[PowerPC] Implement vector unpack instructions #151004
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@llvm/pr-subscribers-mc @llvm/pr-subscribers-backend-powerpc Author: Lei Huang (lei137) ChangesImplement the set of vector uncompress instructions:
Full diff: https://github.com/llvm/llvm-project/pull/151004.diff 4 Files Affected:
diff --git a/llvm/lib/Target/PowerPC/PPCInstrFuture.td b/llvm/lib/Target/PowerPC/PPCInstrFuture.td
index 80fac18d5737f..8b1bdad0852e5 100644
--- a/llvm/lib/Target/PowerPC/PPCInstrFuture.td
+++ b/llvm/lib/Target/PowerPC/PPCInstrFuture.td
@@ -45,6 +45,67 @@ multiclass XOForm_RTAB5_L1r<bits<6> opcode, bits<9> xo, dag OOL, dag IOL,
}
}
+class VXForm_VRTB5<bits<11> xo, bits<5> R, dag OOL, dag IOL, string asmstr,
+ list<dag> pattern> : I<4, OOL, IOL, asmstr, NoItinerary> {
+ bits<5> VRT;
+ bits<5> VRB;
+
+ let Pattern = pattern;
+
+ let Inst{6 -10} = VRT;
+ let Inst{11 -15} = R;
+ let Inst{16 -20} = VRB;
+ let Inst{21 -31} = xo;
+}
+
+class VXForm_VRTB5_UIM2<bits<11> xo, bits<3> R, dag OOL, dag IOL, string asmstr,
+ list<dag> pattern>
+ : I<4, OOL, IOL, asmstr, NoItinerary> {
+ bits<5> VRT;
+ bits<5> VRB;
+ bits<2> UIM;
+
+ let Pattern = pattern;
+
+ let Inst{6 -10} = VRT;
+ let Inst{11 -13} = R;
+ let Inst{14 -15} = UIM;
+ let Inst{16 -20} = VRB;
+ let Inst{21 -31} = xo;
+}
+
+class VXForm_VRTB5_UIM1<bits<11> xo, bits<4> R, dag OOL, dag IOL, string asmstr,
+ list<dag> pattern>
+ : I<4, OOL, IOL, asmstr, NoItinerary> {
+ bits<5> VRT;
+ bits<5> VRB;
+ bits<1> UIM;
+
+ let Pattern = pattern;
+
+ let Inst{6 -10} = VRT;
+ let Inst{11 -14} = R;
+ let Inst{15} = UIM;
+ let Inst{16 -20} = VRB;
+ let Inst{21 -31} = xo;
+}
+
+class VXForm_VRTB5_UIM3<bits<11> xo, bits<2> R, dag OOL, dag IOL, string asmstr,
+ list<dag> pattern>
+ : I<4, OOL, IOL, asmstr, NoItinerary> {
+ bits<5> VRT;
+ bits<5> VRB;
+ bits<3> UIM;
+
+ let Pattern = pattern;
+
+ let Inst{6 -10} = VRT;
+ let Inst{11 -12} = R;
+ let Inst{13 -15} = UIM;
+ let Inst{16 -20} = VRB;
+ let Inst{21 -31} = xo;
+}
+
let Predicates = [IsISAFuture] in {
defm SUBFUS : XOForm_RTAB5_L1r<31, 72, (outs g8rc:$RT),
(ins g8rc:$RA, g8rc:$RB, u1imm:$L),
@@ -81,4 +142,21 @@ let Predicates = [HasVSX, IsISAFuture] in {
(ins vsrprc:$XTp, memr:$RA, g8rc:$RB),
"stxvprll $XTp, $RA, $RB", IIC_LdStLFD, []>;
}
+
+ def VUPKHSNTOB : VXForm_VRTB5<387, 0, (outs vrrc:$VRT), (ins vrrc:$VRB),
+ "vupkhsntob $VRT, $VRB", []>;
+ def VUPKLSNTOB : VXForm_VRTB5<387, 1, (outs vrrc:$VRT), (ins vrrc:$VRB),
+ "vupklsntob $VRT, $VRB", []>;
+ def VUPKINT4TOBF16
+ : VXForm_VRTB5_UIM2<387, 2, (outs vrrc:$VRT), (ins vrrc:$VRB, u2imm:$UIM),
+ "vupkint4tobf16 $VRT, $VRB, $UIM", []>;
+ def VUPKINT8TOBF16
+ : VXForm_VRTB5_UIM1<387, 1, (outs vrrc:$VRT), (ins vrrc:$VRB, u1imm:$UIM),
+ "vupkint8tobf16 $VRT, $VRB, $UIM", []>;
+ def VUPKINT8TOFP32
+ : VXForm_VRTB5_UIM2<387, 3, (outs vrrc:$VRT), (ins vrrc:$VRB, u2imm:$UIM),
+ "vupkint8tofp32 $VRT, $VRB, $UIM", []>;
+ def VUPKINT4TOFP32
+ : VXForm_VRTB5_UIM3<387, 2, (outs vrrc:$VRT), (ins vrrc:$VRB, u3imm:$UIM),
+ "vupkint4tofp32 $VRT, $VRB, $UIM", []>;
}
diff --git a/llvm/test/MC/Disassembler/PowerPC/ppc-encoding-ISAFuture.txt b/llvm/test/MC/Disassembler/PowerPC/ppc-encoding-ISAFuture.txt
index 4bea42243f83b..6adaa5cfdaefc 100644
--- a/llvm/test/MC/Disassembler/PowerPC/ppc-encoding-ISAFuture.txt
+++ b/llvm/test/MC/Disassembler/PowerPC/ppc-encoding-ISAFuture.txt
@@ -195,3 +195,21 @@
#CHECK: dmxxsha224256pad 0, 1
0xf0,0x18,0x0e,0x94
+
+#CHECK: vupkhsntob 2, 4
+0x10,0x40,0x21,0x83
+
+#CHECK: vupklsntob 2, 4
+0x10,0x41,0x21,0x83
+
+#CHECK: vupkint4tobf16 2, 4, 3
+0x10,0x4b,0x21,0x83
+
+#CHECK: vupkint8tobf16 1, 3, 1
+0x10,0x23,0x19,0x83
+
+#CHECK: vupkint4tofp32 3, 5, 2
+0x10,0x72,0x29,0x83
+
+#CHECK: vupkint8tofp32 3, 5, 2
+0x10,0x6e,0x29,0x83
diff --git a/llvm/test/MC/Disassembler/PowerPC/ppc64le-encoding-ISAFuture.txt b/llvm/test/MC/Disassembler/PowerPC/ppc64le-encoding-ISAFuture.txt
index 233693e67292e..84f9bc8e67b60 100644
--- a/llvm/test/MC/Disassembler/PowerPC/ppc64le-encoding-ISAFuture.txt
+++ b/llvm/test/MC/Disassembler/PowerPC/ppc64le-encoding-ISAFuture.txt
@@ -189,3 +189,21 @@
#CHECK: dmxxsha224256pad 0, 1
0x94,0x0e,0x18,0xf0
+
+#CHECK: vupkhsntob 2, 4
+0x83,0x21,0x40,0x10
+
+#CHECK: vupklsntob 2, 4
+0x83,0x21,0x41,0x10
+
+#CHECK: vupkint4tobf16 2, 4, 3
+0x83,0x21,0x4b,0x10
+
+#CHECK: vupkint8tobf16 1, 3, 1
+0x83,0x19,0x23,0x10
+
+#CHECK: vupkint4tofp32 3, 5, 2
+0x83,0x29,0x72,0x10
+
+#CHECK: vupkint8tofp32 3, 5, 2
+0x83,0x29,0x6e,0x10
diff --git a/llvm/test/MC/PowerPC/ppc-encoding-ISAFuture.s b/llvm/test/MC/PowerPC/ppc-encoding-ISAFuture.s
index cba93291e4595..8316bbd9854ea 100644
--- a/llvm/test/MC/PowerPC/ppc-encoding-ISAFuture.s
+++ b/llvm/test/MC/PowerPC/ppc-encoding-ISAFuture.s
@@ -282,3 +282,27 @@
dmxxsha224256pad 0, 1
#CHECK-BE: dmxxsha224256pad 0, 1 # encoding: [0xf0,0x18,0x0e,0x94]
#CHECK-LE: dmxxsha224256pad 0, 1 # encoding: [0x94,0x0e,0x18,0xf0]
+
+ vupkhsntob 2, 4
+#CHECK-BE: vupkhsntob 2, 4 # encoding: [0x10,0x40,0x21,0x83]
+#CHECK-LE: vupkhsntob 2, 4 # encoding: [0x83,0x21,0x40,0x10]
+
+ vupklsntob 2, 4
+#CHECK-BE: vupklsntob 2, 4 # encoding: [0x10,0x41,0x21,0x83]
+#CHECK-LE: vupklsntob 2, 4 # encoding: [0x83,0x21,0x41,0x10]
+
+ vupkint4tobf16 2, 4, 3
+#CHECK-BE: vupkint4tobf16 2, 4, 3 # encoding: [0x10,0x4b,0x21,0x83]
+#CHECK-LE: vupkint4tobf16 2, 4, 3 # encoding: [0x83,0x21,0x4b,0x10]
+
+ vupkint8tobf16 1, 3, 1
+#CHECK-BE: vupkint8tobf16 1, 3, 1 # encoding: [0x10,0x23,0x19,0x83]
+#CHECK-LE: vupkint8tobf16 1, 3, 1 # encoding: [0x83,0x19,0x23,0x10]
+
+ vupkint4tofp32 3, 5, 2
+#CHECK-BE: vupkint4tofp32 3, 5, 2 # encoding: [0x10,0x72,0x29,0x83]
+#CHECK-LE: vupkint4tofp32 3, 5, 2 # encoding: [0x83,0x29,0x72,0x10]
+
+ vupkint8tofp32 3, 5, 2
+#CHECK-BE: vupkint8tofp32 3, 5, 2 # encoding: [0x10,0x6e,0x29,0x83]
+#CHECK-LE: vupkint8tofp32 3, 5, 2 # encoding: [0x83,0x29,0x6e,0x10]
|
diggerlin
reviewed
Jul 29, 2025
diggerlin
reviewed
Jul 29, 2025
| let Inst{16 -20} = VRB; | ||
| let Inst{21 -31} = xo; | ||
| } | ||
|
|
There was a problem hiding this comment.
not sure whether to a base class for above 4 class is a good idea or not ?
since there has same
bits<5> VRT;
bits<5> VRB;
let Inst{6 -10} = VRT;
let Inst{16 -20} = VRB;
let Inst{21 -31} = xo;
and
I<4, OOL, IOL, asmstr, NoItinerary>
There was a problem hiding this comment.
My preference is to keep them separate as the middle bits {11-16} are different combinations of fields for all of them.
b826d20 to
a42903b
Compare
Implement the set of vector uncompress instructions: * vupkhsntob * vupklsntob * vupkint4tobf16 * vupkint8tobf16 * vupkint4tofp32 * vupkint8tofp32
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Implement the set of vector uncompress instructions: