 0 is returned.
+///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCOMISS / COMISS </c> instructions.
@@ -1086,7 +1097,8 @@
/// \param __b
/// A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
/// used in the comparison.
-/// \returns An integer containing the comparison results.
+/// \returns An integer containing the comparison results. If either of the
+/// two lower 32-bit values is NaN, 0 is returned.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_comigt_ss(__m128 __a, __m128 __b)
{
@@ -1097,6 +1109,8 @@
/// operands to determine if the first operand is greater than or equal to
/// the second operand and returns the result of the comparison.
///
+/// If either of the two lower 32-bit values is NaN, 0 is returned.
+///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCOMISS / COMISS </c> instructions.
@@ -1107,7 +1121,8 @@
/// \param __b
/// A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
/// used in the comparison.
-/// \returns An integer containing the comparison results.
+/// \returns An integer containing the comparison results. If either of the two
+/// lower 32-bit values is NaN, 0 is returned.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_comige_ss(__m128 __a, __m128 __b)
{
@@ -1118,6 +1133,8 @@
/// operands to determine if the first operand is not equal to the second
/// operand and returns the result of the comparison.
///
+/// If either of the two lower 32-bit values is NaN, 1 is returned.
+///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VCOMISS / COMISS </c> instructions.
@@ -1128,7 +1145,8 @@
/// \param __b
/// A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
/// used in the comparison.
-/// \returns An integer containing the comparison results.
+/// \returns An integer containing the comparison results. If either of the
+/// two lower 32-bit values is NaN, 1 is returned.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_comineq_ss(__m128 __a, __m128 __b)
{
@@ -1139,6 +1157,8 @@
/// the low-order bits of both operands to determine equality and returns
/// the result of the comparison.
///
+/// If either of the two lower 32-bit values is NaN, 0 is returned.
+///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VUCOMISS / UCOMISS </c> instructions.
@@ -1149,7 +1169,8 @@
/// \param __b
/// A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
/// used in the comparison.
-/// \returns An integer containing the comparison results.
+/// \returns An integer containing the comparison results. If either of the two
+/// lower 32-bit values is NaN, 0 is returned.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_ucomieq_ss(__m128 __a, __m128 __b)
{
@@ -1160,6 +1181,8 @@
/// the low-order bits of both operands to determine if the first operand is
/// less than the second operand and returns the result of the comparison.
///
+/// If either of the two lower 32-bit values is NaN, 0 is returned.
+///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VUCOMISS / UCOMISS </c> instructions.
@@ -1170,7 +1193,8 @@
/// \param __b
/// A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
/// used in the comparison.
-/// \returns An integer containing the comparison results.
+/// \returns An integer containing the comparison results. If either of the two
+/// lower 32-bit values is NaN, 0 is returned.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_ucomilt_ss(__m128 __a, __m128 __b)
{
@@ -1182,6 +1206,8 @@
/// less than or equal to the second operand and returns the result of the
/// comparison.
///
+/// If either of the two lower 32-bit values is NaN, 0 is returned.
+///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VUCOMISS / UCOMISS </c> instructions.
@@ -1192,7 +1218,8 @@
/// \param __b
/// A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
/// used in the comparison.
-/// \returns An integer containing the comparison results.
+/// \returns An integer containing the comparison results. If either of the two
+/// lower 32-bit values is NaN, 0 is returned.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_ucomile_ss(__m128 __a, __m128 __b)
{
@@ -1204,6 +1231,8 @@
/// greater than the second operand and returns the result of the
/// comparison.
///
+/// If either of the two lower 32-bit values is NaN, 0 is returned.
+///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VUCOMISS / UCOMISS </c> instructions.
@@ -1214,7 +1243,8 @@
/// \param __b
/// A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
/// used in the comparison.
-/// \returns An integer containing the comparison results.
+/// \returns An integer containing the comparison results. If either of the two
+/// lower 32-bit values is NaN, 0 is returned.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_ucomigt_ss(__m128 __a, __m128 __b)
{
@@ -1226,6 +1256,8 @@
/// greater than or equal to the second operand and returns the result of
/// the comparison.
///
+/// If either of the two lower 32-bit values is NaN, 0 is returned.
+///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VUCOMISS / UCOMISS </c> instructions.
@@ -1236,7 +1268,8 @@
/// \param __b
/// A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
/// used in the comparison.
-/// \returns An integer containing the comparison results.
+/// \returns An integer containing the comparison results. If either of the two
+/// lower 32-bit values is NaN, 0 is returned.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_ucomige_ss(__m128 __a, __m128 __b)
{
@@ -1247,6 +1280,8 @@
/// the low-order bits of both operands to determine inequality and returns
/// the result of the comparison.
///
+/// If either of the two lower 32-bit values is NaN, 1 is returned.
+///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> VUCOMISS / UCOMISS </c> instructions.
@@ -1257,7 +1292,8 @@
/// \param __b
/// A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
/// used in the comparison.
-/// \returns An integer containing the comparison results.
+/// \returns An integer containing the comparison results. If either of the two
+/// lower 32-bit values is NaN, 1 is returned.
static __inline__ int __DEFAULT_FN_ATTRS
_mm_ucomineq_ss(__m128 __a, __m128 __b)
{
@@ -1571,7 +1607,7 @@
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VMOVSS / MOVSS </c> instruction.
+/// This intrinsic has no corresponding instruction.
///
/// \param __a
/// A 128-bit vector of [4 x float]. The lower 32 bits of this operand are
@@ -1667,7 +1703,7 @@
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VMOVSS / MOVSS + shuffling </c>
+/// This intrinsic corresponds to the <c> VBROADCASTSS / BROADCASTSS </c>
/// instruction.
///
/// \param __p
@@ -1696,7 +1732,7 @@
/// \param __p
/// A pointer to a 128-bit memory location. The address of the memory
/// location has to be 128-bit aligned.
-/// \returns A 128-bit vector of [4 x float] containing the loaded valus.
+/// \returns A 128-bit vector of [4 x float] containing the loaded values.
static __inline__ __m128 __DEFAULT_FN_ATTRS
_mm_load_ps(const float *__p)
{
@@ -1888,7 +1924,7 @@
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VPEXTRQ / MOVQ </c> instruction.
+/// This intrinsic corresponds to the <c> VPEXTRQ / PEXTRQ </c> instruction.
///
/// \param __p
/// A pointer to a 64-bit memory location.
@@ -2160,7 +2196,7 @@
/// __m64 _mm_insert_pi16(__m64 a, int d, int n);
/// \endcode
///
-/// This intrinsic corresponds to the <c> VPINSRW / PINSRW </c> instruction.
+/// This intrinsic corresponds to the <c> PINSRW </c> instruction.
///
/// \param a
/// A 64-bit vector of [4 x i16].
@@ -2258,17 +2294,17 @@
}
/// \brief Takes the most significant bit from each 8-bit element in a 64-bit
-/// integer vector to create a 16-bit mask value. Zero-extends the value to
+/// integer vector to create an 8-bit mask value. Zero-extends the value to
/// 32-bit integer and writes it to the destination.
///
/// \headerfile <x86intrin.h>
///
/// This intrinsic corresponds to the <c> PMOVMSKB </c> instruction.
///
/// \param __a
/// A 64-bit integer vector containing the values with bits to be extracted.
-/// \returns The most significant bit from each 8-bit element in the operand,
-/// written to bits [15:0].
+/// \returns The most significant bit from each 8-bit element in \a __a,
+/// written to bits [7:0].
static __inline__ int __DEFAULT_FN_ATTRS
_mm_movemask_pi8(__m64 __a)
{
@@ -2441,7 +2477,7 @@
/// <li>
/// For checking rounding modes: _MM_ROUND_NEAREST, _MM_ROUND_DOWN,
/// _MM_ROUND_UP, _MM_ROUND_TOWARD_ZERO. There is a convenience wrapper
-/// _MM_GET_ROUNDING_MODE(x) where x is one of these macros.
+/// _MM_GET_ROUNDING_MODE().
/// </li>
/// <li>
/// For checking flush-to-zero mode: _MM_FLUSH_ZERO_ON, _MM_FLUSH_ZERO_OFF.
@@ -2454,11 +2490,11 @@
/// </li>
/// </ul>
///
-/// For example, the expression below checks if an overflow exception has
+/// For example, the following expression checks if an overflow exception has
/// occurred:
/// ( _mm_getcsr() & _MM_EXCEPT_OVERFLOW )
///
-/// The following example gets the current rounding mode:
+/// The following expression gets the current rounding mode:
/// _MM_GET_ROUNDING_MODE()
///
/// \headerfile <x86intrin.h>
@@ -2508,10 +2544,12 @@
/// _mm_setcsr(_mm_getcsr() | _MM_ROUND_UP)
///
/// The following example sets the DAZ and FTZ flags:
-/// void setFlags() {
-/// _MM_SET_FLUSH_ZERO_MODE(_MM_FLUSH_ZERO_ON)
-/// _MM_SET_DENORMALS_ZERO_MODE(_MM_DENORMALS_ZERO_ON)
-/// }
+/// \code
+/// void setFlags() {
+/// _MM_SET_FLUSH_ZERO_MODE(_MM_FLUSH_ZERO_ON);
+/// _MM_SET_DENORMALS_ZERO_MODE(_MM_DENORMALS_ZERO_ON);
+/// }
+/// \endcode
///
/// \headerfile <x86intrin.h>
///
@@ -2618,7 +2656,7 @@
///
/// \headerfile <x86intrin.h>
///
-/// This intrinsic corresponds to the <c> VMOVSS / MOVSS </c> instruction.
+/// This intrinsic corresponds to the <c> VBLENDPS / BLENDPS </c> instruction.
///
/// \param __a
/// A 128-bit floating-point vector of [4 x float]. The upper 96 bits are
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
