From 2f6104867287dececb46e8d93dd9246aad47c282 Mon Sep 17 00:00:00 2001
From: Michael Zuckerman <Michael.zuckerman@intel.com>
Date: Tue, 1 Nov 2016 13:16:44 +0000
Subject: [PATCH] [x86][inline-asm][clang] accept 'v' constraint Commit on
 behalf of: Coby Tayree

1.'v' constraint for (x86) non-avx arch imitates the already implemented 'x' constraint, i.e. allows XMM{0-15} & YMM{0-15} depending on the apparent arch & mode (32/64).
2.for the avx512 arch it allows [X,Y,Z]MM{0-31} (mode dependent)

This patch applies the needed changes to clang
LLVM patch: https://reviews.llvm.org/D25005

Differential Revision: https://reviews.llvm.org/D25005

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@285688 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Basic/Targets.cpp                      |  2 ++
 test/CodeGen/x86-inline-asm-v-constraint.c | 30 ++++++++++++++++++++++
 2 files changed, 32 insertions(+)
 create mode 100644 test/CodeGen/x86-inline-asm-v-constraint.c

diff --git a/lib/Basic/Targets.cpp b/lib/Basic/Targets.cpp
index e2b8271892..d538296600 100644
--- a/lib/Basic/Targets.cpp
+++ b/lib/Basic/Targets.cpp
@@ -4018,6 +4018,7 @@ X86TargetInfo::validateAsmConstraint(const char *&Name,
   case 'u': // Second from top of floating point stack.
   case 'q': // Any register accessible as [r]l: a, b, c, and d.
   case 'y': // Any MMX register.
+  case 'v': // Any {X,Y,Z}MM register (Arch & context dependent)
   case 'x': // Any SSE register.
   case 'k': // Any AVX512 mask register (same as Yk, additionaly allows k0
             // for intermideate k reg operations).
@@ -4062,6 +4063,7 @@ bool X86TargetInfo::validateOperandSize(StringRef Constraint,
   case 't':
   case 'u':
     return Size <= 128;
+  case 'v':
   case 'x':
     if (SSELevel >= AVX512F)
       // 512-bit zmm registers can be used if target supports AVX512F.
diff --git a/test/CodeGen/x86-inline-asm-v-constraint.c b/test/CodeGen/x86-inline-asm-v-constraint.c
new file mode 100644
index 0000000000..d335e4b6a0
--- /dev/null
+++ b/test/CodeGen/x86-inline-asm-v-constraint.c
@@ -0,0 +1,30 @@
+// RUN: %clang_cc1 %s -triple x86_64-unknown-linux-gnu -emit-llvm -target-cpu x86-64 -o - |opt -instnamer -S |FileCheck %s --check-prefix SSE
+// RUN: %clang_cc1 %s -triple x86_64-unknown-linux-gnu -emit-llvm -target-cpu skylake -D AVX -o -|opt -instnamer -S  | FileCheck %s --check-prefixes AVX,SSE
+// RUN: %clang_cc1 %s -triple x86_64-unknown-linux-gnu -emit-llvm -target-cpu skylake-avx512 -D AVX512 -D AVX -o -|opt -instnamer -S  | FileCheck %s --check-prefixes AVX512,AVX,SSE
+// RUN: %clang_cc1 %s -triple x86_64-unknown-linux-gnu -emit-llvm -target-cpu knl -D AVX -D AVX512 -o - |opt -instnamer -S  | FileCheck %s --check-prefixes AVX512,AVX,SSE
+
+typedef float __m128 __attribute__ ((vector_size (16)));
+typedef float __m256 __attribute__ ((vector_size (32)));
+typedef float __m512 __attribute__ ((vector_size (64)));
+
+// SSE: call <4 x float> asm "vmovhlps $1, $2, $0", "=v,v,v,~{dirflag},~{fpsr},~{flags}"(i64 %tmp, <4 x float> %tmp1)
+__m128 testXMM(__m128 _xmm0, long _l) {
+  __asm__("vmovhlps %1, %2, %0" :"=v"(_xmm0) : "v"(_l), "v"(_xmm0));
+  return _xmm0;
+}
+
+// AVX: call <8 x float> asm "vmovsldup $1, $0", "=v,v,~{dirflag},~{fpsr},~{flags}"(<8 x float> %tmp)
+__m256 testYMM(__m256 _ymm0) {
+#ifdef AVX
+  __asm__("vmovsldup %1, %0" :"=v"(_ymm0) : "v"(_ymm0));
+#endif
+  return _ymm0;
+}
+
+// AVX512: call <16 x float> asm "vpternlogd $$0, $1, $2, $0", "=v,v,v,~{dirflag},~{fpsr},~{flags}"(<16 x float> %tmp, <16 x float> %tmp1)
+__m512 testZMM(__m512 _zmm0, __m512 _zmm1) {
+#ifdef AVX512
+  __asm__("vpternlogd $0, %1, %2, %0" :"=v"(_zmm0) : "v"(_zmm1), "v"(_zmm0));
+#endif
+  return _zmm0;
+}
-- 
2.40.0