Enable vpmovmskb for 128-bit vectors

openjdk · May 19, 2021 · efc2372 · efc2372
1 parent 319fe05
commit efc2372
Show file tree

Hide file tree

Showing 6 changed files with 11 additions and 10 deletions.
diff --git a/src/hotspot/cpu/x86/assembler_x86.cpp b/src/hotspot/cpu/x86/assembler_x86.cpp
@@ -4123,9 +4123,10 @@ void Assembler::pmovmskb(Register dst, XMMRegister src) {
   emit_int16((unsigned char)0xD7, (0xC0 | encode));
 }
 
-void Assembler::vpmovmskb(Register dst, XMMRegister src) {
-  assert(VM_Version::supports_avx2(), "");
-  InstructionAttr attributes(AVX_256bit, /* rex_w */ false, /* legacy_mode */ true, /* no_mask_reg */ true, /* uses_vl */ false);
+void Assembler::vpmovmskb(Register dst, XMMRegister src, int vec_enc) {
+  assert((VM_Version::supports_avx() && vec_enc == AVX_128bit) ||
+         (VM_Version::supports_avx2() && vec_enc  == AVX_256bit), "");
+  InstructionAttr attributes(vec_enc, /* rex_w */ false, /* legacy_mode */ true, /* no_mask_reg */ true, /* uses_vl */ false);
   int encode = vex_prefix_and_encode(dst->encoding(), 0, src->encoding(), VEX_SIMD_66, VEX_OPCODE_0F, &attributes);
   emit_int16((unsigned char)0xD7, (0xC0 | encode));
 }

diff --git a/src/hotspot/cpu/x86/assembler_x86.hpp b/src/hotspot/cpu/x86/assembler_x86.hpp
@@ -1746,7 +1746,7 @@ class Assembler : public AbstractAssembler  {
   void vpcmpgtq(XMMRegister dst, XMMRegister nds, XMMRegister src, int vector_len);
 
   void pmovmskb(Register dst, XMMRegister src);
-  void vpmovmskb(Register dst, XMMRegister src);
+  void vpmovmskb(Register dst, XMMRegister src, int vec_enc);
 
   // SSE 4.1 extract
   void pextrd(Register dst, XMMRegister src, int imm8);

diff --git a/src/hotspot/cpu/x86/c2_MacroAssembler_x86.cpp b/src/hotspot/cpu/x86/c2_MacroAssembler_x86.cpp
@@ -3779,10 +3779,10 @@ void C2_MacroAssembler::vector_mask_operation(int opc, Register dst, XMMRegister
 
 void C2_MacroAssembler::vector_mask_operation(int opc, Register dst, XMMRegister mask, XMMRegister xtmp,
                                               XMMRegister xtmp1, Register tmp, int masklen, int vec_enc) {
-  assert(VM_Version::supports_avx2(), "");
+  assert(VM_Version::supports_avx(), "");
   vpxor(xtmp, xtmp, xtmp, vec_enc);
   vpsubb(xtmp, xtmp, mask, vec_enc);
-  vpmovmskb(tmp, xtmp);
+  vpmovmskb(tmp, xtmp, vec_enc);
   switch(opc) {
     case Op_VectorMaskTrueCount:
       popcntq(dst, tmp);

diff --git a/src/hotspot/cpu/x86/macroAssembler_x86.cpp b/src/hotspot/cpu/x86/macroAssembler_x86.cpp
@@ -3216,9 +3216,9 @@ void MacroAssembler::vpmovzxbw(XMMRegister dst, Address src, int vector_len) {
   Assembler::vpmovzxbw(dst, src, vector_len);
 }
 
-void MacroAssembler::vpmovmskb(Register dst, XMMRegister src) {
+void MacroAssembler::vpmovmskb(Register dst, XMMRegister src, int vector_len) {
   assert((src->encoding() < 16),"XMM register should be 0-15");
-  Assembler::vpmovmskb(dst, src);
+  Assembler::vpmovmskb(dst, src, vector_len);
 }
 
 void MacroAssembler::vpmullw(XMMRegister dst, XMMRegister nds, XMMRegister src, int vector_len) {

diff --git a/src/hotspot/cpu/x86/macroAssembler_x86.hpp b/src/hotspot/cpu/x86/macroAssembler_x86.hpp
@@ -1303,7 +1303,7 @@ class MacroAssembler: public Assembler {
   void vpmovzxbw(XMMRegister dst, Address src, int vector_len);
   void vpmovzxbw(XMMRegister dst, XMMRegister src, int vector_len) { Assembler::vpmovzxbw(dst, src, vector_len); }
 
-  void vpmovmskb(Register dst, XMMRegister src);
+  void vpmovmskb(Register dst, XMMRegister src, int vector_len = Assembler::AVX_256bit);
 
   void vpmullw(XMMRegister dst, XMMRegister nds, XMMRegister src, int vector_len);
   void vpmullw(XMMRegister dst, XMMRegister nds, Address src, int vector_len);

diff --git a/src/hotspot/cpu/x86/x86.ad b/src/hotspot/cpu/x86/x86.ad
@@ -1584,7 +1584,7 @@ const bool Matcher::match_rule_supported(int opcode) {
     case Op_VectorMaskFirstTrue:
     case Op_VectorMaskLastTrue:
     case Op_VectorMaskTrueCount:
-      if (!is_LP64 || UseAVX < 2) {
+      if (!is_LP64 || UseAVX < 1) {
          return false;
       }
       break;