[clang] [X86] Change target of __builtin_ia32_cmp[p|s][s|d] from avx into sse/sse2 (PR #67410)
Freddy Ye via cfe-commits
cfe-commits at lists.llvm.org
Wed Sep 27 00:32:12 PDT 2023
https://github.com/FreddyLeaf updated https://github.com/llvm/llvm-project/pull/67410
>From 3ae0fa2592d3a11dd084d3aefb54c26819016781 Mon Sep 17 00:00:00 2001
From: Freddy Ye <freddy.ye at intel.com>
Date: Tue, 26 Sep 2023 16:44:01 +0800
Subject: [PATCH 1/5] [X86] Change target of __builtin_ia32_cmp[p|s][s|d] from
avx into sse/sse2
---
clang/include/clang/Basic/BuiltinsX86.def | 8 +-
clang/lib/Headers/avxintrin.h | 272 -------------
clang/lib/Headers/emmintrin.h | 119 ++++++
clang/lib/Headers/xmmintrin.h | 152 +++++++
clang/test/CodeGen/X86/avx-builtins.c | 396 -------------------
clang/test/CodeGen/X86/sse-builtins.c | 198 ++++++++++
clang/test/CodeGen/X86/sse2-builtins.c | 198 ++++++++++
clang/test/CodeGen/target-features-error-2.c | 4 +-
8 files changed, 673 insertions(+), 674 deletions(-)
diff --git a/clang/include/clang/Basic/BuiltinsX86.def b/clang/include/clang/Basic/BuiltinsX86.def
index e4802f8ab1c1562..6bbbc4bbdd75c68 100644
--- a/clang/include/clang/Basic/BuiltinsX86.def
+++ b/clang/include/clang/Basic/BuiltinsX86.def
@@ -233,6 +233,8 @@ TARGET_BUILTIN(__builtin_ia32_minps, "V4fV4fV4f", "ncV:128:", "sse")
TARGET_BUILTIN(__builtin_ia32_maxps, "V4fV4fV4f", "ncV:128:", "sse")
TARGET_BUILTIN(__builtin_ia32_minss, "V4fV4fV4f", "ncV:128:", "sse")
TARGET_BUILTIN(__builtin_ia32_maxss, "V4fV4fV4f", "ncV:128:", "sse")
+TARGET_BUILTIN(__builtin_ia32_cmpps, "V4fV4fV4fIc", "ncV:128:", "sse")
+TARGET_BUILTIN(__builtin_ia32_cmpss, "V4fV4fV4fIc", "ncV:128:", "sse")
TARGET_BUILTIN(__builtin_ia32_cmpeqpd, "V2dV2dV2d", "ncV:128:", "sse2")
TARGET_BUILTIN(__builtin_ia32_cmpltpd, "V2dV2dV2d", "ncV:128:", "sse2")
@@ -250,6 +252,8 @@ TARGET_BUILTIN(__builtin_ia32_cmpneqsd, "V2dV2dV2d", "ncV:128:", "sse2")
TARGET_BUILTIN(__builtin_ia32_cmpnltsd, "V2dV2dV2d", "ncV:128:", "sse2")
TARGET_BUILTIN(__builtin_ia32_cmpnlesd, "V2dV2dV2d", "ncV:128:", "sse2")
TARGET_BUILTIN(__builtin_ia32_cmpordsd, "V2dV2dV2d", "ncV:128:", "sse2")
+TARGET_BUILTIN(__builtin_ia32_cmpsd, "V2dV2dV2dIc", "ncV:128:", "sse2")
+TARGET_BUILTIN(__builtin_ia32_cmppd, "V2dV2dV2dIc", "ncV:128:", "sse2")
TARGET_BUILTIN(__builtin_ia32_minpd, "V2dV2dV2d", "ncV:128:", "sse2")
TARGET_BUILTIN(__builtin_ia32_maxpd, "V2dV2dV2d", "ncV:128:", "sse2")
TARGET_BUILTIN(__builtin_ia32_minsd, "V2dV2dV2d", "ncV:128:", "sse2")
@@ -469,12 +473,8 @@ TARGET_BUILTIN(__builtin_ia32_blendvps256, "V8fV8fV8fV8f", "ncV:256:", "avx")
TARGET_BUILTIN(__builtin_ia32_shufpd256, "V4dV4dV4dIi", "ncV:256:", "avx")
TARGET_BUILTIN(__builtin_ia32_shufps256, "V8fV8fV8fIi", "ncV:256:", "avx")
TARGET_BUILTIN(__builtin_ia32_dpps256, "V8fV8fV8fIc", "ncV:256:", "avx")
-TARGET_BUILTIN(__builtin_ia32_cmppd, "V2dV2dV2dIc", "ncV:128:", "avx")
TARGET_BUILTIN(__builtin_ia32_cmppd256, "V4dV4dV4dIc", "ncV:256:", "avx")
-TARGET_BUILTIN(__builtin_ia32_cmpps, "V4fV4fV4fIc", "ncV:128:", "avx")
TARGET_BUILTIN(__builtin_ia32_cmpps256, "V8fV8fV8fIc", "ncV:256:", "avx")
-TARGET_BUILTIN(__builtin_ia32_cmpsd, "V2dV2dV2dIc", "ncV:128:", "avx")
-TARGET_BUILTIN(__builtin_ia32_cmpss, "V4fV4fV4fIc", "ncV:128:", "avx")
TARGET_BUILTIN(__builtin_ia32_vextractf128_pd256, "V2dV4dIi", "ncV:256:", "avx")
TARGET_BUILTIN(__builtin_ia32_vextractf128_ps256, "V4fV8fIi", "ncV:256:", "avx")
TARGET_BUILTIN(__builtin_ia32_vextractf128_si256, "V4iV8iIi", "ncV:256:", "avx")
diff --git a/clang/lib/Headers/avxintrin.h b/clang/lib/Headers/avxintrin.h
index b796bb773ec11f0..afbf26403f201b6 100644
--- a/clang/lib/Headers/avxintrin.h
+++ b/clang/lib/Headers/avxintrin.h
@@ -1569,160 +1569,6 @@ _mm256_blendv_ps(__m256 __a, __m256 __b, __m256 __c)
((__m256d)__builtin_ia32_shufpd256((__v4df)(__m256d)(a), \
(__v4df)(__m256d)(b), (int)(mask)))
-/* Compare */
-#define _CMP_EQ_OQ 0x00 /* Equal (ordered, non-signaling) */
-#define _CMP_LT_OS 0x01 /* Less-than (ordered, signaling) */
-#define _CMP_LE_OS 0x02 /* Less-than-or-equal (ordered, signaling) */
-#define _CMP_UNORD_Q 0x03 /* Unordered (non-signaling) */
-#define _CMP_NEQ_UQ 0x04 /* Not-equal (unordered, non-signaling) */
-#define _CMP_NLT_US 0x05 /* Not-less-than (unordered, signaling) */
-#define _CMP_NLE_US 0x06 /* Not-less-than-or-equal (unordered, signaling) */
-#define _CMP_ORD_Q 0x07 /* Ordered (non-signaling) */
-#define _CMP_EQ_UQ 0x08 /* Equal (unordered, non-signaling) */
-#define _CMP_NGE_US 0x09 /* Not-greater-than-or-equal (unordered, signaling) */
-#define _CMP_NGT_US 0x0a /* Not-greater-than (unordered, signaling) */
-#define _CMP_FALSE_OQ 0x0b /* False (ordered, non-signaling) */
-#define _CMP_NEQ_OQ 0x0c /* Not-equal (ordered, non-signaling) */
-#define _CMP_GE_OS 0x0d /* Greater-than-or-equal (ordered, signaling) */
-#define _CMP_GT_OS 0x0e /* Greater-than (ordered, signaling) */
-#define _CMP_TRUE_UQ 0x0f /* True (unordered, non-signaling) */
-#define _CMP_EQ_OS 0x10 /* Equal (ordered, signaling) */
-#define _CMP_LT_OQ 0x11 /* Less-than (ordered, non-signaling) */
-#define _CMP_LE_OQ 0x12 /* Less-than-or-equal (ordered, non-signaling) */
-#define _CMP_UNORD_S 0x13 /* Unordered (signaling) */
-#define _CMP_NEQ_US 0x14 /* Not-equal (unordered, signaling) */
-#define _CMP_NLT_UQ 0x15 /* Not-less-than (unordered, non-signaling) */
-#define _CMP_NLE_UQ 0x16 /* Not-less-than-or-equal (unordered, non-signaling) */
-#define _CMP_ORD_S 0x17 /* Ordered (signaling) */
-#define _CMP_EQ_US 0x18 /* Equal (unordered, signaling) */
-#define _CMP_NGE_UQ 0x19 /* Not-greater-than-or-equal (unordered, non-signaling) */
-#define _CMP_NGT_UQ 0x1a /* Not-greater-than (unordered, non-signaling) */
-#define _CMP_FALSE_OS 0x1b /* False (ordered, signaling) */
-#define _CMP_NEQ_OS 0x1c /* Not-equal (ordered, signaling) */
-#define _CMP_GE_OQ 0x1d /* Greater-than-or-equal (ordered, non-signaling) */
-#define _CMP_GT_OQ 0x1e /* Greater-than (ordered, non-signaling) */
-#define _CMP_TRUE_US 0x1f /* True (unordered, signaling) */
-
-/// Compares each of the corresponding double-precision values of two
-/// 128-bit vectors of [2 x double], using the operation specified by the
-/// immediate integer operand.
-///
-/// Returns a [2 x double] vector consisting of two doubles corresponding to
-/// the two comparison results: zero if the comparison is false, and all 1's
-/// if the comparison is true.
-///
-/// \headerfile <x86intrin.h>
-///
-/// \code
-/// __m128d _mm_cmp_pd(__m128d a, __m128d b, const int c);
-/// \endcode
-///
-/// This intrinsic corresponds to the <c> VCMPPD </c> instruction.
-///
-/// \param a
-/// A 128-bit vector of [2 x double].
-/// \param b
-/// A 128-bit vector of [2 x double].
-/// \param c
-/// An immediate integer operand, with bits [4:0] specifying which comparison
-/// operation to use: \n
-/// 0x00: Equal (ordered, non-signaling) \n
-/// 0x01: Less-than (ordered, signaling) \n
-/// 0x02: Less-than-or-equal (ordered, signaling) \n
-/// 0x03: Unordered (non-signaling) \n
-/// 0x04: Not-equal (unordered, non-signaling) \n
-/// 0x05: Not-less-than (unordered, signaling) \n
-/// 0x06: Not-less-than-or-equal (unordered, signaling) \n
-/// 0x07: Ordered (non-signaling) \n
-/// 0x08: Equal (unordered, non-signaling) \n
-/// 0x09: Not-greater-than-or-equal (unordered, signaling) \n
-/// 0x0A: Not-greater-than (unordered, signaling) \n
-/// 0x0B: False (ordered, non-signaling) \n
-/// 0x0C: Not-equal (ordered, non-signaling) \n
-/// 0x0D: Greater-than-or-equal (ordered, signaling) \n
-/// 0x0E: Greater-than (ordered, signaling) \n
-/// 0x0F: True (unordered, non-signaling) \n
-/// 0x10: Equal (ordered, signaling) \n
-/// 0x11: Less-than (ordered, non-signaling) \n
-/// 0x12: Less-than-or-equal (ordered, non-signaling) \n
-/// 0x13: Unordered (signaling) \n
-/// 0x14: Not-equal (unordered, signaling) \n
-/// 0x15: Not-less-than (unordered, non-signaling) \n
-/// 0x16: Not-less-than-or-equal (unordered, non-signaling) \n
-/// 0x17: Ordered (signaling) \n
-/// 0x18: Equal (unordered, signaling) \n
-/// 0x19: Not-greater-than-or-equal (unordered, non-signaling) \n
-/// 0x1A: Not-greater-than (unordered, non-signaling) \n
-/// 0x1B: False (ordered, signaling) \n
-/// 0x1C: Not-equal (ordered, signaling) \n
-/// 0x1D: Greater-than-or-equal (ordered, non-signaling) \n
-/// 0x1E: Greater-than (ordered, non-signaling) \n
-/// 0x1F: True (unordered, signaling)
-/// \returns A 128-bit vector of [2 x double] containing the comparison results.
-#define _mm_cmp_pd(a, b, c) \
- ((__m128d)__builtin_ia32_cmppd((__v2df)(__m128d)(a), \
- (__v2df)(__m128d)(b), (c)))
-
-/// Compares each of the corresponding values of two 128-bit vectors of
-/// [4 x float], using the operation specified by the immediate integer
-/// operand.
-///
-/// Returns a [4 x float] vector consisting of four floats corresponding to
-/// the four comparison results: zero if the comparison is false, and all 1's
-/// if the comparison is true.
-///
-/// \headerfile <x86intrin.h>
-///
-/// \code
-/// __m128 _mm_cmp_ps(__m128 a, __m128 b, const int c);
-/// \endcode
-///
-/// This intrinsic corresponds to the <c> VCMPPS </c> instruction.
-///
-/// \param a
-/// A 128-bit vector of [4 x float].
-/// \param b
-/// A 128-bit vector of [4 x float].
-/// \param c
-/// An immediate integer operand, with bits [4:0] specifying which comparison
-/// operation to use: \n
-/// 0x00: Equal (ordered, non-signaling) \n
-/// 0x01: Less-than (ordered, signaling) \n
-/// 0x02: Less-than-or-equal (ordered, signaling) \n
-/// 0x03: Unordered (non-signaling) \n
-/// 0x04: Not-equal (unordered, non-signaling) \n
-/// 0x05: Not-less-than (unordered, signaling) \n
-/// 0x06: Not-less-than-or-equal (unordered, signaling) \n
-/// 0x07: Ordered (non-signaling) \n
-/// 0x08: Equal (unordered, non-signaling) \n
-/// 0x09: Not-greater-than-or-equal (unordered, signaling) \n
-/// 0x0A: Not-greater-than (unordered, signaling) \n
-/// 0x0B: False (ordered, non-signaling) \n
-/// 0x0C: Not-equal (ordered, non-signaling) \n
-/// 0x0D: Greater-than-or-equal (ordered, signaling) \n
-/// 0x0E: Greater-than (ordered, signaling) \n
-/// 0x0F: True (unordered, non-signaling) \n
-/// 0x10: Equal (ordered, signaling) \n
-/// 0x11: Less-than (ordered, non-signaling) \n
-/// 0x12: Less-than-or-equal (ordered, non-signaling) \n
-/// 0x13: Unordered (signaling) \n
-/// 0x14: Not-equal (unordered, signaling) \n
-/// 0x15: Not-less-than (unordered, non-signaling) \n
-/// 0x16: Not-less-than-or-equal (unordered, non-signaling) \n
-/// 0x17: Ordered (signaling) \n
-/// 0x18: Equal (unordered, signaling) \n
-/// 0x19: Not-greater-than-or-equal (unordered, non-signaling) \n
-/// 0x1A: Not-greater-than (unordered, non-signaling) \n
-/// 0x1B: False (ordered, signaling) \n
-/// 0x1C: Not-equal (ordered, signaling) \n
-/// 0x1D: Greater-than-or-equal (ordered, non-signaling) \n
-/// 0x1E: Greater-than (ordered, non-signaling) \n
-/// 0x1F: True (unordered, signaling)
-/// \returns A 128-bit vector of [4 x float] containing the comparison results.
-#define _mm_cmp_ps(a, b, c) \
- ((__m128)__builtin_ia32_cmpps((__v4sf)(__m128)(a), \
- (__v4sf)(__m128)(b), (c)))
-
/// Compares each of the corresponding double-precision values of two
/// 256-bit vectors of [4 x double], using the operation specified by the
/// immediate integer operand.
@@ -1843,124 +1689,6 @@ _mm256_blendv_ps(__m256 __a, __m256 __b, __m256 __c)
((__m256)__builtin_ia32_cmpps256((__v8sf)(__m256)(a), \
(__v8sf)(__m256)(b), (c)))
-/// Compares each of the corresponding scalar double-precision values of
-/// two 128-bit vectors of [2 x double], using the operation specified by the
-/// immediate integer operand.
-///
-/// If the result is true, all 64 bits of the destination vector are set;
-/// otherwise they are cleared.
-///
-/// \headerfile <x86intrin.h>
-///
-/// \code
-/// __m128d _mm_cmp_sd(__m128d a, __m128d b, const int c);
-/// \endcode
-///
-/// This intrinsic corresponds to the <c> VCMPSD </c> instruction.
-///
-/// \param a
-/// A 128-bit vector of [2 x double].
-/// \param b
-/// A 128-bit vector of [2 x double].
-/// \param c
-/// An immediate integer operand, with bits [4:0] specifying which comparison
-/// operation to use: \n
-/// 0x00: Equal (ordered, non-signaling) \n
-/// 0x01: Less-than (ordered, signaling) \n
-/// 0x02: Less-than-or-equal (ordered, signaling) \n
-/// 0x03: Unordered (non-signaling) \n
-/// 0x04: Not-equal (unordered, non-signaling) \n
-/// 0x05: Not-less-than (unordered, signaling) \n
-/// 0x06: Not-less-than-or-equal (unordered, signaling) \n
-/// 0x07: Ordered (non-signaling) \n
-/// 0x08: Equal (unordered, non-signaling) \n
-/// 0x09: Not-greater-than-or-equal (unordered, signaling) \n
-/// 0x0A: Not-greater-than (unordered, signaling) \n
-/// 0x0B: False (ordered, non-signaling) \n
-/// 0x0C: Not-equal (ordered, non-signaling) \n
-/// 0x0D: Greater-than-or-equal (ordered, signaling) \n
-/// 0x0E: Greater-than (ordered, signaling) \n
-/// 0x0F: True (unordered, non-signaling) \n
-/// 0x10: Equal (ordered, signaling) \n
-/// 0x11: Less-than (ordered, non-signaling) \n
-/// 0x12: Less-than-or-equal (ordered, non-signaling) \n
-/// 0x13: Unordered (signaling) \n
-/// 0x14: Not-equal (unordered, signaling) \n
-/// 0x15: Not-less-than (unordered, non-signaling) \n
-/// 0x16: Not-less-than-or-equal (unordered, non-signaling) \n
-/// 0x17: Ordered (signaling) \n
-/// 0x18: Equal (unordered, signaling) \n
-/// 0x19: Not-greater-than-or-equal (unordered, non-signaling) \n
-/// 0x1A: Not-greater-than (unordered, non-signaling) \n
-/// 0x1B: False (ordered, signaling) \n
-/// 0x1C: Not-equal (ordered, signaling) \n
-/// 0x1D: Greater-than-or-equal (ordered, non-signaling) \n
-/// 0x1E: Greater-than (ordered, non-signaling) \n
-/// 0x1F: True (unordered, signaling)
-/// \returns A 128-bit vector of [2 x double] containing the comparison results.
-#define _mm_cmp_sd(a, b, c) \
- ((__m128d)__builtin_ia32_cmpsd((__v2df)(__m128d)(a), \
- (__v2df)(__m128d)(b), (c)))
-
-/// Compares each of the corresponding scalar values of two 128-bit
-/// vectors of [4 x float], using the operation specified by the immediate
-/// integer operand.
-///
-/// If the result is true, all 32 bits of the destination vector are set;
-/// otherwise they are cleared.
-///
-/// \headerfile <x86intrin.h>
-///
-/// \code
-/// __m128 _mm_cmp_ss(__m128 a, __m128 b, const int c);
-/// \endcode
-///
-/// This intrinsic corresponds to the <c> VCMPSS </c> instruction.
-///
-/// \param a
-/// A 128-bit vector of [4 x float].
-/// \param b
-/// A 128-bit vector of [4 x float].
-/// \param c
-/// An immediate integer operand, with bits [4:0] specifying which comparison
-/// operation to use: \n
-/// 0x00: Equal (ordered, non-signaling) \n
-/// 0x01: Less-than (ordered, signaling) \n
-/// 0x02: Less-than-or-equal (ordered, signaling) \n
-/// 0x03: Unordered (non-signaling) \n
-/// 0x04: Not-equal (unordered, non-signaling) \n
-/// 0x05: Not-less-than (unordered, signaling) \n
-/// 0x06: Not-less-than-or-equal (unordered, signaling) \n
-/// 0x07: Ordered (non-signaling) \n
-/// 0x08: Equal (unordered, non-signaling) \n
-/// 0x09: Not-greater-than-or-equal (unordered, signaling) \n
-/// 0x0A: Not-greater-than (unordered, signaling) \n
-/// 0x0B: False (ordered, non-signaling) \n
-/// 0x0C: Not-equal (ordered, non-signaling) \n
-/// 0x0D: Greater-than-or-equal (ordered, signaling) \n
-/// 0x0E: Greater-than (ordered, signaling) \n
-/// 0x0F: True (unordered, non-signaling) \n
-/// 0x10: Equal (ordered, signaling) \n
-/// 0x11: Less-than (ordered, non-signaling) \n
-/// 0x12: Less-than-or-equal (ordered, non-signaling) \n
-/// 0x13: Unordered (signaling) \n
-/// 0x14: Not-equal (unordered, signaling) \n
-/// 0x15: Not-less-than (unordered, non-signaling) \n
-/// 0x16: Not-less-than-or-equal (unordered, non-signaling) \n
-/// 0x17: Ordered (signaling) \n
-/// 0x18: Equal (unordered, signaling) \n
-/// 0x19: Not-greater-than-or-equal (unordered, non-signaling) \n
-/// 0x1A: Not-greater-than (unordered, non-signaling) \n
-/// 0x1B: False (ordered, signaling) \n
-/// 0x1C: Not-equal (ordered, signaling) \n
-/// 0x1D: Greater-than-or-equal (ordered, non-signaling) \n
-/// 0x1E: Greater-than (ordered, non-signaling) \n
-/// 0x1F: True (unordered, signaling)
-/// \returns A 128-bit vector of [4 x float] containing the comparison results.
-#define _mm_cmp_ss(a, b, c) \
- ((__m128)__builtin_ia32_cmpss((__v4sf)(__m128)(a), \
- (__v4sf)(__m128)(b), (c)))
-
/// Takes a [8 x i32] vector and returns the vector element value
/// indexed by the immediate constant operand.
///
diff --git a/clang/lib/Headers/emmintrin.h b/clang/lib/Headers/emmintrin.h
index 8de2864b110653f..3e103ee7a24b69c 100644
--- a/clang/lib/Headers/emmintrin.h
+++ b/clang/lib/Headers/emmintrin.h
@@ -4742,6 +4742,125 @@ static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_castsi128_pd(__m128i __a) {
return (__m128d)__a;
}
+/// Compares each of the corresponding double-precision values of two
+/// 128-bit vectors of [2 x double], using the operation specified by the
+/// immediate integer operand.
+///
+/// Returns a [2 x double] vector consisting of two doubles corresponding to
+/// the two comparison results: zero if the comparison is false, and all 1's
+/// if the comparison is true.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// __m128d _mm_cmp_pd(__m128d a, __m128d b, const int c);
+/// \endcode
+///
+/// This intrinsic corresponds to the <c> VCMPPD </c> instruction.
+///
+/// \param a
+/// A 128-bit vector of [2 x double].
+/// \param b
+/// A 128-bit vector of [2 x double].
+/// \param c
+/// An immediate integer operand, with bits [4:0] specifying which comparison
+/// operation to use: \n
+/// 0x00: Equal (ordered, non-signaling) \n
+/// 0x01: Less-than (ordered, signaling) \n
+/// 0x02: Less-than-or-equal (ordered, signaling) \n
+/// 0x03: Unordered (non-signaling) \n
+/// 0x04: Not-equal (unordered, non-signaling) \n
+/// 0x05: Not-less-than (unordered, signaling) \n
+/// 0x06: Not-less-than-or-equal (unordered, signaling) \n
+/// 0x07: Ordered (non-signaling) \n
+/// 0x08: Equal (unordered, non-signaling) \n
+/// 0x09: Not-greater-than-or-equal (unordered, signaling) \n
+/// 0x0A: Not-greater-than (unordered, signaling) \n
+/// 0x0B: False (ordered, non-signaling) \n
+/// 0x0C: Not-equal (ordered, non-signaling) \n
+/// 0x0D: Greater-than-or-equal (ordered, signaling) \n
+/// 0x0E: Greater-than (ordered, signaling) \n
+/// 0x0F: True (unordered, non-signaling) \n
+/// 0x10: Equal (ordered, signaling) \n
+/// 0x11: Less-than (ordered, non-signaling) \n
+/// 0x12: Less-than-or-equal (ordered, non-signaling) \n
+/// 0x13: Unordered (signaling) \n
+/// 0x14: Not-equal (unordered, signaling) \n
+/// 0x15: Not-less-than (unordered, non-signaling) \n
+/// 0x16: Not-less-than-or-equal (unordered, non-signaling) \n
+/// 0x17: Ordered (signaling) \n
+/// 0x18: Equal (unordered, signaling) \n
+/// 0x19: Not-greater-than-or-equal (unordered, non-signaling) \n
+/// 0x1A: Not-greater-than (unordered, non-signaling) \n
+/// 0x1B: False (ordered, signaling) \n
+/// 0x1C: Not-equal (ordered, signaling) \n
+/// 0x1D: Greater-than-or-equal (ordered, non-signaling) \n
+/// 0x1E: Greater-than (ordered, non-signaling) \n
+/// 0x1F: True (unordered, signaling)
+/// \returns A 128-bit vector of [2 x double] containing the comparison results.
+#define _mm_cmp_pd(a, b, c) \
+ ((__m128d)__builtin_ia32_cmppd((__v2df)(__m128d)(a), \
+ (__v2df)(__m128d)(b), (c)))
+
+/// Compares each of the corresponding scalar double-precision values of
+/// two 128-bit vectors of [2 x double], using the operation specified by the
+/// immediate integer operand.
+///
+/// If the result is true, all 64 bits of the destination vector are set;
+/// otherwise they are cleared.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// __m128d _mm_cmp_sd(__m128d a, __m128d b, const int c);
+/// \endcode
+///
+/// This intrinsic corresponds to the <c> VCMPSD </c> instruction.
+///
+/// \param a
+/// A 128-bit vector of [2 x double].
+/// \param b
+/// A 128-bit vector of [2 x double].
+/// \param c
+/// An immediate integer operand, with bits [4:0] specifying which comparison
+/// operation to use: \n
+/// 0x00: Equal (ordered, non-signaling) \n
+/// 0x01: Less-than (ordered, signaling) \n
+/// 0x02: Less-than-or-equal (ordered, signaling) \n
+/// 0x03: Unordered (non-signaling) \n
+/// 0x04: Not-equal (unordered, non-signaling) \n
+/// 0x05: Not-less-than (unordered, signaling) \n
+/// 0x06: Not-less-than-or-equal (unordered, signaling) \n
+/// 0x07: Ordered (non-signaling) \n
+/// 0x08: Equal (unordered, non-signaling) \n
+/// 0x09: Not-greater-than-or-equal (unordered, signaling) \n
+/// 0x0A: Not-greater-than (unordered, signaling) \n
+/// 0x0B: False (ordered, non-signaling) \n
+/// 0x0C: Not-equal (ordered, non-signaling) \n
+/// 0x0D: Greater-than-or-equal (ordered, signaling) \n
+/// 0x0E: Greater-than (ordered, signaling) \n
+/// 0x0F: True (unordered, non-signaling) \n
+/// 0x10: Equal (ordered, signaling) \n
+/// 0x11: Less-than (ordered, non-signaling) \n
+/// 0x12: Less-than-or-equal (ordered, non-signaling) \n
+/// 0x13: Unordered (signaling) \n
+/// 0x14: Not-equal (unordered, signaling) \n
+/// 0x15: Not-less-than (unordered, non-signaling) \n
+/// 0x16: Not-less-than-or-equal (unordered, non-signaling) \n
+/// 0x17: Ordered (signaling) \n
+/// 0x18: Equal (unordered, signaling) \n
+/// 0x19: Not-greater-than-or-equal (unordered, non-signaling) \n
+/// 0x1A: Not-greater-than (unordered, non-signaling) \n
+/// 0x1B: False (ordered, signaling) \n
+/// 0x1C: Not-equal (ordered, signaling) \n
+/// 0x1D: Greater-than-or-equal (ordered, non-signaling) \n
+/// 0x1E: Greater-than (ordered, non-signaling) \n
+/// 0x1F: True (unordered, signaling)
+/// \returns A 128-bit vector of [2 x double] containing the comparison results.
+#define _mm_cmp_sd(a, b, c) \
+ ((__m128d)__builtin_ia32_cmpsd((__v2df)(__m128d)(a), \
+ (__v2df)(__m128d)(b), (c)))
+
#if defined(__cplusplus)
extern "C" {
#endif
diff --git a/clang/lib/Headers/xmmintrin.h b/clang/lib/Headers/xmmintrin.h
index 2d1d33c69f0bbdb..7b238d8ba000641 100644
--- a/clang/lib/Headers/xmmintrin.h
+++ b/clang/lib/Headers/xmmintrin.h
@@ -2936,6 +2936,158 @@ _mm_movemask_ps(__m128 __a)
return __builtin_ia32_movmskps((__v4sf)__a);
}
+/* Compare */
+#define _CMP_EQ_OQ 0x00 /* Equal (ordered, non-signaling) */
+#define _CMP_LT_OS 0x01 /* Less-than (ordered, signaling) */
+#define _CMP_LE_OS 0x02 /* Less-than-or-equal (ordered, signaling) */
+#define _CMP_UNORD_Q 0x03 /* Unordered (non-signaling) */
+#define _CMP_NEQ_UQ 0x04 /* Not-equal (unordered, non-signaling) */
+#define _CMP_NLT_US 0x05 /* Not-less-than (unordered, signaling) */
+#define _CMP_NLE_US 0x06 /* Not-less-than-or-equal (unordered, signaling) */
+#define _CMP_ORD_Q 0x07 /* Ordered (non-signaling) */
+#define _CMP_EQ_UQ 0x08 /* Equal (unordered, non-signaling) */
+#define _CMP_NGE_US 0x09 /* Not-greater-than-or-equal (unordered, signaling) */
+#define _CMP_NGT_US 0x0a /* Not-greater-than (unordered, signaling) */
+#define _CMP_FALSE_OQ 0x0b /* False (ordered, non-signaling) */
+#define _CMP_NEQ_OQ 0x0c /* Not-equal (ordered, non-signaling) */
+#define _CMP_GE_OS 0x0d /* Greater-than-or-equal (ordered, signaling) */
+#define _CMP_GT_OS 0x0e /* Greater-than (ordered, signaling) */
+#define _CMP_TRUE_UQ 0x0f /* True (unordered, non-signaling) */
+#define _CMP_EQ_OS 0x10 /* Equal (ordered, signaling) */
+#define _CMP_LT_OQ 0x11 /* Less-than (ordered, non-signaling) */
+#define _CMP_LE_OQ 0x12 /* Less-than-or-equal (ordered, non-signaling) */
+#define _CMP_UNORD_S 0x13 /* Unordered (signaling) */
+#define _CMP_NEQ_US 0x14 /* Not-equal (unordered, signaling) */
+#define _CMP_NLT_UQ 0x15 /* Not-less-than (unordered, non-signaling) */
+#define _CMP_NLE_UQ 0x16 /* Not-less-than-or-equal (unordered, non-signaling) */
+#define _CMP_ORD_S 0x17 /* Ordered (signaling) */
+#define _CMP_EQ_US 0x18 /* Equal (unordered, signaling) */
+#define _CMP_NGE_UQ 0x19 /* Not-greater-than-or-equal (unordered, non-signaling) */
+#define _CMP_NGT_UQ 0x1a /* Not-greater-than (unordered, non-signaling) */
+#define _CMP_FALSE_OS 0x1b /* False (ordered, signaling) */
+#define _CMP_NEQ_OS 0x1c /* Not-equal (ordered, signaling) */
+#define _CMP_GE_OQ 0x1d /* Greater-than-or-equal (ordered, non-signaling) */
+#define _CMP_GT_OQ 0x1e /* Greater-than (ordered, non-signaling) */
+#define _CMP_TRUE_US 0x1f /* True (unordered, signaling) */
+
+/// Compares each of the corresponding values of two 128-bit vectors of
+/// [4 x float], using the operation specified by the immediate integer
+/// operand.
+///
+/// Returns a [4 x float] vector consisting of four floats corresponding to
+/// the four comparison results: zero if the comparison is false, and all 1's
+/// if the comparison is true.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// __m128 _mm_cmp_ps(__m128 a, __m128 b, const int c);
+/// \endcode
+///
+/// This intrinsic corresponds to the <c> VCMPPS </c> instruction.
+///
+/// \param a
+/// A 128-bit vector of [4 x float].
+/// \param b
+/// A 128-bit vector of [4 x float].
+/// \param c
+/// An immediate integer operand, with bits [4:0] specifying which comparison
+/// operation to use: \n
+/// 0x00: Equal (ordered, non-signaling) \n
+/// 0x01: Less-than (ordered, signaling) \n
+/// 0x02: Less-than-or-equal (ordered, signaling) \n
+/// 0x03: Unordered (non-signaling) \n
+/// 0x04: Not-equal (unordered, non-signaling) \n
+/// 0x05: Not-less-than (unordered, signaling) \n
+/// 0x06: Not-less-than-or-equal (unordered, signaling) \n
+/// 0x07: Ordered (non-signaling) \n
+/// 0x08: Equal (unordered, non-signaling) \n
+/// 0x09: Not-greater-than-or-equal (unordered, signaling) \n
+/// 0x0A: Not-greater-than (unordered, signaling) \n
+/// 0x0B: False (ordered, non-signaling) \n
+/// 0x0C: Not-equal (ordered, non-signaling) \n
+/// 0x0D: Greater-than-or-equal (ordered, signaling) \n
+/// 0x0E: Greater-than (ordered, signaling) \n
+/// 0x0F: True (unordered, non-signaling) \n
+/// 0x10: Equal (ordered, signaling) \n
+/// 0x11: Less-than (ordered, non-signaling) \n
+/// 0x12: Less-than-or-equal (ordered, non-signaling) \n
+/// 0x13: Unordered (signaling) \n
+/// 0x14: Not-equal (unordered, signaling) \n
+/// 0x15: Not-less-than (unordered, non-signaling) \n
+/// 0x16: Not-less-than-or-equal (unordered, non-signaling) \n
+/// 0x17: Ordered (signaling) \n
+/// 0x18: Equal (unordered, signaling) \n
+/// 0x19: Not-greater-than-or-equal (unordered, non-signaling) \n
+/// 0x1A: Not-greater-than (unordered, non-signaling) \n
+/// 0x1B: False (ordered, signaling) \n
+/// 0x1C: Not-equal (ordered, signaling) \n
+/// 0x1D: Greater-than-or-equal (ordered, non-signaling) \n
+/// 0x1E: Greater-than (ordered, non-signaling) \n
+/// 0x1F: True (unordered, signaling)
+/// \returns A 128-bit vector of [4 x float] containing the comparison results.
+#define _mm_cmp_ps(a, b, c) \
+ ((__m128)__builtin_ia32_cmpps((__v4sf)(__m128)(a), \
+ (__v4sf)(__m128)(b), (c)))
+
+/// Compares each of the corresponding scalar values of two 128-bit
+/// vectors of [4 x float], using the operation specified by the immediate
+/// integer operand.
+///
+/// If the result is true, all 32 bits of the destination vector are set;
+/// otherwise they are cleared.
+///
+/// \headerfile <x86intrin.h>
+///
+/// \code
+/// __m128 _mm_cmp_ss(__m128 a, __m128 b, const int c);
+/// \endcode
+///
+/// This intrinsic corresponds to the <c> VCMPSS </c> instruction.
+///
+/// \param a
+/// A 128-bit vector of [4 x float].
+/// \param b
+/// A 128-bit vector of [4 x float].
+/// \param c
+/// An immediate integer operand, with bits [4:0] specifying which comparison
+/// operation to use: \n
+/// 0x00: Equal (ordered, non-signaling) \n
+/// 0x01: Less-than (ordered, signaling) \n
+/// 0x02: Less-than-or-equal (ordered, signaling) \n
+/// 0x03: Unordered (non-signaling) \n
+/// 0x04: Not-equal (unordered, non-signaling) \n
+/// 0x05: Not-less-than (unordered, signaling) \n
+/// 0x06: Not-less-than-or-equal (unordered, signaling) \n
+/// 0x07: Ordered (non-signaling) \n
+/// 0x08: Equal (unordered, non-signaling) \n
+/// 0x09: Not-greater-than-or-equal (unordered, signaling) \n
+/// 0x0A: Not-greater-than (unordered, signaling) \n
+/// 0x0B: False (ordered, non-signaling) \n
+/// 0x0C: Not-equal (ordered, non-signaling) \n
+/// 0x0D: Greater-than-or-equal (ordered, signaling) \n
+/// 0x0E: Greater-than (ordered, signaling) \n
+/// 0x0F: True (unordered, non-signaling) \n
+/// 0x10: Equal (ordered, signaling) \n
+/// 0x11: Less-than (ordered, non-signaling) \n
+/// 0x12: Less-than-or-equal (ordered, non-signaling) \n
+/// 0x13: Unordered (signaling) \n
+/// 0x14: Not-equal (unordered, signaling) \n
+/// 0x15: Not-less-than (unordered, non-signaling) \n
+/// 0x16: Not-less-than-or-equal (unordered, non-signaling) \n
+/// 0x17: Ordered (signaling) \n
+/// 0x18: Equal (unordered, signaling) \n
+/// 0x19: Not-greater-than-or-equal (unordered, non-signaling) \n
+/// 0x1A: Not-greater-than (unordered, non-signaling) \n
+/// 0x1B: False (ordered, signaling) \n
+/// 0x1C: Not-equal (ordered, signaling) \n
+/// 0x1D: Greater-than-or-equal (ordered, non-signaling) \n
+/// 0x1E: Greater-than (ordered, non-signaling) \n
+/// 0x1F: True (unordered, signaling)
+/// \returns A 128-bit vector of [4 x float] containing the comparison results.
+#define _mm_cmp_ss(a, b, c) \
+ ((__m128)__builtin_ia32_cmpss((__v4sf)(__m128)(a), \
+ (__v4sf)(__m128)(b), (c)))
#define _MM_ALIGN16 __attribute__((aligned(16)))
diff --git a/clang/test/CodeGen/X86/avx-builtins.c b/clang/test/CodeGen/X86/avx-builtins.c
index 9178ecaf3f8fe43..18258d84f602ff4 100644
--- a/clang/test/CodeGen/X86/avx-builtins.c
+++ b/clang/test/CodeGen/X86/avx-builtins.c
@@ -596,402 +596,6 @@ __m256 test_mm256_cmp_ps_true_us(__m256 a, __m256 b) {
return _mm256_cmp_ps(a, b, _CMP_TRUE_US);
}
-__m128d test_mm_cmp_pd_eq_oq(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_eq_oq
- // CHECK: fcmp oeq <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_EQ_OQ);
-}
-
-__m128d test_mm_cmp_pd_lt_os(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_lt_os
- // CHECK: fcmp olt <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_LT_OS);
-}
-
-__m128d test_mm_cmp_pd_le_os(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_le_os
- // CHECK: fcmp ole <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_LE_OS);
-}
-
-__m128d test_mm_cmp_pd_unord_q(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_unord_q
- // CHECK: fcmp uno <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_UNORD_Q);
-}
-
-__m128d test_mm_cmp_pd_neq_uq(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_neq_uq
- // CHECK: fcmp une <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_NEQ_UQ);
-}
-
-__m128d test_mm_cmp_pd_nlt_us(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_nlt_us
- // CHECK: fcmp uge <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_NLT_US);
-}
-
-__m128d test_mm_cmp_pd_nle_us(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_nle_us
- // CHECK: fcmp ugt <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_NLE_US);
-}
-
-__m128d test_mm_cmp_pd_ord_q(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_ord_q
- // CHECK: fcmp ord <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_ORD_Q);
-}
-
-__m128d test_mm_cmp_pd_eq_uq(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_eq_uq
- // CHECK: fcmp ueq <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_EQ_UQ);
-}
-
-__m128d test_mm_cmp_pd_nge_us(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_nge_us
- // CHECK: fcmp ult <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_NGE_US);
-}
-
-__m128d test_mm_cmp_pd_ngt_us(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_ngt_us
- // CHECK: fcmp ule <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_NGT_US);
-}
-
-__m128d test_mm_cmp_pd_false_oq(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_false_oq
- // CHECK: fcmp false <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_FALSE_OQ);
-}
-
-__m128d test_mm_cmp_pd_neq_oq(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_neq_oq
- // CHECK: fcmp one <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_NEQ_OQ);
-}
-
-__m128d test_mm_cmp_pd_ge_os(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_ge_os
- // CHECK: fcmp oge <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_GE_OS);
-}
-
-__m128d test_mm_cmp_pd_gt_os(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_gt_os
- // CHECK: fcmp ogt <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_GT_OS);
-}
-
-__m128d test_mm_cmp_pd_true_uq(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_true_uq
- // CHECK: fcmp true <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_TRUE_UQ);
-}
-
-__m128d test_mm_cmp_pd_eq_os(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_eq_os
- // CHECK: fcmp oeq <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_EQ_OS);
-}
-
-__m128d test_mm_cmp_pd_lt_oq(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_lt_oq
- // CHECK: fcmp olt <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_LT_OQ);
-}
-
-__m128d test_mm_cmp_pd_le_oq(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_le_oq
- // CHECK: fcmp ole <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_LE_OQ);
-}
-
-__m128d test_mm_cmp_pd_unord_s(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_unord_s
- // CHECK: fcmp uno <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_UNORD_S);
-}
-
-__m128d test_mm_cmp_pd_neq_us(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_neq_us
- // CHECK: fcmp une <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_NEQ_US);
-}
-
-__m128d test_mm_cmp_pd_nlt_uq(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_nlt_uq
- // CHECK: fcmp uge <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_NLT_UQ);
-}
-
-__m128d test_mm_cmp_pd_nle_uq(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_nle_uq
- // CHECK: fcmp ugt <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_NLE_UQ);
-}
-
-__m128d test_mm_cmp_pd_ord_s(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_ord_s
- // CHECK: fcmp ord <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_ORD_S);
-}
-
-__m128d test_mm_cmp_pd_eq_us(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_eq_us
- // CHECK: fcmp ueq <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_EQ_US);
-}
-
-__m128d test_mm_cmp_pd_nge_uq(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_nge_uq
- // CHECK: fcmp ult <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_NGE_UQ);
-}
-
-__m128d test_mm_cmp_pd_ngt_uq(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_ngt_uq
- // CHECK: fcmp ule <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_NGT_UQ);
-}
-
-__m128d test_mm_cmp_pd_false_os(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_false_os
- // CHECK: fcmp false <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_FALSE_OS);
-}
-
-__m128d test_mm_cmp_pd_neq_os(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_neq_os
- // CHECK: fcmp one <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_NEQ_OS);
-}
-
-__m128d test_mm_cmp_pd_ge_oq(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_ge_oq
- // CHECK: fcmp oge <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_GE_OQ);
-}
-
-__m128d test_mm_cmp_pd_gt_oq(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_gt_oq
- // CHECK: fcmp ogt <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_GT_OQ);
-}
-
-__m128d test_mm_cmp_pd_true_us(__m128d a, __m128d b) {
- // CHECK-LABEL: test_mm_cmp_pd_true_us
- // CHECK: fcmp true <2 x double> %{{.*}}, %{{.*}}
- return _mm_cmp_pd(a, b, _CMP_TRUE_US);
-}
-
-__m128 test_mm_cmp_ps_eq_oq(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_eq_oq
- // CHECK: fcmp oeq <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_EQ_OQ);
-}
-
-__m128 test_mm_cmp_ps_lt_os(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_lt_os
- // CHECK: fcmp olt <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_LT_OS);
-}
-
-__m128 test_mm_cmp_ps_le_os(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_le_os
- // CHECK: fcmp ole <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_LE_OS);
-}
-
-__m128 test_mm_cmp_ps_unord_q(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_unord_q
- // CHECK: fcmp uno <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_UNORD_Q);
-}
-
-__m128 test_mm_cmp_ps_neq_uq(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_neq_uq
- // CHECK: fcmp une <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_NEQ_UQ);
-}
-
-__m128 test_mm_cmp_ps_nlt_us(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_nlt_us
- // CHECK: fcmp uge <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_NLT_US);
-}
-
-__m128 test_mm_cmp_ps_nle_us(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_nle_us
- // CHECK: fcmp ugt <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_NLE_US);
-}
-
-__m128 test_mm_cmp_ps_ord_q(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_ord_q
- // CHECK: fcmp ord <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_ORD_Q);
-}
-
-__m128 test_mm_cmp_ps_eq_uq(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_eq_uq
- // CHECK: fcmp ueq <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_EQ_UQ);
-}
-
-__m128 test_mm_cmp_ps_nge_us(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_nge_us
- // CHECK: fcmp ult <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_NGE_US);
-}
-
-__m128 test_mm_cmp_ps_ngt_us(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_ngt_us
- // CHECK: fcmp ule <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_NGT_US);
-}
-
-__m128 test_mm_cmp_ps_false_oq(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_false_oq
- // CHECK: fcmp false <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_FALSE_OQ);
-}
-
-__m128 test_mm_cmp_ps_neq_oq(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_neq_oq
- // CHECK: fcmp one <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_NEQ_OQ);
-}
-
-__m128 test_mm_cmp_ps_ge_os(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_ge_os
- // CHECK: fcmp oge <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_GE_OS);
-}
-
-__m128 test_mm_cmp_ps_gt_os(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_gt_os
- // CHECK: fcmp ogt <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_GT_OS);
-}
-
-__m128 test_mm_cmp_ps_true_uq(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_true_uq
- // CHECK: fcmp true <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_TRUE_UQ);
-}
-
-__m128 test_mm_cmp_ps_eq_os(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_eq_os
- // CHECK: fcmp oeq <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_EQ_OS);
-}
-
-__m128 test_mm_cmp_ps_lt_oq(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_lt_oq
- // CHECK: fcmp olt <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_LT_OQ);
-}
-
-__m128 test_mm_cmp_ps_le_oq(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_le_oq
- // CHECK: fcmp ole <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_LE_OQ);
-}
-
-__m128 test_mm_cmp_ps_unord_s(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_unord_s
- // CHECK: fcmp uno <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_UNORD_S);
-}
-
-__m128 test_mm_cmp_ps_neq_us(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_neq_us
- // CHECK: fcmp une <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_NEQ_US);
-}
-
-__m128 test_mm_cmp_ps_nlt_uq(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_nlt_uq
- // CHECK: fcmp uge <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_NLT_UQ);
-}
-
-__m128 test_mm_cmp_ps_nle_uq(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_nle_uq
- // CHECK: fcmp ugt <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_NLE_UQ);
-}
-
-__m128 test_mm_cmp_ps_ord_s(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_ord_s
- // CHECK: fcmp ord <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_ORD_S);
-}
-
-__m128 test_mm_cmp_ps_eq_us(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_eq_us
- // CHECK: fcmp ueq <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_EQ_US);
-}
-
-__m128 test_mm_cmp_ps_nge_uq(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_nge_uq
- // CHECK: fcmp ult <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_NGE_UQ);
-}
-
-__m128 test_mm_cmp_ps_ngt_uq(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_ngt_uq
- // CHECK: fcmp ule <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_NGT_UQ);
-}
-
-__m128 test_mm_cmp_ps_false_os(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_false_os
- // CHECK: fcmp false <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_FALSE_OS);
-}
-
-__m128 test_mm_cmp_ps_neq_os(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_neq_os
- // CHECK: fcmp one <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_NEQ_OS);
-}
-
-__m128 test_mm_cmp_ps_ge_oq(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_ge_oq
- // CHECK: fcmp oge <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_GE_OQ);
-}
-
-__m128 test_mm_cmp_ps_gt_oq(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_gt_oq
- // CHECK: fcmp ogt <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_GT_OQ);
-}
-
-__m128 test_mm_cmp_ps_true_us(__m128 a, __m128 b) {
- // CHECK-LABEL: test_mm_cmp_ps_true_us
- // CHECK: fcmp true <4 x float> %{{.*}}, %{{.*}}
- return _mm_cmp_ps(a, b, _CMP_TRUE_US);
-}
-
-__m128d test_mm_cmp_sd(__m128d A, __m128d B) {
- // CHECK-LABEL: test_mm_cmp_sd
- // CHECK: call <2 x double> @llvm.x86.sse2.cmp.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 13)
- return _mm_cmp_sd(A, B, _CMP_GE_OS);
-}
-
-__m128 test_mm_cmp_ss(__m128 A, __m128 B) {
- // CHECK-LABEL: test_mm_cmp_ss
- // CHECK: call <4 x float> @llvm.x86.sse.cmp.ss(<4 x float> %{{.*}}, <4 x float> %{{.*}}, i8 13)
- return _mm_cmp_ss(A, B, _CMP_GE_OS);
-}
-
__m256d test_mm256_cvtepi32_pd(__m128i A) {
// CHECK-LABEL: test_mm256_cvtepi32_pd
// CHECK: sitofp <4 x i32> %{{.*}} to <4 x double>
diff --git a/clang/test/CodeGen/X86/sse-builtins.c b/clang/test/CodeGen/X86/sse-builtins.c
index 885c82856522d2a..5c7fcdfe5170c2d 100644
--- a/clang/test/CodeGen/X86/sse-builtins.c
+++ b/clang/test/CodeGen/X86/sse-builtins.c
@@ -813,3 +813,201 @@ __m128 test_mm_xor_ps(__m128 A, __m128 B) {
// CHECK: xor <4 x i32>
return _mm_xor_ps(A, B);
}
+
+__m128 test_mm_cmp_ps_eq_oq(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_eq_oq
+ // CHECK: fcmp oeq <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_EQ_OQ);
+}
+
+__m128 test_mm_cmp_ps_lt_os(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_lt_os
+ // CHECK: fcmp olt <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_LT_OS);
+}
+
+__m128 test_mm_cmp_ps_le_os(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_le_os
+ // CHECK: fcmp ole <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_LE_OS);
+}
+
+__m128 test_mm_cmp_ps_unord_q(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_unord_q
+ // CHECK: fcmp uno <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_UNORD_Q);
+}
+
+__m128 test_mm_cmp_ps_neq_uq(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_neq_uq
+ // CHECK: fcmp une <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_NEQ_UQ);
+}
+
+__m128 test_mm_cmp_ps_nlt_us(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_nlt_us
+ // CHECK: fcmp uge <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_NLT_US);
+}
+
+__m128 test_mm_cmp_ps_nle_us(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_nle_us
+ // CHECK: fcmp ugt <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_NLE_US);
+}
+
+__m128 test_mm_cmp_ps_ord_q(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_ord_q
+ // CHECK: fcmp ord <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_ORD_Q);
+}
+
+__m128 test_mm_cmp_ps_eq_uq(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_eq_uq
+ // CHECK: fcmp ueq <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_EQ_UQ);
+}
+
+__m128 test_mm_cmp_ps_nge_us(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_nge_us
+ // CHECK: fcmp ult <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_NGE_US);
+}
+
+__m128 test_mm_cmp_ps_ngt_us(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_ngt_us
+ // CHECK: fcmp ule <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_NGT_US);
+}
+
+__m128 test_mm_cmp_ps_false_oq(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_false_oq
+ // CHECK: fcmp false <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_FALSE_OQ);
+}
+
+__m128 test_mm_cmp_ps_neq_oq(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_neq_oq
+ // CHECK: fcmp one <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_NEQ_OQ);
+}
+
+__m128 test_mm_cmp_ps_ge_os(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_ge_os
+ // CHECK: fcmp oge <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_GE_OS);
+}
+
+__m128 test_mm_cmp_ps_gt_os(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_gt_os
+ // CHECK: fcmp ogt <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_GT_OS);
+}
+
+__m128 test_mm_cmp_ps_true_uq(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_true_uq
+ // CHECK: fcmp true <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_TRUE_UQ);
+}
+
+__m128 test_mm_cmp_ps_eq_os(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_eq_os
+ // CHECK: fcmp oeq <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_EQ_OS);
+}
+
+__m128 test_mm_cmp_ps_lt_oq(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_lt_oq
+ // CHECK: fcmp olt <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_LT_OQ);
+}
+
+__m128 test_mm_cmp_ps_le_oq(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_le_oq
+ // CHECK: fcmp ole <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_LE_OQ);
+}
+
+__m128 test_mm_cmp_ps_unord_s(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_unord_s
+ // CHECK: fcmp uno <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_UNORD_S);
+}
+
+__m128 test_mm_cmp_ps_neq_us(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_neq_us
+ // CHECK: fcmp une <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_NEQ_US);
+}
+
+__m128 test_mm_cmp_ps_nlt_uq(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_nlt_uq
+ // CHECK: fcmp uge <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_NLT_UQ);
+}
+
+__m128 test_mm_cmp_ps_nle_uq(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_nle_uq
+ // CHECK: fcmp ugt <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_NLE_UQ);
+}
+
+__m128 test_mm_cmp_ps_ord_s(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_ord_s
+ // CHECK: fcmp ord <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_ORD_S);
+}
+
+__m128 test_mm_cmp_ps_eq_us(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_eq_us
+ // CHECK: fcmp ueq <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_EQ_US);
+}
+
+__m128 test_mm_cmp_ps_nge_uq(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_nge_uq
+ // CHECK: fcmp ult <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_NGE_UQ);
+}
+
+__m128 test_mm_cmp_ps_ngt_uq(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_ngt_uq
+ // CHECK: fcmp ule <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_NGT_UQ);
+}
+
+__m128 test_mm_cmp_ps_false_os(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_false_os
+ // CHECK: fcmp false <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_FALSE_OS);
+}
+
+__m128 test_mm_cmp_ps_neq_os(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_neq_os
+ // CHECK: fcmp one <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_NEQ_OS);
+}
+
+__m128 test_mm_cmp_ps_ge_oq(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_ge_oq
+ // CHECK: fcmp oge <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_GE_OQ);
+}
+
+__m128 test_mm_cmp_ps_gt_oq(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_gt_oq
+ // CHECK: fcmp ogt <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_GT_OQ);
+}
+
+__m128 test_mm_cmp_ps_true_us(__m128 a, __m128 b) {
+ // CHECK-LABEL: test_mm_cmp_ps_true_us
+ // CHECK: fcmp true <4 x float> %{{.*}}, %{{.*}}
+ return _mm_cmp_ps(a, b, _CMP_TRUE_US);
+}
+
+__m128 test_mm_cmp_ss(__m128 A, __m128 B) {
+ // CHECK-LABEL: test_mm_cmp_ss
+ // CHECK: call <4 x float> @llvm.x86.sse.cmp.ss(<4 x float> %{{.*}}, <4 x float> %{{.*}}, i8 13)
+ return _mm_cmp_ss(A, B, _CMP_GE_OS);
+}
\ No newline at end of file
diff --git a/clang/test/CodeGen/X86/sse2-builtins.c b/clang/test/CodeGen/X86/sse2-builtins.c
index 7165d2791827cfc..2d8359189f4a00a 100644
--- a/clang/test/CodeGen/X86/sse2-builtins.c
+++ b/clang/test/CodeGen/X86/sse2-builtins.c
@@ -1719,3 +1719,201 @@ __m128i test_mm_xor_si128(__m128i A, __m128i B) {
// CHECK: xor <2 x i64> %{{.*}}, %{{.*}}
return _mm_xor_si128(A, B);
}
+
+__m128d test_mm_cmp_pd_eq_oq(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_eq_oq
+ // CHECK: fcmp oeq <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_EQ_OQ);
+}
+
+__m128d test_mm_cmp_pd_lt_os(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_lt_os
+ // CHECK: fcmp olt <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_LT_OS);
+}
+
+__m128d test_mm_cmp_pd_le_os(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_le_os
+ // CHECK: fcmp ole <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_LE_OS);
+}
+
+__m128d test_mm_cmp_pd_unord_q(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_unord_q
+ // CHECK: fcmp uno <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_UNORD_Q);
+}
+
+__m128d test_mm_cmp_pd_neq_uq(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_neq_uq
+ // CHECK: fcmp une <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_NEQ_UQ);
+}
+
+__m128d test_mm_cmp_pd_nlt_us(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_nlt_us
+ // CHECK: fcmp uge <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_NLT_US);
+}
+
+__m128d test_mm_cmp_pd_nle_us(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_nle_us
+ // CHECK: fcmp ugt <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_NLE_US);
+}
+
+__m128d test_mm_cmp_pd_ord_q(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_ord_q
+ // CHECK: fcmp ord <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_ORD_Q);
+}
+
+__m128d test_mm_cmp_pd_eq_uq(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_eq_uq
+ // CHECK: fcmp ueq <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_EQ_UQ);
+}
+
+__m128d test_mm_cmp_pd_nge_us(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_nge_us
+ // CHECK: fcmp ult <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_NGE_US);
+}
+
+__m128d test_mm_cmp_pd_ngt_us(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_ngt_us
+ // CHECK: fcmp ule <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_NGT_US);
+}
+
+__m128d test_mm_cmp_pd_false_oq(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_false_oq
+ // CHECK: fcmp false <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_FALSE_OQ);
+}
+
+__m128d test_mm_cmp_pd_neq_oq(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_neq_oq
+ // CHECK: fcmp one <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_NEQ_OQ);
+}
+
+__m128d test_mm_cmp_pd_ge_os(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_ge_os
+ // CHECK: fcmp oge <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_GE_OS);
+}
+
+__m128d test_mm_cmp_pd_gt_os(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_gt_os
+ // CHECK: fcmp ogt <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_GT_OS);
+}
+
+__m128d test_mm_cmp_pd_true_uq(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_true_uq
+ // CHECK: fcmp true <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_TRUE_UQ);
+}
+
+__m128d test_mm_cmp_pd_eq_os(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_eq_os
+ // CHECK: fcmp oeq <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_EQ_OS);
+}
+
+__m128d test_mm_cmp_pd_lt_oq(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_lt_oq
+ // CHECK: fcmp olt <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_LT_OQ);
+}
+
+__m128d test_mm_cmp_pd_le_oq(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_le_oq
+ // CHECK: fcmp ole <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_LE_OQ);
+}
+
+__m128d test_mm_cmp_pd_unord_s(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_unord_s
+ // CHECK: fcmp uno <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_UNORD_S);
+}
+
+__m128d test_mm_cmp_pd_neq_us(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_neq_us
+ // CHECK: fcmp une <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_NEQ_US);
+}
+
+__m128d test_mm_cmp_pd_nlt_uq(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_nlt_uq
+ // CHECK: fcmp uge <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_NLT_UQ);
+}
+
+__m128d test_mm_cmp_pd_nle_uq(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_nle_uq
+ // CHECK: fcmp ugt <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_NLE_UQ);
+}
+
+__m128d test_mm_cmp_pd_ord_s(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_ord_s
+ // CHECK: fcmp ord <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_ORD_S);
+}
+
+__m128d test_mm_cmp_pd_eq_us(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_eq_us
+ // CHECK: fcmp ueq <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_EQ_US);
+}
+
+__m128d test_mm_cmp_pd_nge_uq(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_nge_uq
+ // CHECK: fcmp ult <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_NGE_UQ);
+}
+
+__m128d test_mm_cmp_pd_ngt_uq(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_ngt_uq
+ // CHECK: fcmp ule <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_NGT_UQ);
+}
+
+__m128d test_mm_cmp_pd_false_os(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_false_os
+ // CHECK: fcmp false <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_FALSE_OS);
+}
+
+__m128d test_mm_cmp_pd_neq_os(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_neq_os
+ // CHECK: fcmp one <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_NEQ_OS);
+}
+
+__m128d test_mm_cmp_pd_ge_oq(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_ge_oq
+ // CHECK: fcmp oge <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_GE_OQ);
+}
+
+__m128d test_mm_cmp_pd_gt_oq(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_gt_oq
+ // CHECK: fcmp ogt <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_GT_OQ);
+}
+
+__m128d test_mm_cmp_pd_true_us(__m128d a, __m128d b) {
+ // CHECK-LABEL: test_mm_cmp_pd_true_us
+ // CHECK: fcmp true <2 x double> %{{.*}}, %{{.*}}
+ return _mm_cmp_pd(a, b, _CMP_TRUE_US);
+}
+
+__m128d test_mm_cmp_sd(__m128d A, __m128d B) {
+ // CHECK-LABEL: test_mm_cmp_sd
+ // CHECK: call <2 x double> @llvm.x86.sse2.cmp.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i8 13)
+ return _mm_cmp_sd(A, B, _CMP_GE_OS);
+}
diff --git a/clang/test/CodeGen/target-features-error-2.c b/clang/test/CodeGen/target-features-error-2.c
index 60586fb57f1c044..4f8bc8712aa51db 100644
--- a/clang/test/CodeGen/target-features-error-2.c
+++ b/clang/test/CodeGen/target-features-error-2.c
@@ -14,8 +14,8 @@ int baz(__m256i a) {
#endif
#if NEED_AVX_2
-__m128 need_avx(__m128 a, __m128 b) {
- return _mm_cmp_ps(a, b, 0); // expected-error {{'__builtin_ia32_cmpps' needs target feature avx}}
+__m256 need_avx(__m256 a, __m256 b) {
+ return _mm256_cmp_ps(a, b, 0); // expected-error {{'__builtin_ia32_cmpps256' needs target feature avx}}
}
#endif
>From 8341496f864caab44f15094b057c4cfc3a1ce094 Mon Sep 17 00:00:00 2001
From: Freddy Ye <freddy.ye at intel.com>
Date: Tue, 26 Sep 2023 17:43:09 +0800
Subject: [PATCH 2/5] clang-format
---
clang/lib/Headers/emmintrin.h | 12 +++---
clang/lib/Headers/xmmintrin.h | 73 ++++++++++++++++++-----------------
2 files changed, 43 insertions(+), 42 deletions(-)
diff --git a/clang/lib/Headers/emmintrin.h b/clang/lib/Headers/emmintrin.h
index 3e103ee7a24b69c..f857b9864d084e1 100644
--- a/clang/lib/Headers/emmintrin.h
+++ b/clang/lib/Headers/emmintrin.h
@@ -4798,9 +4798,9 @@ static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_castsi128_pd(__m128i __a) {
/// 0x1E: Greater-than (ordered, non-signaling) \n
/// 0x1F: True (unordered, signaling)
/// \returns A 128-bit vector of [2 x double] containing the comparison results.
-#define _mm_cmp_pd(a, b, c) \
- ((__m128d)__builtin_ia32_cmppd((__v2df)(__m128d)(a), \
- (__v2df)(__m128d)(b), (c)))
+#define _mm_cmp_pd(a, b, c) \
+ ((__m128d)__builtin_ia32_cmppd((__v2df)(__m128d)(a), (__v2df)(__m128d)(b), \
+ (c)))
/// Compares each of the corresponding scalar double-precision values of
/// two 128-bit vectors of [2 x double], using the operation specified by the
@@ -4857,9 +4857,9 @@ static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_castsi128_pd(__m128i __a) {
/// 0x1E: Greater-than (ordered, non-signaling) \n
/// 0x1F: True (unordered, signaling)
/// \returns A 128-bit vector of [2 x double] containing the comparison results.
-#define _mm_cmp_sd(a, b, c) \
- ((__m128d)__builtin_ia32_cmpsd((__v2df)(__m128d)(a), \
- (__v2df)(__m128d)(b), (c)))
+#define _mm_cmp_sd(a, b, c) \
+ ((__m128d)__builtin_ia32_cmpsd((__v2df)(__m128d)(a), (__v2df)(__m128d)(b), \
+ (c)))
#if defined(__cplusplus)
extern "C" {
diff --git a/clang/lib/Headers/xmmintrin.h b/clang/lib/Headers/xmmintrin.h
index 7b238d8ba000641..fbca88a2823f2d8 100644
--- a/clang/lib/Headers/xmmintrin.h
+++ b/clang/lib/Headers/xmmintrin.h
@@ -2937,38 +2937,41 @@ _mm_movemask_ps(__m128 __a)
}
/* Compare */
-#define _CMP_EQ_OQ 0x00 /* Equal (ordered, non-signaling) */
-#define _CMP_LT_OS 0x01 /* Less-than (ordered, signaling) */
-#define _CMP_LE_OS 0x02 /* Less-than-or-equal (ordered, signaling) */
-#define _CMP_UNORD_Q 0x03 /* Unordered (non-signaling) */
-#define _CMP_NEQ_UQ 0x04 /* Not-equal (unordered, non-signaling) */
-#define _CMP_NLT_US 0x05 /* Not-less-than (unordered, signaling) */
-#define _CMP_NLE_US 0x06 /* Not-less-than-or-equal (unordered, signaling) */
-#define _CMP_ORD_Q 0x07 /* Ordered (non-signaling) */
-#define _CMP_EQ_UQ 0x08 /* Equal (unordered, non-signaling) */
-#define _CMP_NGE_US 0x09 /* Not-greater-than-or-equal (unordered, signaling) */
-#define _CMP_NGT_US 0x0a /* Not-greater-than (unordered, signaling) */
+#define _CMP_EQ_OQ 0x00 /* Equal (ordered, non-signaling) */
+#define _CMP_LT_OS 0x01 /* Less-than (ordered, signaling) */
+#define _CMP_LE_OS 0x02 /* Less-than-or-equal (ordered, signaling) */
+#define _CMP_UNORD_Q 0x03 /* Unordered (non-signaling) */
+#define _CMP_NEQ_UQ 0x04 /* Not-equal (unordered, non-signaling) */
+#define _CMP_NLT_US 0x05 /* Not-less-than (unordered, signaling) */
+#define _CMP_NLE_US 0x06 /* Not-less-than-or-equal (unordered, signaling) */
+#define _CMP_ORD_Q 0x07 /* Ordered (non-signaling) */
+#define _CMP_EQ_UQ 0x08 /* Equal (unordered, non-signaling) */
+#define _CMP_NGE_US 0x09 /* Not-greater-than-or-equal (unordered, signaling) \
+ */
+#define _CMP_NGT_US 0x0a /* Not-greater-than (unordered, signaling) */
#define _CMP_FALSE_OQ 0x0b /* False (ordered, non-signaling) */
-#define _CMP_NEQ_OQ 0x0c /* Not-equal (ordered, non-signaling) */
-#define _CMP_GE_OS 0x0d /* Greater-than-or-equal (ordered, signaling) */
-#define _CMP_GT_OS 0x0e /* Greater-than (ordered, signaling) */
-#define _CMP_TRUE_UQ 0x0f /* True (unordered, non-signaling) */
-#define _CMP_EQ_OS 0x10 /* Equal (ordered, signaling) */
-#define _CMP_LT_OQ 0x11 /* Less-than (ordered, non-signaling) */
-#define _CMP_LE_OQ 0x12 /* Less-than-or-equal (ordered, non-signaling) */
-#define _CMP_UNORD_S 0x13 /* Unordered (signaling) */
-#define _CMP_NEQ_US 0x14 /* Not-equal (unordered, signaling) */
-#define _CMP_NLT_UQ 0x15 /* Not-less-than (unordered, non-signaling) */
-#define _CMP_NLE_UQ 0x16 /* Not-less-than-or-equal (unordered, non-signaling) */
-#define _CMP_ORD_S 0x17 /* Ordered (signaling) */
-#define _CMP_EQ_US 0x18 /* Equal (unordered, signaling) */
-#define _CMP_NGE_UQ 0x19 /* Not-greater-than-or-equal (unordered, non-signaling) */
-#define _CMP_NGT_UQ 0x1a /* Not-greater-than (unordered, non-signaling) */
+#define _CMP_NEQ_OQ 0x0c /* Not-equal (ordered, non-signaling) */
+#define _CMP_GE_OS 0x0d /* Greater-than-or-equal (ordered, signaling) */
+#define _CMP_GT_OS 0x0e /* Greater-than (ordered, signaling) */
+#define _CMP_TRUE_UQ 0x0f /* True (unordered, non-signaling) */
+#define _CMP_EQ_OS 0x10 /* Equal (ordered, signaling) */
+#define _CMP_LT_OQ 0x11 /* Less-than (ordered, non-signaling) */
+#define _CMP_LE_OQ 0x12 /* Less-than-or-equal (ordered, non-signaling) */
+#define _CMP_UNORD_S 0x13 /* Unordered (signaling) */
+#define _CMP_NEQ_US 0x14 /* Not-equal (unordered, signaling) */
+#define _CMP_NLT_UQ 0x15 /* Not-less-than (unordered, non-signaling) */
+#define _CMP_NLE_UQ \
+ 0x16 /* Not-less-than-or-equal (unordered, non-signaling) */
+#define _CMP_ORD_S 0x17 /* Ordered (signaling) */
+#define _CMP_EQ_US 0x18 /* Equal (unordered, signaling) */
+#define _CMP_NGE_UQ \
+ 0x19 /* Not-greater-than-or-equal (unordered, non-signaling) */
+#define _CMP_NGT_UQ 0x1a /* Not-greater-than (unordered, non-signaling) */
#define _CMP_FALSE_OS 0x1b /* False (ordered, signaling) */
-#define _CMP_NEQ_OS 0x1c /* Not-equal (ordered, signaling) */
-#define _CMP_GE_OQ 0x1d /* Greater-than-or-equal (ordered, non-signaling) */
-#define _CMP_GT_OQ 0x1e /* Greater-than (ordered, non-signaling) */
-#define _CMP_TRUE_US 0x1f /* True (unordered, signaling) */
+#define _CMP_NEQ_OS 0x1c /* Not-equal (ordered, signaling) */
+#define _CMP_GE_OQ 0x1d /* Greater-than-or-equal (ordered, non-signaling) */
+#define _CMP_GT_OQ 0x1e /* Greater-than (ordered, non-signaling) */
+#define _CMP_TRUE_US 0x1f /* True (unordered, signaling) */
/// Compares each of the corresponding values of two 128-bit vectors of
/// [4 x float], using the operation specified by the immediate integer
@@ -3026,9 +3029,8 @@ _mm_movemask_ps(__m128 __a)
/// 0x1E: Greater-than (ordered, non-signaling) \n
/// 0x1F: True (unordered, signaling)
/// \returns A 128-bit vector of [4 x float] containing the comparison results.
-#define _mm_cmp_ps(a, b, c) \
- ((__m128)__builtin_ia32_cmpps((__v4sf)(__m128)(a), \
- (__v4sf)(__m128)(b), (c)))
+#define _mm_cmp_ps(a, b, c) \
+ ((__m128)__builtin_ia32_cmpps((__v4sf)(__m128)(a), (__v4sf)(__m128)(b), (c)))
/// Compares each of the corresponding scalar values of two 128-bit
/// vectors of [4 x float], using the operation specified by the immediate
@@ -3085,9 +3087,8 @@ _mm_movemask_ps(__m128 __a)
/// 0x1E: Greater-than (ordered, non-signaling) \n
/// 0x1F: True (unordered, signaling)
/// \returns A 128-bit vector of [4 x float] containing the comparison results.
-#define _mm_cmp_ss(a, b, c) \
- ((__m128)__builtin_ia32_cmpss((__v4sf)(__m128)(a), \
- (__v4sf)(__m128)(b), (c)))
+#define _mm_cmp_ss(a, b, c) \
+ ((__m128)__builtin_ia32_cmpss((__v4sf)(__m128)(a), (__v4sf)(__m128)(b), (c)))
#define _MM_ALIGN16 __attribute__((aligned(16)))
>From 08a46a8e10fd6da351161a5a4e68879c64dba22d Mon Sep 17 00:00:00 2001
From: Freddy Ye <freddy.ye at intel.com>
Date: Tue, 26 Sep 2023 18:32:00 +0800
Subject: [PATCH 3/5] clang-format
---
clang/lib/Headers/xmmintrin.h | 21 +++++++++++----------
1 file changed, 11 insertions(+), 10 deletions(-)
diff --git a/clang/lib/Headers/xmmintrin.h b/clang/lib/Headers/xmmintrin.h
index fbca88a2823f2d8..2be56f76c6c1976 100644
--- a/clang/lib/Headers/xmmintrin.h
+++ b/clang/lib/Headers/xmmintrin.h
@@ -2937,16 +2937,17 @@ _mm_movemask_ps(__m128 __a)
}
/* Compare */
-#define _CMP_EQ_OQ 0x00 /* Equal (ordered, non-signaling) */
-#define _CMP_LT_OS 0x01 /* Less-than (ordered, signaling) */
-#define _CMP_LE_OS 0x02 /* Less-than-or-equal (ordered, signaling) */
-#define _CMP_UNORD_Q 0x03 /* Unordered (non-signaling) */
-#define _CMP_NEQ_UQ 0x04 /* Not-equal (unordered, non-signaling) */
-#define _CMP_NLT_US 0x05 /* Not-less-than (unordered, signaling) */
-#define _CMP_NLE_US 0x06 /* Not-less-than-or-equal (unordered, signaling) */
-#define _CMP_ORD_Q 0x07 /* Ordered (non-signaling) */
-#define _CMP_EQ_UQ 0x08 /* Equal (unordered, non-signaling) */
-#define _CMP_NGE_US 0x09 /* Not-greater-than-or-equal (unordered, signaling) \
+#define _CMP_EQ_OQ 0x00 /* Equal (ordered, non-signaling) */
+#define _CMP_LT_OS 0x01 /* Less-than (ordered, signaling) */
+#define _CMP_LE_OS 0x02 /* Less-than-or-equal (ordered, signaling) */
+#define _CMP_UNORD_Q 0x03 /* Unordered (non-signaling) */
+#define _CMP_NEQ_UQ 0x04 /* Not-equal (unordered, non-signaling) */
+#define _CMP_NLT_US 0x05 /* Not-less-than (unordered, signaling) */
+#define _CMP_NLE_US 0x06 /* Not-less-than-or-equal (unordered, signaling) */
+#define _CMP_ORD_Q 0x07 /* Ordered (non-signaling) */
+#define _CMP_EQ_UQ 0x08 /* Equal (unordered, non-signaling) */
+#define _CMP_NGE_US \
+ 0x09 /* Not-greater-than-or-equal (unordered, signaling) \
*/
#define _CMP_NGT_US 0x0a /* Not-greater-than (unordered, signaling) */
#define _CMP_FALSE_OQ 0x0b /* False (ordered, non-signaling) */
>From 2531cd9430aca27ad92bd2366520b014cbdc96a6 Mon Sep 17 00:00:00 2001
From: Freddy Ye <freddy.ye at intel.com>
Date: Tue, 26 Sep 2023 20:13:14 +0800
Subject: [PATCH 4/5] Address comments.
---
clang/lib/Headers/emmintrin.h | 4 ++--
clang/lib/Headers/xmmintrin.h | 4 ++--
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/clang/lib/Headers/emmintrin.h b/clang/lib/Headers/emmintrin.h
index f857b9864d084e1..536f5eaf45cd859 100644
--- a/clang/lib/Headers/emmintrin.h
+++ b/clang/lib/Headers/emmintrin.h
@@ -4756,7 +4756,7 @@ static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_castsi128_pd(__m128i __a) {
/// __m128d _mm_cmp_pd(__m128d a, __m128d b, const int c);
/// \endcode
///
-/// This intrinsic corresponds to the <c> VCMPPD </c> instruction.
+/// This intrinsic corresponds to the <c> (V)CMPPD </c> instruction.
///
/// \param a
/// A 128-bit vector of [2 x double].
@@ -4815,7 +4815,7 @@ static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_castsi128_pd(__m128i __a) {
/// __m128d _mm_cmp_sd(__m128d a, __m128d b, const int c);
/// \endcode
///
-/// This intrinsic corresponds to the <c> VCMPSD </c> instruction.
+/// This intrinsic corresponds to the <c> (V)CMPSD </c> instruction.
///
/// \param a
/// A 128-bit vector of [2 x double].
diff --git a/clang/lib/Headers/xmmintrin.h b/clang/lib/Headers/xmmintrin.h
index 2be56f76c6c1976..5890f0706ad5271 100644
--- a/clang/lib/Headers/xmmintrin.h
+++ b/clang/lib/Headers/xmmintrin.h
@@ -2988,7 +2988,7 @@ _mm_movemask_ps(__m128 __a)
/// __m128 _mm_cmp_ps(__m128 a, __m128 b, const int c);
/// \endcode
///
-/// This intrinsic corresponds to the <c> VCMPPS </c> instruction.
+/// This intrinsic corresponds to the <c> (V)CMPPS </c> instruction.
///
/// \param a
/// A 128-bit vector of [4 x float].
@@ -3046,7 +3046,7 @@ _mm_movemask_ps(__m128 __a)
/// __m128 _mm_cmp_ss(__m128 a, __m128 b, const int c);
/// \endcode
///
-/// This intrinsic corresponds to the <c> VCMPSS </c> instruction.
+/// This intrinsic corresponds to the <c> (V)CMPSS </c> instruction.
///
/// \param a
/// A 128-bit vector of [4 x float].
>From 85d84aa16d142f3541390307184cd95cdf548813 Mon Sep 17 00:00:00 2001
From: Freddy Ye <freddy.ye at intel.com>
Date: Wed, 27 Sep 2023 15:29:36 +0800
Subject: [PATCH 5/5] Add sema checking depending on has avx or not.
---
clang/lib/Headers/emmintrin.h | 2 ++
clang/lib/Headers/xmmintrin.h | 2 ++
clang/lib/Sema/SemaChecking.cpp | 2 ++
3 files changed, 6 insertions(+)
diff --git a/clang/lib/Headers/emmintrin.h b/clang/lib/Headers/emmintrin.h
index 536f5eaf45cd859..20cd1d4d732fcac 100644
--- a/clang/lib/Headers/emmintrin.h
+++ b/clang/lib/Headers/emmintrin.h
@@ -4765,6 +4765,7 @@ static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_castsi128_pd(__m128i __a) {
/// \param c
/// An immediate integer operand, with bits [4:0] specifying which comparison
/// operation to use: \n
+/// (Note that without avx enabled, only bits [2:0] are supported) \n
/// 0x00: Equal (ordered, non-signaling) \n
/// 0x01: Less-than (ordered, signaling) \n
/// 0x02: Less-than-or-equal (ordered, signaling) \n
@@ -4824,6 +4825,7 @@ static __inline__ __m128d __DEFAULT_FN_ATTRS _mm_castsi128_pd(__m128i __a) {
/// \param c
/// An immediate integer operand, with bits [4:0] specifying which comparison
/// operation to use: \n
+/// (Note that without avx enabled, only bits [2:0] are supported) \n
/// 0x00: Equal (ordered, non-signaling) \n
/// 0x01: Less-than (ordered, signaling) \n
/// 0x02: Less-than-or-equal (ordered, signaling) \n
diff --git a/clang/lib/Headers/xmmintrin.h b/clang/lib/Headers/xmmintrin.h
index 5890f0706ad5271..709cb4a4a12c8a2 100644
--- a/clang/lib/Headers/xmmintrin.h
+++ b/clang/lib/Headers/xmmintrin.h
@@ -2997,6 +2997,7 @@ _mm_movemask_ps(__m128 __a)
/// \param c
/// An immediate integer operand, with bits [4:0] specifying which comparison
/// operation to use: \n
+/// (Note that without avx enabled, only bits [2:0] are supported) \n
/// 0x00: Equal (ordered, non-signaling) \n
/// 0x01: Less-than (ordered, signaling) \n
/// 0x02: Less-than-or-equal (ordered, signaling) \n
@@ -3055,6 +3056,7 @@ _mm_movemask_ps(__m128 __a)
/// \param c
/// An immediate integer operand, with bits [4:0] specifying which comparison
/// operation to use: \n
+/// (Note that without avx enabled, only bits [2:0] are supported) \n
/// 0x00: Equal (ordered, non-signaling) \n
/// 0x01: Less-than (ordered, signaling) \n
/// 0x02: Less-than-or-equal (ordered, signaling) \n
diff --git a/clang/lib/Sema/SemaChecking.cpp b/clang/lib/Sema/SemaChecking.cpp
index 1d56c495e899722..3f5b81d3b191fc7 100644
--- a/clang/lib/Sema/SemaChecking.cpp
+++ b/clang/lib/Sema/SemaChecking.cpp
@@ -6276,6 +6276,8 @@ bool Sema::CheckX86BuiltinFunctionCall(const TargetInfo &TI, unsigned BuiltinID,
case X86::BI__builtin_ia32_cmpss:
case X86::BI__builtin_ia32_cmppd:
case X86::BI__builtin_ia32_cmpsd:
+ i = 2; l = 0; u = TI.hasFeature("avx") ? 31 : 7;
+ break;
case X86::BI__builtin_ia32_cmpps256:
case X86::BI__builtin_ia32_cmppd256:
case X86::BI__builtin_ia32_cmpps128_mask:
More information about the cfe-commits
mailing list