[X86][BtVer2] Teach how to identify zero-idio VPERM2F128rr instructions.

[andreadb]

Summary

This patch adds another variant class to identify zero-idiom VPERM2F128rr instructions.

On Jaguar, a VPERM wih bit 3 and 7 of the mask set, is a zero-idiom.

Please let me know if okay to commit.

Thanks,
Andrea

[mattd]

lib/Target/X86/X86ScheduleBtVer2.td

692 ↗

(On Diff #167514)

If I have read things correctly, 136 represents a bit mask, it might be clearer to represent that value as 0x88 or 0b10001000

[andreadb]

Addressed review comments.

Also, moved the predicate definition to X86SchedPredicates.td

[RKSimon]

LGTM - thanks

llvm/trunk/lib/Target/X86/X86SchedPredicates.td

 
 // A predicate used to identify dependency-breaking instructions that clear the
 // content of the destination register. Note that this predicate only checks if
 // input registers are the same. This predicate doesn't make any assumptions on
 // the expected instruction opcodes, because different processors may implement
 // different zero-idioms.
 def ZeroIdiomPredicate : CheckSameRegOperand<1, 2>;
 
+// A predicate used to identify VPERM that have bits 3 and 7 of their mask set.
+// On some processors, these VPERM instructions are zero-idioms.
+def ZeroIdiomVPERMPredicate : CheckAll<[
+  ZeroIdiomPredicate,
+  CheckImmOperand<3, 0x88>
+]>;
+
 // A predicate used to check if a LEA instruction uses all three source
 // operands: base, index, and offset.
 def IsThreeOperandsLEAPredicate: CheckAll<[
   // isRegOperand(Base)
   CheckIsRegOperand<1>,
   CheckNot<CheckInvalidRegOperand<1>>,
 
   // isRegOperand(Index)

llvm/trunk/lib/Target/X86/X86ScheduleBtVer2.td

def : InstRW<[JWriteVZeroIdiomALUX], (instrs PSUBBrr, VPSUBBrr,
                                              PSUBSWrr, VPSUBSWrr,
                                              PSUBUSBrr, VPSUBUSBrr,
                                              PSUBUSWrr, VPSUBUSWrr,
                                              PCMPGTBrr, VPCMPGTBrr,
                                              PCMPGTDrr, VPCMPGTDrr,
                                              PCMPGTQrr, VPCMPGTQrr,
                                              PCMPGTWrr, VPCMPGTWrr)>;
 
+def JWriteVPERM2F128 : SchedWriteVariant<[
+  SchedVar<MCSchedPredicate<ZeroIdiomVPERMPredicate>, [JWriteZeroIdiomYmm]>,
+  SchedVar<NoSchedPred,                               [WriteFShuffle256]>
+]>;
+def : InstRW<[JWriteVPERM2F128], (instrs VPERM2F128rr)>;
+
 // This write is used for slow LEA instructions.
 def JWrite3OpsLEA : SchedWriteRes<[JALU1, JSAGU]> {
   let Latency = 2;
 }
 
 // On Jaguar, a slow LEA is either a 3Ops LEA (base, index, offset), or an LEA
 // with a `Scale` value different than 1.
 def JSlowLEAPredicate : MCSchedPredicate<
DepBreakingClass<[
     // xmm int variants.
     VPXORrr, VPANDNrr,
     VPSUBBrr, VPSUBWrr, VPSUBDrr, VPSUBQrr,
     VPSUBSBrr, VPSUBSWrr, VPSUBUSBrr, VPSUBUSWrr,
     VPCMPGTBrr, VPCMPGTWrr, VPCMPGTDrr, VPCMPGTQrr,
 
     // ymm variants.
     VXORPSYrr, VXORPDYrr, VANDNPSYrr, VANDNPDYrr
-  ], ZeroIdiomPredicate>
+  ], ZeroIdiomPredicate>,
+
+  DepBreakingClass<[ VPERM2F128rr ], ZeroIdiomVPERMPredicate>
 ]>;
 
 def : IsDepBreakingFunction<[
   // GPR
   DepBreakingClass<[ SBB32rr, SBB64rr ], ZeroIdiomPredicate>,
   DepBreakingClass<[ CMP32rr, CMP64rr ], CheckSameRegOperand<0, 1> >,
 
   // MMX

llvm/trunk/test/tools/llvm-mca/X86/BtVer2/zero-idioms-avx-256.s

 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     3     1.0    1.0    0.0       vaddps %ymm0, %ymm1, %ymm2
 # CHECK-NEXT: 1.     3     1.0    1.0    1.0       vandnps  %ymm2, %ymm2, %ymm3
 
 # CHECK:      [4] Code Region - ZERO-IDIOM-5
 
 # CHECK:      Iterations:        100
 # CHECK-NEXT: Instructions:      200
-# CHECK-NEXT: Total Cycles:      403
+# CHECK-NEXT: Total Cycles:      205
 # CHECK-NEXT: Total uOps:        400
 
 # CHECK:      Dispatch Width:    2
-# CHECK-NEXT: uOps Per Cycle:    0.99
-# CHECK-NEXT: IPC:               0.50
+# CHECK-NEXT: uOps Per Cycle:    1.95
+# CHECK-NEXT: IPC:               0.98
 # CHECK-NEXT: Block RThroughput: 2.0
 
 # CHECK:      Instruction Info:
 # CHECK-NEXT: [1]: #uOps
 # CHECK-NEXT: [2]: Latency
 # CHECK-NEXT: [3]: RThroughput
 # CHECK-NEXT: [4]: MayLoad
 # CHECK-NEXT: [5]: MayStore
 # CHECK-NEXT: [6]: HasSideEffects (U)
 
 # CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
-# CHECK-NEXT:  2      1     1.00                        vperm2f128  $136, %ymm0, %ymm0, %ymm1
+# CHECK-NEXT:  2      1     0.50                        vperm2f128  $136, %ymm0, %ymm0, %ymm1
 # CHECK-NEXT:  2      3     2.00                        vaddps  %ymm1, %ymm1, %ymm0
 
 # CHECK:      Resources:
 # CHECK-NEXT: [0]   - JALU0
 # CHECK-NEXT: [1]   - JALU1
 # CHECK-NEXT: [2]   - JDiv
 # CHECK-NEXT: [3]   - JFPA
 # CHECK-NEXT: [4]   - JFPM
 # CHECK-NEXT: [5]   - JFPU0
 # CHECK-NEXT: [6]   - JFPU1
 # CHECK-NEXT: [7]   - JLAGU
 # CHECK-NEXT: [8]   - JMul
 # CHECK-NEXT: [9]   - JSAGU
 # CHECK-NEXT: [10]  - JSTC
 # CHECK-NEXT: [11]  - JVALU0
 # CHECK-NEXT: [12]  - JVALU1
 # CHECK-NEXT: [13]  - JVIMUL
 
 # CHECK:      Resource pressure per iteration:
 # CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]
-# CHECK-NEXT:  -      -      -     2.00   2.00   2.00   2.00    -      -      -      -      -      -      -
+# CHECK-NEXT:  -      -      -     2.00   1.00   2.00   1.00    -      -      -      -      -      -      -
 
 # CHECK:      Resource pressure by instruction:
 # CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]   Instructions:
-# CHECK-NEXT:  -      -      -      -     2.00    -     2.00    -      -      -      -      -      -      -     vperm2f128  $136, %ymm0, %ymm0, %ymm1
+# CHECK-NEXT:  -      -      -      -     1.00    -     1.00    -      -      -      -      -      -      -     vperm2f128  $136, %ymm0, %ymm0, %ymm1
 # CHECK-NEXT:  -      -      -     2.00    -     2.00    -      -      -      -      -      -      -      -     vaddps  %ymm1, %ymm1, %ymm0
 
 # CHECK:      Timeline view:
-# CHECK-NEXT:                     01234
+# CHECK-NEXT:                     0
 # CHECK-NEXT: Index     0123456789
 
-# CHECK:      [0,0]     DeER .    .   .   vperm2f128  $136, %ymm0, %ymm0, %ymm1
-# CHECK-NEXT: [0,1]     .DeeeER   .   .   vaddps  %ymm1, %ymm1, %ymm0
-# CHECK-NEXT: [1,0]     . D==eER  .   .   vperm2f128  $136, %ymm0, %ymm0, %ymm1
-# CHECK-NEXT: [1,1]     .  D==eeeER   .   vaddps  %ymm1, %ymm1, %ymm0
-# CHECK-NEXT: [2,0]     .   D====eER  .   vperm2f128  $136, %ymm0, %ymm0, %ymm1
-# CHECK-NEXT: [2,1]     .    D====eeeER   vaddps  %ymm1, %ymm1, %ymm0
+# CHECK:      [0,0]     DeER .    .   vperm2f128  $136, %ymm0, %ymm0, %ymm1
+# CHECK-NEXT: [0,1]     .DeeeER   .   vaddps  %ymm1, %ymm1, %ymm0
+# CHECK-NEXT: [1,0]     . DeE-R   .   vperm2f128  $136, %ymm0, %ymm0, %ymm1
+# CHECK-NEXT: [1,1]     .  DeeeER .   vaddps  %ymm1, %ymm1, %ymm0
+# CHECK-NEXT: [2,0]     .   DeE-R .   vperm2f128  $136, %ymm0, %ymm0, %ymm1
+# CHECK-NEXT: [2,1]     .    DeeeER   vaddps  %ymm1, %ymm1, %ymm0
 
 # CHECK:      Average Wait times (based on the timeline view):
 # CHECK-NEXT: [0]: Executions
 # CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
 # CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
 # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
 
 # CHECK:            [0]    [1]    [2]    [3]
-# CHECK-NEXT: 0.     3     3.0    0.3    0.0       vperm2f128 $136, %ymm0, %ymm0, %ymm1
-# CHECK-NEXT: 1.     3     3.0    0.0    0.0       vaddps %ymm1, %ymm1, %ymm0
+# CHECK-NEXT: 0.     3     1.0    1.0    0.7       vperm2f128 $136, %ymm0, %ymm0, %ymm1
+# CHECK-NEXT: 1.     3     1.0    0.0    0.0       vaddps %ymm1, %ymm1, %ymm0