[x86][inline-asm][clang] accept 'v' constraint

[coby]

Summary

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

[delena]

test/CodeGen/x86-inline-asm-v-constraint.c

3

add KNL tests here.

[coby]

Addressing comments:
Added a check for KNL as well

[coby]

Commitd to revision 283716

lib/Basic/Targets.cpp

X86TargetInfo::validateAsmConstraint(const char *&Name,
   case 'd': // edx.
   case 'S': // esi.
   case 'D': // edi.
   case 'A': // edx:eax.
   case 't': // Top of floating point stack.
   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 'Q': // Any register accessible as [r]h: a, b, c, and d.
   case 'R': // "Legacy" registers: ax, bx, cx, dx, di, si, sp, bp.
   case 'l': // "Index" registers: any general register that can be used as an
             // index in a base+index memory access.
     Info.setAllowsRegister();
     return true;
   // Floating point constant constraints.
bool X86TargetInfo::validateOperandSize(StringRef Constraint,
   switch (Constraint[0]) {
   default: break;
   case 'y':
     return Size <= 64;
   case 'f':
   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.
       return Size <= 512U;
     else if (SSELevel >= AVX)
       // 256-bit ymm registers can be used if target supports AVX.
       return Size <= 256U;
     return Size <= 128U;

test/CodeGen/x86-inline-asm-v-constraint.c

+// RUN: %clang_cc1 %s -triple x86_64-unknown-linux-gnu -emit-llvm -target-cpu x86-64 -o - | FileCheck %s --check-prefix SSE
+// RUN: %clang_cc1 %s -triple x86_64-unknown-linux-gnu -emit-llvm -target-cpu skylake -D AVX -o - | 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 - | 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 - | 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 %0, <4 x float> %1)
+__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> %0)
+__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> %0, <16 x float> %1)
+__m512 testZMM(__m512 _zmm0, __m512 _zmm1) {
+#ifdef AVX512
+  __asm__("vpternlogd $0, %1, %2, %0" :"=v"(_zmm0) : "v"(_zmm1), "v"(_zmm0));
+#endif
+  return _zmm0;
+}