From eeb2123a839fe7a6bb25d70f941d50e81ff33cf5 Mon Sep 17 00:00:00 2001
From: Clement Courbet <courbet@google.com>
Date: Wed, 2 May 2018 13:40:48 +0000
Subject: [PATCH] [X86] Fix scheduling info for VMPSADBWYrmi.

https://reviews.llvm.org/D46356

llvm-svn: 331355
---
 llvm/lib/Target/X86/X86SchedBroadwell.td | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/llvm/lib/Target/X86/X86SchedBroadwell.td b/llvm/lib/Target/X86/X86SchedBroadwell.td
index 0531ef5..1994625 100755
--- a/llvm/lib/Target/X86/X86SchedBroadwell.td
+++ b/llvm/lib/Target/X86/X86SchedBroadwell.td
@@ -11,7 +11,6 @@
 // scheduling and other instruction cost heuristics.
 //
 //===----------------------------------------------------------------------===//
-
 def BroadwellModel : SchedMachineModel {
   // All x86 instructions are modeled as a single micro-op, and BW can decode 4
   // instructions per cycle.
@@ -156,9 +155,9 @@ def  : WriteRes<WriteFStore,       [BWPort237, BWPort4]>;
 def  : WriteRes<WriteFMove,        [BWPort5]>;
 
 defm : BWWriteResPair<WriteFAdd,   [BWPort1],  3, [1], 1, 5>; // Floating point add/sub.
-defm : BWWriteResPair<WriteFAddY,  [BWPort1],  3, [1], 1, 6>; // Floating point add/sub (YMM/ZMM).
+defm : BWWriteResPair<WriteFAddY,  [BWPort1],  3, [1], 1, 7>; // Floating point add/sub (YMM/ZMM).
 defm : BWWriteResPair<WriteFCmp,   [BWPort1],  3, [1], 1, 5>; // Floating point compare.
-defm : BWWriteResPair<WriteFCmpY,  [BWPort1],  3, [1], 1, 6>; // Floating point compare (YMM/ZMM).
+defm : BWWriteResPair<WriteFCmpY,  [BWPort1],  3, [1], 1, 7>; // Floating point compare (YMM/ZMM).
 defm : BWWriteResPair<WriteFCom,   [BWPort1],  3>; // Floating point compare to flags.
 defm : BWWriteResPair<WriteFMul,   [BWPort0],  5, [1], 1, 5>; // Floating point multiplication.
 defm : BWWriteResPair<WriteFMulY,  [BWPort0],  5, [1], 1, 7>; // Floating point multiplication (YMM/ZMM).
@@ -1369,8 +1368,20 @@ def BWWriteResGroup101 : SchedWriteRes<[BWPort1,BWPort23]> {
 }
 def: InstRW<[BWWriteResGroup101], (instregex "(ADD|SUB|SUBR)_F(32|64)m",
                                              "ILD_F(16|32|64)m",
+                                             "VADDPDYrm",
+                                             "VADDPSYrm",
+                                             "VADDSUBPDYrm",
+                                             "VADDSUBPSYrm",
+                                             "VCMPPDYrmi",
+                                             "VCMPPSYrmi",
                                              "VCVTPS2DQYrm",
-                                             "VCVTTPS2DQYrm")>;
+                                             "VCVTTPS2DQYrm",
+                                             "VMAX(C?)PDYrm",
+                                             "VMAX(C?)PSYrm",
+                                             "VMIN(C?)PDYrm",
+                                             "VMIN(C?)PSYrm",
+                                             "VSUBPDYrm",
+                                             "VSUBPSYrm")>;
 
 def BWWriteResGroup102 : SchedWriteRes<[BWPort5,BWPort23]> {
   let Latency = 9;
@@ -1643,7 +1654,7 @@ def: InstRW<[BWWriteResGroup137_1], (instregex "(V?)SQRTSSr")>;
 def BWWriteResGroup138 : SchedWriteRes<[BWPort0,BWPort5,BWPort23]> {
   let Latency = 13;
   let NumMicroOps = 4;
-  let ResourceCycles = [1,2,1,7];
+  let ResourceCycles = [1,2,1];
 }
 def: InstRW<[BWWriteResGroup138], (instregex "VMPSADBWYrmi")>;
 
-- 
2.7.4