X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;ds=sidebyside;f=lib%2FTarget%2FARM%2FARMScheduleA9.td;h=49fedf63f8bca209b925b0ac6d908deb31dad507;hb=83ec87755ed4d07f6650d6727fb762052bd0041c;hp=d5ab5dcc87b17201c27cf46b57eaf557ca603978;hpb=41957f6eb2271e5f1981b32a873d1b58217c6411;p=oota-llvm.git

diff --git a/lib/Target/ARM/ARMScheduleA9.td b/lib/Target/ARM/ARMScheduleA9.td
index d5ab5dcc87b..49fedf63f8b 100644
--- a/lib/Target/ARM/ARMScheduleA9.td
+++ b/lib/Target/ARM/ARMScheduleA9.td
@@ -50,6 +50,16 @@ def CortexA9Itineraries : ProcessorItineraries<
   InstrItinData<IIC_iMOVix2 , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_ALU0, A9_ALU1]>,
                                InstrStage<1, [A9_ALU0, A9_ALU1]>], [2]>,
+  InstrItinData<IIC_iMOVix2addpc,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
+                                  InstrStage<1, [A9_ALU0, A9_ALU1]>,
+                                  InstrStage<1, [A9_ALU0, A9_ALU1]>,
+                                  InstrStage<1, [A9_ALU0, A9_ALU1]>], [3]>,
+  InstrItinData<IIC_iMOVix2ld,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
+                               InstrStage<1, [A9_ALU0, A9_ALU1]>,
+                               InstrStage<1, [A9_ALU0, A9_ALU1]>,
+                               InstrStage<1, [A9_MUX0], 0>,
+                               InstrStage<1, [A9_AGU], 0>,
+                               InstrStage<1, [A9_LSUnit]>], [5]>,
   //
   // MVN instructions
   InstrItinData<IIC_iMVNi   , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
@@ -123,7 +133,8 @@ def CortexA9Itineraries : ProcessorItineraries<
   InstrItinData<IIC_iCMPr   , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_ALU0, A9_ALU1]>],
                                [1, 1], [A9_LdBypass, A9_LdBypass]>,
-  InstrItinData<IIC_iCMPsi  , [InstrStage<2, [A9_ALU0, A9_ALU1]>],
+  InstrItinData<IIC_iCMPsi  , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
+                               InstrStage<2, [A9_ALU0, A9_ALU1]>],
                                 [1, 1], [A9_LdBypass, NoBypass]>,
   InstrItinData<IIC_iCMPsr  , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<3, [A9_ALU0, A9_ALU1]>],
@@ -149,6 +160,10 @@ def CortexA9Itineraries : ProcessorItineraries<
                                InstrStage<1, [A9_ALU0, A9_ALU1]>], [1, 1]>,
   InstrItinData<IIC_iCMOVsr , [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<2, [A9_ALU0, A9_ALU1]>], [2, 1, 1]>,
+  InstrItinData<IIC_iCMOVix2, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
+                               InstrStage<1, [A9_ALU0, A9_ALU1]>,
+                               InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
+                               InstrStage<1, [A9_ALU0, A9_ALU1]>], [2]>,
 
   // Integer multiply pipeline
   //
@@ -402,6 +417,10 @@ def CortexA9Itineraries : ProcessorItineraries<
                                 InstrStage<1, [A9_AGU], 0>,
                                 InstrStage<2, [A9_LSUnit]>], [2]>,
 
+  //
+  // Preload
+  InstrItinData<IIC_Preload,   [InstrStage<1, [A9_Issue0, A9_Issue1]>], [1, 1]>,
+
   // Branch
   //
   // no delay slots, so the latency of a branch is unimportant
@@ -637,19 +656,19 @@ def CortexA9Itineraries : ProcessorItineraries<
                               [1, 1, 1]>,
   //
   // Single-precision to Integer Move
+  //
+  // On A9 move-from-VFP is free to issue with no stall if other VFP
+  // operations are in flight. I assume it still can't dual-issue though.
   InstrItinData<IIC_fpMOVSI,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
-                               InstrStage<1, [A9_MUX0], 0>,
-                               InstrStage<1, [A9_DRegsVFP], 0, Required>,
-                               InstrStage<2, [A9_DRegsN],   0, Reserved>,
-                               InstrStage<1, [A9_NPipe]>],
+                               InstrStage<1, [A9_MUX0], 0>],
                               [2, 1]>,
   //
   // Double-precision to Integer Move
+  //
+  // On A9 move-from-VFP is free to issue with no stall if other VFP
+  // operations are in flight. I assume it still can't dual-issue though.
   InstrItinData<IIC_fpMOVDI,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
-                               InstrStage<1, [A9_MUX0], 0>,
-                               InstrStage<1, [A9_DRegsVFP], 0, Required>,
-                               InstrStage<2, [A9_DRegsN],   0, Reserved>,
-                               InstrStage<1, [A9_NPipe]>],
+                               InstrStage<1, [A9_MUX0], 0>],
                               [2, 1, 1]>,
   //
   // Single-precision FP Load
@@ -672,20 +691,22 @@ def CortexA9Itineraries : ProcessorItineraries<
                               [2, 1]>,
   //
   // FP Load Multiple
+  // FIXME: assumes 2 doubles which requires 2 LS cycles.
   InstrItinData<IIC_fpLoad_m, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsVFP], 0, Required>,
                                InstrStage<2, [A9_DRegsN],   0, Reserved>,
                                InstrStage<1, [A9_NPipe], 0>,
-                               InstrStage<1, [A9_LSUnit]>], [1, 1, 1, 1]>,
+                               InstrStage<2, [A9_LSUnit]>], [1, 1, 1, 1]>,
   //
   // FP Load Multiple + update
+  // FIXME: assumes 2 doubles which requires 2 LS cycles.
   InstrItinData<IIC_fpLoad_mu,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsVFP], 0, Required>,
                                InstrStage<2, [A9_DRegsN],   0, Reserved>,
                                InstrStage<1, [A9_NPipe], 0>,
-                               InstrStage<1, [A9_LSUnit]>], [2, 1, 1, 1]>,
+                               InstrStage<2, [A9_LSUnit]>], [2, 1, 1, 1]>,
   //
   // Single-precision FP Store
   InstrItinData<IIC_fpStore32,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
@@ -706,169 +727,206 @@ def CortexA9Itineraries : ProcessorItineraries<
                               [1, 1]>,
   //
   // FP Store Multiple
+  // FIXME: assumes 2 doubles which requires 2 LS cycles.
   InstrItinData<IIC_fpStore_m,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsVFP], 0, Required>,
                                InstrStage<2, [A9_DRegsN],   0, Reserved>,
                                InstrStage<1, [A9_NPipe], 0>,
-                               InstrStage<1, [A9_LSUnit]>], [1, 1, 1, 1]>,
+                               InstrStage<2, [A9_LSUnit]>], [1, 1, 1, 1]>,
   //
   // FP Store Multiple + update
+  // FIXME: assumes 2 doubles which requires 2 LS cycles.
   InstrItinData<IIC_fpStore_mu,[InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                 InstrStage<1, [A9_MUX0], 0>,
                                 InstrStage<1, [A9_DRegsVFP], 0, Required>,
                                 InstrStage<2, [A9_DRegsN],   0, Reserved>,
                                 InstrStage<1, [A9_NPipe], 0>,
-                                InstrStage<1, [A9_LSUnit]>], [2, 1, 1, 1]>,
+                                InstrStage<2, [A9_LSUnit]>], [2, 1, 1, 1]>,
   // NEON
   // VLD1
-  // FIXME: Conservatively assume insufficent alignment.
   InstrItinData<IIC_VLD1,     [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<2, [A9_NPipe], 0>,
-                               InstrStage<2, [A9_LSUnit]>],
-                              [2, 1]>,
+                               InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
+                              [1, 1]>,
   // VLD1x2
   InstrItinData<IIC_VLD1x2,   [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<2, [A9_NPipe], 0>,
-                               InstrStage<2, [A9_LSUnit]>],
-                              [2, 2, 1]>,
+                               InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
+                              [1, 1, 1]>,
   // VLD1x3
   InstrItinData<IIC_VLD1x3,   [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
-                              [2, 2, 3, 1]>,
+                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
+                              [1, 1, 2, 1]>,
   // VLD1x4
   InstrItinData<IIC_VLD1x4,   [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
-                              [2, 2, 3, 3, 1]>,
+                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
+                              [1, 1, 2, 2, 1]>,
   // VLD1u
   InstrItinData<IIC_VLD1u,    [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<2, [A9_NPipe], 0>,
-                               InstrStage<2, [A9_LSUnit]>],
-                              [2, 2, 1]>,
+                               InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
+                              [1, 2, 1]>,
   // VLD1x2u
   InstrItinData<IIC_VLD1x2u,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<2, [A9_NPipe], 0>,
-                               InstrStage<2, [A9_LSUnit]>],
-                              [2, 2, 2, 1]>,
+                               InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
+                              [1, 1, 2, 1]>,
   // VLD1x3u
   InstrItinData<IIC_VLD1x3u,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
-                              [2, 2, 3, 2, 1]>,
+                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
+                              [1, 1, 2, 2, 1]>,
   // VLD1x4u
   InstrItinData<IIC_VLD1x4u,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
-                              [2, 2, 3, 3, 2, 1]>,
+                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
+                              [1, 1, 2, 2, 2, 1]>,
   //
   // VLD1ln
   InstrItinData<IIC_VLD1ln,   [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 1>,
-                               InstrStage<3, [A9_LSUnit]>],
-                              [4, 1, 1, 1]>,
+                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
+                              [3, 1, 1, 1]>,
   //
   // VLD1lnu
   InstrItinData<IIC_VLD1lnu,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 1>,
-                               InstrStage<3, [A9_LSUnit]>],
-                              [4, 2, 1, 1, 1, 1]>,
+                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
+                              [3, 2, 1, 1, 1, 1]>,
+  //
+  // VLD1dup
+  InstrItinData<IIC_VLD1dup,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
+                               InstrStage<1, [A9_MUX0], 0>,
+                               InstrStage<1, [A9_DRegsN],   0, Required>,
+                               InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
+                              [2, 1]>,
+  //
+  // VLD1dupu
+  InstrItinData<IIC_VLD1dupu, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
+                               InstrStage<1, [A9_MUX0], 0>,
+                               InstrStage<1, [A9_DRegsN],   0, Required>,
+                               InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
+                              [2, 2, 1, 1]>,
   //
   // VLD2
   InstrItinData<IIC_VLD2,     [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
                                // Extra latency cycles since wbck is 7 cycles
-                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<2, [A9_NPipe], 0>,
-                               InstrStage<2, [A9_LSUnit]>],
-                              [3, 3, 1]>,
+                               InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
+                              [2, 2, 1]>,
   //
   // VLD2x2
   InstrItinData<IIC_VLD2x2,   [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
-                              [3, 4, 3, 4, 1]>,
+                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
+                              [2, 3, 2, 3, 1]>,
   //
   // VLD2ln
   InstrItinData<IIC_VLD2ln,   [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
-                              [4, 4, 1, 1, 1, 1]>,
+                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
+                              [3, 3, 1, 1, 1, 1]>,
   //
   // VLD2u
   InstrItinData<IIC_VLD2u,    [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
                                // Extra latency cycles since wbck is 7 cycles
-                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<2, [A9_NPipe], 0>,
-                               InstrStage<2, [A9_LSUnit]>],
-                              [3, 3, 2, 1, 1, 1]>,
+                               InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
+                              [2, 2, 2, 1, 1, 1]>,
   //
   // VLD2x2u
   InstrItinData<IIC_VLD2x2u,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
-                              [3, 4, 3, 4, 2, 1]>,
+                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
+                              [2, 3, 2, 3, 2, 1]>,
   //
   // VLD2lnu
   InstrItinData<IIC_VLD2lnu,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
-                              [4, 4, 2, 1, 1, 1, 1, 1]>,
+                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
+                              [3, 3, 2, 1, 1, 1, 1, 1]>,
+  //
+  // VLD2dup
+  InstrItinData<IIC_VLD2dup,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
+                               InstrStage<1, [A9_MUX0], 0>,
+                               InstrStage<1, [A9_DRegsN],   0, Required>,
+                               InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
+                              [2, 2, 1]>,
+  //
+  // VLD2dupu
+  InstrItinData<IIC_VLD2dupu, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
+                               InstrStage<1, [A9_MUX0], 0>,
+                               InstrStage<1, [A9_DRegsN],   0, Required>,
+                               InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
+                              [2, 2, 2, 1, 1]>,
   //
   // VLD3
   InstrItinData<IIC_VLD3,     [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<10,[A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<4, [A9_NPipe], 0>,
-                               InstrStage<4, [A9_LSUnit]>],
-                              [4, 4, 5, 1]>,
+                               InstrStage<9,[A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<3, [A9_NPipe], 0>,
+                               InstrStage<3, [A9_LSUnit]>],
+                              [3, 3, 4, 1]>,
   //
   // VLD3ln
   InstrItinData<IIC_VLD3ln,   [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
@@ -883,10 +941,10 @@ def CortexA9Itineraries : ProcessorItineraries<
   InstrItinData<IIC_VLD3u,    [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<10,[A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<4, [A9_NPipe], 0>,
-                               InstrStage<4, [A9_LSUnit]>],
-                              [4, 4, 5, 2, 1]>,
+                               InstrStage<9,[A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<3, [A9_NPipe], 0>,
+                               InstrStage<3, [A9_LSUnit]>],
+                              [3, 3, 4, 2, 1]>,
   //
   // VLD3lnu
   InstrItinData<IIC_VLD3lnu,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
@@ -897,94 +955,130 @@ def CortexA9Itineraries : ProcessorItineraries<
                                InstrStage<5, [A9_LSUnit]>],
                               [5, 5, 6, 2, 1, 1, 1, 1, 1, 2]>,
   //
+  // VLD3dup
+  InstrItinData<IIC_VLD3dup,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
+                               InstrStage<1, [A9_MUX0], 0>,
+                               InstrStage<1, [A9_DRegsN],   0, Required>,
+                               InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<3, [A9_NPipe], 0>,
+                               InstrStage<3, [A9_LSUnit]>],
+                              [3, 3, 4, 1]>,
+  //
+  // VLD3dupu
+  InstrItinData<IIC_VLD3dupu, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
+                               InstrStage<1, [A9_MUX0], 0>,
+                               InstrStage<1, [A9_DRegsN],   0, Required>,
+                               InstrStage<9, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<3, [A9_NPipe], 0>,
+                               InstrStage<3, [A9_LSUnit]>],
+                              [3, 3, 4, 2, 1, 1]>,
+  //
   // VLD4
   InstrItinData<IIC_VLD4,     [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<10,[A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<4, [A9_NPipe], 0>,
-                               InstrStage<4, [A9_LSUnit]>],
-                              [4, 4, 5, 5, 1]>,
+                               InstrStage<9,[A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<3, [A9_NPipe], 0>,
+                               InstrStage<3, [A9_LSUnit]>],
+                              [3, 3, 4, 4, 1]>,
   //
   // VLD4ln
   InstrItinData<IIC_VLD4ln,   [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<11,[A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<5, [A9_NPipe], 0>,
-                               InstrStage<5, [A9_LSUnit]>],
-                              [5, 5, 6, 6, 1, 1, 1, 1, 2, 2]>,
+                               InstrStage<10,[A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<4, [A9_NPipe], 0>,
+                               InstrStage<4, [A9_LSUnit]>],
+                              [4, 4, 5, 5, 1, 1, 1, 1, 2, 2]>,
   //
   // VLD4u
   InstrItinData<IIC_VLD4u,    [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
+                               InstrStage<1, [A9_MUX0], 0>,
+                               InstrStage<1, [A9_DRegsN],   0, Required>,
+                               InstrStage<9,[A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<3, [A9_NPipe], 0>,
+                               InstrStage<3, [A9_LSUnit]>],
+                              [3, 3, 4, 4, 2, 1]>,
+  //
+  // VLD4lnu
+  InstrItinData<IIC_VLD4lnu,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
                                InstrStage<10,[A9_DRegsVFP], 0, Reserved>,
                                InstrStage<4, [A9_NPipe], 0>,
                                InstrStage<4, [A9_LSUnit]>],
-                              [4, 4, 5, 5, 2, 1]>,
+                              [4, 4, 5, 5, 2, 1, 1, 1, 1, 1, 2, 2]>,
   //
-  // VLD4lnu
-  InstrItinData<IIC_VLD4lnu,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
+  // VLD4dup
+  InstrItinData<IIC_VLD4dup,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<11,[A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<5, [A9_NPipe], 0>,
-                               InstrStage<5, [A9_LSUnit]>],
-                              [5, 5, 6, 6, 2, 1, 1, 1, 1, 1, 2, 2]>,
+                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
+                              [2, 2, 3, 3, 1]>,
   //
-  // VST1
-  InstrItinData<IIC_VST1,     [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
+  // VLD4dupu
+  InstrItinData<IIC_VLD4dupu, [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<8, [A9_DRegsVFP], 0, Reserved>,
                                InstrStage<2, [A9_NPipe], 0>,
                                InstrStage<2, [A9_LSUnit]>],
+                              [2, 2, 3, 3, 2, 1, 1]>,
+  //
+  // VST1
+  InstrItinData<IIC_VST1,     [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
+                               InstrStage<1, [A9_MUX0], 0>,
+                               InstrStage<1, [A9_DRegsN],   0, Required>,
+                               InstrStage<1, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
                               [1, 1, 1]>,
   //
   // VST1x2
   InstrItinData<IIC_VST1x2,   [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<2, [A9_NPipe], 0>,
-                               InstrStage<2, [A9_LSUnit]>],
+                               InstrStage<1, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
                               [1, 1, 1, 1]>,
   //
   // VST1x3
   InstrItinData<IIC_VST1x3,   [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
+                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
                               [1, 1, 1, 1, 2]>,
   //
   // VST1x4
   InstrItinData<IIC_VST1x4,   [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
+                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
                               [1, 1, 1, 1, 2, 2]>,
   //
   // VST1u
   InstrItinData<IIC_VST1u,    [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<2, [A9_NPipe], 0>,
-                               InstrStage<2, [A9_LSUnit]>],
+                               InstrStage<1, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
                               [2, 1, 1, 1, 1]>,
   //
   // VST1x2u
   InstrItinData<IIC_VST1x2u,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<2, [A9_NPipe], 0>,
-                               InstrStage<2, [A9_LSUnit]>],
+                               InstrStage<1, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
                               [2, 1, 1, 1, 1, 1]>,
   //
   // VST1x3u
@@ -992,44 +1086,44 @@ def CortexA9Itineraries : ProcessorItineraries<
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
                                InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
                               [2, 1, 1, 1, 1, 1, 2]>,
   //
   // VST1x4u
   InstrItinData<IIC_VST1x4u,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
+                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
                               [2, 1, 1, 1, 1, 1, 2, 2]>,
   //
   // VST1ln
   InstrItinData<IIC_VST1ln,   [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<2, [A9_NPipe], 1>,
-                               InstrStage<2, [A9_LSUnit]>],
+                               InstrStage<1, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
                               [1, 1, 1]>,
   //
   // VST1lnu
   InstrItinData<IIC_VST1lnu,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 1>,
-                               InstrStage<3, [A9_LSUnit]>],
+                               InstrStage<1, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
                               [2, 1, 1, 1, 1]>,
   //
   // VST2
   InstrItinData<IIC_VST2,     [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<2, [A9_NPipe], 0>,
-                               InstrStage<2, [A9_LSUnit]>],
+                               InstrStage<1, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
                               [1, 1, 1, 1]>,
   //
   // VST2x2
@@ -1045,9 +1139,9 @@ def CortexA9Itineraries : ProcessorItineraries<
   InstrItinData<IIC_VST2u,    [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<2, [A9_NPipe], 0>,
-                               InstrStage<2, [A9_LSUnit]>],
+                               InstrStage<1, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
                               [2, 1, 1, 1, 1, 1]>,
   //
   // VST2x2u
@@ -1063,36 +1157,36 @@ def CortexA9Itineraries : ProcessorItineraries<
   InstrItinData<IIC_VST2ln,   [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<2, [A9_NPipe], 0>,
-                               InstrStage<2, [A9_LSUnit]>],
+                               InstrStage<1, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
                               [1, 1, 1, 1]>,
   //
   // VST2lnu
   InstrItinData<IIC_VST2lnu,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
+                               InstrStage<1, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<1, [A9_NPipe], 0>,
+                               InstrStage<1, [A9_LSUnit]>],
                               [2, 1, 1, 1, 1, 1]>,
   //
   // VST3
   InstrItinData<IIC_VST3,     [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
+                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
                               [1, 1, 1, 1, 2]>,
   //
   // VST3u
   InstrItinData<IIC_VST3u,    [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
+                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
                               [2, 1, 1, 1, 1, 1, 2]>,
   //
   // VST3ln
@@ -1117,36 +1211,36 @@ def CortexA9Itineraries : ProcessorItineraries<
   InstrItinData<IIC_VST4,     [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
+                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
                               [1, 1, 1, 1, 2, 2]>,
   //
   // VST4u
   InstrItinData<IIC_VST4u,    [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
+                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
                               [2, 1, 1, 1, 1, 1, 2, 2]>,
   //
   // VST4ln
   InstrItinData<IIC_VST4ln,   [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
+                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
                               [1, 1, 1, 1, 2, 2]>,
   //
   // VST4lnu
   InstrItinData<IIC_VST4lnu,  [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
-                               InstrStage<3, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<3, [A9_NPipe], 0>,
-                               InstrStage<3, [A9_LSUnit]>],
+                               InstrStage<2, [A9_DRegsVFP], 0, Reserved>,
+                               InstrStage<2, [A9_NPipe], 0>,
+                               InstrStage<2, [A9_LSUnit]>],
                               [2, 1, 1, 1, 1, 1, 2, 2]>,
 
   //
@@ -1316,11 +1410,11 @@ def CortexA9Itineraries : ProcessorItineraries<
                               [4, 2, 2]>,
   //
   // Double-register Absolute Difference and Accumulate
-  InstrItinData<IIC_VABAD,    [InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
-                               InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
+  InstrItinData<IIC_VABAD,    [InstrStage<1, [A9_Issue0, A9_Issue1], 0>,
                                InstrStage<1, [A9_MUX0], 0>,
                                InstrStage<1, [A9_DRegsN],   0, Required>,
                                // Extra latency cycles since wbck is 6 cycles
+                               InstrStage<7, [A9_DRegsVFP], 0, Reserved>,
                                InstrStage<1, [A9_NPipe]>],
                               [6, 3, 2, 1]>,
   //