Add {mix,max}{ss,sd}{rr,rm} AVX forms.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@106264 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 90 insertions, 22 deletions

diff --git a/lib/Target/X86/X86InstrSSE.td b/lib/Target/X86/X86InstrSSE.td
index ce380c8..8ffb8e8 100644
--- a/lib/Target/X86/X86InstrSSE.td
+++ b/lib/Target/X86/X86InstrSSE.td
@@ -857,29 +857,30 @@ let Constraints = "$src1 = $dst" in {
 multiclass sse12_fp_binop_rm<bits<8> opc, string OpcodeStr,
                             SDNode OpNode, bit Commutable = 0> {
 
-  // Scalar operation, reg+reg.
-  def SSrr : SSI<opc, MRMSrcReg, (outs FR32:$dst), (ins FR32:$src1, FR32:$src2),
-                 !strconcat(OpcodeStr, "ss\t{$src2, $dst|$dst, $src2}"),
-                 [(set FR32:$dst, (OpNode FR32:$src1, FR32:$src2))]> {
-    let isCommutable = Commutable;
-  }
+  let Constraints = "", isAsmParserOnly = 1, hasVEX_4VPrefix = 1 in {
+    // Scalar operation, reg+reg.
+    let Prefix = 12 /* XS */ in
+      defm V#NAME#SS : sse12_fp_scalar<opc,
+        !strconcat(OpcodeStr, "ss\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
+                   OpNode, FR32, f32mem>;
 
-  def SDrr : SDI<opc, MRMSrcReg, (outs FR64:$dst), (ins FR64:$src1, FR64:$src2),
-                 !strconcat(OpcodeStr, "sd\t{$src2, $dst|$dst, $src2}"),
-                 [(set FR64:$dst, (OpNode FR64:$src1, FR64:$src2))]> {
-    let isCommutable = Commutable;
+    let Prefix = 11 /* XD */ in
+      defm V#NAME#SD : sse12_fp_scalar<opc,
+        !strconcat(OpcodeStr, "sd\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
+                   OpNode, FR64, f64mem>;
   }
 
-  // Scalar operation, reg+mem.
-  def SSrm : SSI<opc, MRMSrcMem, (outs FR32:$dst),
-                                 (ins FR32:$src1, f32mem:$src2),
-                 !strconcat(OpcodeStr, "ss\t{$src2, $dst|$dst, $src2}"),
-                 [(set FR32:$dst, (OpNode FR32:$src1, (load addr:$src2)))]>;
-
-  def SDrm : SDI<opc, MRMSrcMem, (outs FR64:$dst),
-                                 (ins FR64:$src1, f64mem:$src2),
-                 !strconcat(OpcodeStr, "sd\t{$src2, $dst|$dst, $src2}"),
-                 [(set FR64:$dst, (OpNode FR64:$src1, (load addr:$src2)))]>;
+  let Constraints = "$src1 = $dst" in {
+    // Scalar operation, reg+reg.
+    let Prefix = 12 /* XS */ in
+      defm SS : sse12_fp_scalar<opc,
+                      !strconcat(OpcodeStr, "ss\t{$src2, $dst|$dst, $src2}"),
+                      OpNode, FR32, f32mem>;
+    let Prefix = 11 /* XD */ in
+      defm SD : sse12_fp_scalar<opc,
+                      !strconcat(OpcodeStr, "sd\t{$src2, $dst|$dst, $src2}"),
+                      OpNode, FR64, f64mem>;
+  }
 
   // Vector operation, reg+reg.
   def PSrr : PSI<opc, MRMSrcReg, (outs VR128:$dst),
@@ -985,8 +986,10 @@ multiclass sse12_fp_binop_rm<bits<8> opc, string OpcodeStr,
 }
 }
 
-defm MAX : sse12_fp_binop_rm<0x5F, "max", X86fmax>;
-defm MIN : sse12_fp_binop_rm<0x5D, "min", X86fmin>;
+let isCommutable = 0 in {
+  defm MAX : sse12_fp_binop_rm<0x5F, "max", X86fmax>;
+  defm MIN : sse12_fp_binop_rm<0x5D, "min", X86fmin>;
+}
 
 //===----------------------------------------------------------------------===//
 // SSE packed FP Instructions
diff --git a/test/MC/AsmParser/X86/x86_32-encoding.s b/test/MC/AsmParser/X86/x86_32-encoding.s
index 998e9c6..b8b7c22 100644
--- a/test/MC/AsmParser/X86/x86_32-encoding.s
+++ b/test/MC/AsmParser/X86/x86_32-encoding.s
@@ -10180,3 +10180,35 @@ pshufb	CPI1_0(%rip), %xmm1
 // CHECK: vdivpd  3735928559(%ebx,%ecx,8), %xmm2, %xmm5
 // CHECK: encoding: [0xc5,0xe9,0x5e,0xac,0xcb,0xef,0xbe,0xad,0xde]
           vdivpd  3735928559(%ebx,%ecx,8), %xmm2, %xmm5
+// CHECK: vmaxss  %xmm2, %xmm4, %xmm6
+// CHECK: encoding: [0xc5,0xda,0x5f,0xf2]
+          vmaxss  %xmm2, %xmm4, %xmm6
+
+// CHECK: vmaxsd  %xmm2, %xmm4, %xmm6
+// CHECK: encoding: [0xc5,0xdb,0x5f,0xf2]
+          vmaxsd  %xmm2, %xmm4, %xmm6
+
+// CHECK: vminss  %xmm2, %xmm4, %xmm6
+// CHECK: encoding: [0xc5,0xda,0x5d,0xf2]
+          vminss  %xmm2, %xmm4, %xmm6
+
+// CHECK: vminsd  %xmm2, %xmm4, %xmm6
+// CHECK: encoding: [0xc5,0xdb,0x5d,0xf2]
+          vminsd  %xmm2, %xmm4, %xmm6
+
+// CHECK: vmaxss  -4(%ebx,%ecx,8), %xmm2, %xmm5
+// CHECK: encoding: [0xc5,0xea,0x5f,0x6c,0xcb,0xfc]
+          vmaxss  -4(%ebx,%ecx,8), %xmm2, %xmm5
+
+// CHECK: vmaxsd  -4(%ebx,%ecx,8), %xmm2, %xmm5
+// CHECK: encoding: [0xc5,0xeb,0x5f,0x6c,0xcb,0xfc]
+          vmaxsd  -4(%ebx,%ecx,8), %xmm2, %xmm5
+
+// CHECK: vminss  -4(%ebx,%ecx,8), %xmm2, %xmm5
+// CHECK: encoding: [0xc5,0xea,0x5d,0x6c,0xcb,0xfc]
+          vminss  -4(%ebx,%ecx,8), %xmm2, %xmm5
+
+// CHECK: vminsd  -4(%ebx,%ecx,8), %xmm2, %xmm5
+// CHECK: encoding: [0xc5,0xeb,0x5d,0x6c,0xcb,0xfc]
+          vminsd  -4(%ebx,%ecx,8), %xmm2, %xmm5
+
diff --git a/test/MC/AsmParser/X86/x86_64-encoding.s b/test/MC/AsmParser/X86/x86_64-encoding.s
index c574bcb..591274c 100644
--- a/test/MC/AsmParser/X86/x86_64-encoding.s
+++ b/test/MC/AsmParser/X86/x86_64-encoding.s
@@ -231,3 +231,36 @@ vmulpd  -4(%rcx,%rbx,8), %xmm10, %xmm11
 // CHECK: vdivpd  -4(%rcx,%rbx,8), %xmm10, %xmm11
 // CHECK: encoding: [0xc5,0x29,0x5e,0x5c,0xd9,0xfc]
 vdivpd  -4(%rcx,%rbx,8), %xmm10, %xmm11
+
+// CHECK: vmaxss  %xmm10, %xmm14, %xmm12
+// CHECK: encoding: [0xc4,0x41,0x0a,0x5f,0xe2]
+          vmaxss  %xmm10, %xmm14, %xmm12
+
+// CHECK: vmaxsd  %xmm10, %xmm14, %xmm12
+// CHECK: encoding: [0xc4,0x41,0x0b,0x5f,0xe2]
+          vmaxsd  %xmm10, %xmm14, %xmm12
+
+// CHECK: vminss  %xmm10, %xmm14, %xmm12
+// CHECK: encoding: [0xc4,0x41,0x0a,0x5d,0xe2]
+          vminss  %xmm10, %xmm14, %xmm12
+
+// CHECK: vminsd  %xmm10, %xmm14, %xmm12
+// CHECK: encoding: [0xc4,0x41,0x0b,0x5d,0xe2]
+          vminsd  %xmm10, %xmm14, %xmm12
+
+// CHECK: vmaxss  -4(%rbx,%rcx,8), %xmm12, %xmm10
+// CHECK: encoding: [0xc5,0x1a,0x5f,0x54,0xcb,0xfc]
+          vmaxss  -4(%rbx,%rcx,8), %xmm12, %xmm10
+
+// CHECK: vmaxsd  -4(%rbx,%rcx,8), %xmm12, %xmm10
+// CHECK: encoding: [0xc5,0x1b,0x5f,0x54,0xcb,0xfc]
+          vmaxsd  -4(%rbx,%rcx,8), %xmm12, %xmm10
+
+// CHECK: vminss  -4(%rbx,%rcx,8), %xmm12, %xmm10
+// CHECK: encoding: [0xc5,0x1a,0x5d,0x54,0xcb,0xfc]
+          vminss  -4(%rbx,%rcx,8), %xmm12, %xmm10
+
+// CHECK: vminsd  -4(%rbx,%rcx,8), %xmm12, %xmm10
+// CHECK: encoding: [0xc5,0x1b,0x5d,0x54,0xcb,0xfc]
+          vminsd  -4(%rbx,%rcx,8), %xmm12, %xmm10
+