[X86][BtVer2] Improved latency and throughput of float/vector loads and stores.

This patch introduces the following changes to the btver2 scheduling model:

- The number of micro opcodes for YMM loads and stores is now 2 (it was
  incorrectly set to 1 for both aligned and misaligned loads/stores).

- Increased the number of AGU resource cycles for YMM loads and stores
  to 2cy (instead of 1cy).

- Removed JFPU01 and JFPX from the list of resources consumed by pure
  float/vector loads (no MMX).

I verified with llvm-exegesis that pure XMM/YMM loads are no-pipe. Those
are dispatched to the FPU but not really issues on JFPU01.

Differential Revision: https://reviews.llvm.org/D68871

llvm-svn: 374765

1 files changed, 6 insertions, 6 deletions

diff --git a/llvm/lib/Target/X86/X86ScheduleBtVer2.td b/llvm/lib/Target/X86/X86ScheduleBtVer2.td
index 3addf048dba..d0421d94ee0 100644
--- a/llvm/lib/Target/X86/X86ScheduleBtVer2.td
+++ b/llvm/lib/Target/X86/X86ScheduleBtVer2.td
@@ -501,14 +501,14 @@ defm : X86WriteRes<WriteFLD0,          [JFPU1, JSTC], 3, [1,1], 1>;
 defm : X86WriteRes<WriteFLD1,          [JFPU1, JSTC], 3, [1,1], 1>;
 defm : X86WriteRes<WriteFLDC,          [JFPU1, JSTC], 3, [1,1], 1>;
 defm : X86WriteRes<WriteFLoad,         [JLAGU, JFPU01, JFPX], 5, [1, 1, 1], 1>;
-defm : X86WriteRes<WriteFLoadX,        [JLAGU, JFPU01, JFPX], 5, [1, 1, 1], 1>;
-defm : X86WriteRes<WriteFLoadY,        [JLAGU, JFPU01, JFPX], 5, [1, 1, 1], 1>;
+defm : X86WriteRes<WriteFLoadX,        [JLAGU], 5, [1], 1>;
+defm : X86WriteRes<WriteFLoadY,        [JLAGU], 5, [2], 2>;
 defm : X86WriteRes<WriteFMaskedLoad,   [JLAGU, JFPU01, JFPX], 6, [1, 2, 2], 1>;
 defm : X86WriteRes<WriteFMaskedLoadY,  [JLAGU, JFPU01, JFPX], 6, [2, 4, 4], 2>;
 
 defm : X86WriteRes<WriteFStore,        [JSAGU, JFPU1,  JSTC], 2, [1, 1, 1], 1>;
 defm : X86WriteRes<WriteFStoreX,       [JSAGU, JFPU1,  JSTC], 1, [1, 1, 1], 1>;
-defm : X86WriteRes<WriteFStoreY,       [JSAGU, JFPU1,  JSTC], 1, [1, 1, 1], 1>;
+defm : X86WriteRes<WriteFStoreY,       [JSAGU, JFPU1,  JSTC], 1, [2, 2, 2], 2>;
 defm : X86WriteRes<WriteFStoreNT,      [JSAGU, JFPU1,  JSTC], 3, [1, 1, 1], 1>;
 defm : X86WriteRes<WriteFStoreNTX,     [JSAGU, JFPU1,  JSTC], 3, [1, 1, 1], 1>;
 defm : X86WriteRes<WriteFStoreNTY,     [JSAGU, JFPU1,  JSTC], 3, [2, 2, 2], 1>;
@@ -657,8 +657,8 @@ defm : X86WriteResUnsupported<WriteCvtPS2PHZSt>;
 ////////////////////////////////////////////////////////////////////////////////
 
 defm : X86WriteRes<WriteVecLoad,          [JLAGU, JFPU01, JVALU], 5, [1, 1, 1], 1>;
-defm : X86WriteRes<WriteVecLoadX,         [JLAGU, JFPU01, JVALU], 5, [1, 1, 1], 1>;
-defm : X86WriteRes<WriteVecLoadY,         [JLAGU, JFPU01, JVALU], 5, [1, 1, 1], 1>;
+defm : X86WriteRes<WriteVecLoadX,         [JLAGU], 5, [1], 1>;
+defm : X86WriteRes<WriteVecLoadY,         [JLAGU], 5, [2], 2>;
 defm : X86WriteRes<WriteVecLoadNT,        [JLAGU, JFPU01, JVALU], 5, [1, 1, 1], 1>;
 defm : X86WriteRes<WriteVecLoadNTY,       [JLAGU, JFPU01, JVALU], 5, [1, 1, 1], 1>;
 defm : X86WriteRes<WriteVecMaskedLoad,    [JLAGU, JFPU01, JVALU], 6, [1, 2, 2], 1>;
@@ -666,7 +666,7 @@ defm : X86WriteRes<WriteVecMaskedLoadY,   [JLAGU, JFPU01, JVALU], 6, [2, 4, 4],
 
 defm : X86WriteRes<WriteVecStore,         [JSAGU, JFPU1,   JSTC], 2, [1, 1, 1], 1>;
 defm : X86WriteRes<WriteVecStoreX,        [JSAGU, JFPU1,   JSTC], 1, [1, 1, 1], 1>;
-defm : X86WriteRes<WriteVecStoreY,        [JSAGU, JFPU1,   JSTC], 1, [1, 1, 1], 1>;
+defm : X86WriteRes<WriteVecStoreY,        [JSAGU, JFPU1,   JSTC], 1, [2, 2, 2], 2>;
 defm : X86WriteRes<WriteVecStoreNT,       [JSAGU, JFPU1,   JSTC], 2, [1, 1, 1], 1>;
 defm : X86WriteRes<WriteVecStoreNTY,      [JSAGU, JFPU1,   JSTC], 2, [2, 2, 2], 1>;
 defm : X86WriteRes<WriteVecMaskedStore,   [JSAGU, JFPU01, JVALU], 6, [1, 1, 4], 1>;