summaryrefslogtreecommitdiffstats
path: root/llvm/lib
diff options
context:
space:
mode:
authorCraig Topper <craig.topper@gmail.com>2017-02-20 02:47:42 +0000
committerCraig Topper <craig.topper@gmail.com>2017-02-20 02:47:42 +0000
commit5b4e36aafaa171849c4737a6faa693de02b718ab (patch)
tree10111b33c9ca2b102417b9a45df39fa98a4ffffe /llvm/lib
parent528d874583d1882df21389354031558580f6e52f (diff)
downloadbcm5719-llvm-5b4e36aafaa171849c4737a6faa693de02b718ab.tar.gz
bcm5719-llvm-5b4e36aafaa171849c4737a6faa693de02b718ab.zip
[AVX-512] Add more VPTERNLOG patterns to enable folding of broadcast loads that aren't in operand 2.
llvm-svn: 295634
Diffstat (limited to 'llvm/lib')
-rw-r--r--llvm/lib/Target/X86/X86InstrAVX512.td39
1 files changed, 39 insertions, 0 deletions
diff --git a/llvm/lib/Target/X86/X86InstrAVX512.td b/llvm/lib/Target/X86/X86InstrAVX512.td
index 3c62d16d42e..484ace999ce 100644
--- a/llvm/lib/Target/X86/X86InstrAVX512.td
+++ b/llvm/lib/Target/X86/X86InstrAVX512.td
@@ -8992,6 +8992,45 @@ multiclass avx512_ternlog<bits<8> opc, string OpcodeStr, SDNode OpNode,
_.RC:$src1)),
(!cast<Instruction>(NAME#_.ZSuffix#rmik) _.RC:$src1, _.KRCWM:$mask,
_.RC:$src2, addr:$src3, (VPTERNLOG132_imm8 imm:$src4))>;
+
+ // Additional patterns for matching broadcasts in other positions.
+ def : Pat<(_.VT (OpNode (X86VBroadcast (_.ScalarLdFrag addr:$src3)),
+ _.RC:$src2, _.RC:$src1, (i8 imm:$src4))),
+ (!cast<Instruction>(NAME#_.ZSuffix#rmbi) _.RC:$src1, _.RC:$src2,
+ addr:$src3, (VPTERNLOG321_imm8 imm:$src4))>;
+ def : Pat<(_.VT (OpNode _.RC:$src1,
+ (X86VBroadcast (_.ScalarLdFrag addr:$src3)),
+ _.RC:$src2, (i8 imm:$src4))),
+ (!cast<Instruction>(NAME#_.ZSuffix#rmbi) _.RC:$src1, _.RC:$src2,
+ addr:$src3, (VPTERNLOG132_imm8 imm:$src4))>;
+
+ // Additional patterns for matching zero masking with broadcasts in other
+ // positions.
+ def : Pat<(_.VT (vselect _.KRCWM:$mask,
+ (OpNode (X86VBroadcast (_.ScalarLdFrag addr:$src3)),
+ _.RC:$src2, _.RC:$src1, (i8 imm:$src4)),
+ _.ImmAllZerosV)),
+ (!cast<Instruction>(NAME#_.ZSuffix#rmbikz) _.RC:$src1,
+ _.KRCWM:$mask, _.RC:$src2, addr:$src3,
+ (VPTERNLOG321_imm8 imm:$src4))>;
+ def : Pat<(_.VT (vselect _.KRCWM:$mask,
+ (OpNode _.RC:$src1,
+ (X86VBroadcast (_.ScalarLdFrag addr:$src3)),
+ _.RC:$src2, (i8 imm:$src4)),
+ _.ImmAllZerosV)),
+ (!cast<Instruction>(NAME#_.ZSuffix#rmbikz) _.RC:$src1,
+ _.KRCWM:$mask, _.RC:$src2, addr:$src3,
+ (VPTERNLOG132_imm8 imm:$src4))>;
+
+ // Additional patterns for matching masked broadcasts with different
+ // operand orders.
+ def : Pat<(_.VT (vselect _.KRCWM:$mask,
+ (OpNode _.RC:$src1,
+ (X86VBroadcast (_.ScalarLdFrag addr:$src3)),
+ _.RC:$src2, (i8 imm:$src4)),
+ _.RC:$src1)),
+ (!cast<Instruction>(NAME#_.ZSuffix#rmbik) _.RC:$src1, _.KRCWM:$mask,
+ _.RC:$src2, addr:$src3, (VPTERNLOG132_imm8 imm:$src4))>;
}
multiclass avx512_common_ternlog<string OpcodeStr, AVX512VLVectorVTInfo _>{
OpenPOWER on IntegriCloud