[llvm] [PowerPC10][XXEVAL] Exploit xxeval instruction for cases of the ternary(A,X, and(B,C)), ternary(A,X,B), ternary(A,X,C), ternary(A,X,xor(B,C)) forms. (PR #141733)
Tony Varghese via llvm-commits
llvm-commits at lists.llvm.org
Wed Jun 11 01:45:06 PDT 2025
- Previous message: [llvm] [PowerPC10][XXEVAL] Exploit xxeval instruction for cases of the ternary(A,X, and(B,C)), ternary(A,X,B), ternary(A,X,C), ternary(A,X,xor(B,C)) forms. (PR #141733)
- Next message: [llvm] [PowerPC10][XXEVAL] Exploit xxeval instruction for cases of the ternary(A,X, and(B,C)), ternary(A,X,B), ternary(A,X,C), ternary(A,X,xor(B,C)) forms. (PR #141733)
- Messages sorted by:
[ date ]
[ thread ]
[ subject ]
[ author ]
https://github.com/tonykuttai updated https://github.com/llvm/llvm-project/pull/141733
>From f20275c8d2fca4ddcaa504f3a9381a05197a1751 Mon Sep 17 00:00:00 2001
From: Tony Varghese <tony.varghese at ibm.com>
Date: Thu, 29 May 2025 16:33:21 +0000
Subject: [PATCH] [PowerPC10][XXEVAL] Exploit xxeval instruction for cases of
the ternary(A,X, and(B,C)), ternary(A,X,B), ternary(A,X,C),
ternary(A,X,xor(B,C)) forms.
---
llvm/lib/Target/PowerPC/PPCInstrP10.td | 200 +++++++++++++++---
.../CodeGen/PowerPC/xxeval-vselect-x-and.ll | 42 +---
.../CodeGen/PowerPC/xxeval-vselect-x-b.ll | 32 +--
.../CodeGen/PowerPC/xxeval-vselect-x-c.ll | 26 +--
.../CodeGen/PowerPC/xxeval-vselect-x-xor.ll | 38 +---
5 files changed, 210 insertions(+), 128 deletions(-)
diff --git a/llvm/lib/Target/PowerPC/PPCInstrP10.td b/llvm/lib/Target/PowerPC/PPCInstrP10.td
index a7f758745efe2..9c5e34a45b9b5 100644
--- a/llvm/lib/Target/PowerPC/PPCInstrP10.td
+++ b/llvm/lib/Target/PowerPC/PPCInstrP10.td
@@ -2159,8 +2159,131 @@ let AddedComplexity = 400, Predicates = [IsISA3_1, HasVSX] in {
(COPY_TO_REGCLASS $VRB, VSRC), 2)))>;
}
-class xxevalPattern <dag pattern, bits<8> imm> :
- Pat<(v4i32 pattern), (XXEVAL $vA, $vB, $vC, imm)> {}
+class xxevalPattern <ValueType vt, dag pattern, bits<8> imm> :
+ Pat<(vt pattern), (XXEVAL $vA, $vB, $vC, imm)> {}
+
+class DagCondVNot<dag d, bit negate> {
+ // Utility to define a vnot around the dag.
+ dag res = !if(!ne(negate, 0),
+ (vnot d),
+ d);
+}
+
+class XXEvalUnaryPattern<ValueType vt> {
+ // vnot Operand B
+ dag vnotB = !cond(
+ !eq(vt, v4i32) : (vnot v4i32:$vB),
+ !eq(vt, v2i64) : (v2i64 (bitconvert (vnot (v4i32 (bitconvert v2i64:$vB)))))
+ );
+ // vnot Operand C
+ dag vnotC = !cond(
+ !eq(vt, v4i32) : (vnot v4i32:$vC),
+ !eq(vt, v2i64) : (v2i64 (bitconvert (vnot (v4i32 (bitconvert v2i64:$vC)))))
+ );
+}
+
+class XXEvalBinaryPattern<ValueType vt, SDPatternOperator op, bit notResult = 0> {
+ // Defines a wrapper class for binary patterns with optional NOT on result.
+ // Generate op pattern with optional NOT wrapping for result depending on "notResult".
+ dag opPat = !cond(
+ !eq(vt, v4i32) : DagCondVNot<(op v4i32:$vB, v4i32:$vC), notResult>.res,
+ !eq(vt, v2i64) : (v2i64 (bitconvert DagCondVNot<(op
+ (v4i32 (bitconvert v2i64:$vB)),
+ (v4i32 (bitconvert v2i64:$vC))), notResult>.res))
+ );
+}
+
+multiclass XXEvalVSelectWithXAnd<ValueType vt, bits<8> baseImm> {
+ // Multiclass for Ternary(A, X, and(B, C)) style patterns.
+ // Ternary(A, xor(B,C), and(B,C)) => imm: baseImm
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalBinaryPattern<vt, xor>.opPat, XXEvalBinaryPattern<vt, and>.opPat),
+ baseImm>;
+ // Ternary(A, nor(B,C), and(B,C)) => imm: baseImm + 2
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalBinaryPattern<vt, or, 1>.opPat, XXEvalBinaryPattern<vt, and>.opPat),
+ !add(baseImm, 2)>;
+ // Ternary(A, eqv(B,C), and(B,C)) => imm: baseImm + 3
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalBinaryPattern<vt, xor, 1>.opPat, XXEvalBinaryPattern<vt, and>.opPat),
+ !add(baseImm, 3)>;
+ // Ternary(A, not(C), and(B,C)) => imm: baseImm + 4
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalUnaryPattern<vt>.vnotC, XXEvalBinaryPattern<vt, and>.opPat),
+ !add(baseImm, 4)>;
+ // Ternary(A, not(B), and(B,C)) => imm: baseImm + 6
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalUnaryPattern<vt>.vnotB, XXEvalBinaryPattern<vt, and>.opPat),
+ !add(baseImm, 6)>;
+}
+
+multiclass XXEvalVSelectWithXB<ValueType vt, bits<8> baseImm>{
+ // Multiclass for Ternary(A, X, B) style patterns
+ // Ternary(A, and(B,C), B) => imm: baseImm
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalBinaryPattern<vt, and>.opPat, vt:$vB),
+ baseImm>;
+ // Ternary(A, nor(B,C), B) => imm: baseImm + 7
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalBinaryPattern<vt, or, 1>.opPat, vt:$vB),
+ !add(baseImm, 7)>;
+ // Ternary(A, eqv(B,C), B) => imm: baseImm + 8
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalBinaryPattern<vt, xor, 1>.opPat, vt:$vB),
+ !add(baseImm, 8)>;
+ // Ternary(A, not(C), B) => imm: baseImm + 9
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalUnaryPattern<vt>.vnotC, vt:$vB),
+ !add(baseImm, 9)>;
+ // Ternary(A, nand(B,C), B) => imm: baseImm + 13
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalBinaryPattern<vt, and, 1>.opPat, vt:$vB),
+ !add(baseImm, 13)>;
+}
+
+multiclass XXEvalVSelectWithXC<ValueType vt, bits<8> baseImm>{
+ // Multiclass for Ternary(A, X, C) style patterns
+ // Ternary(A, and(B,C), C) => imm: baseImm
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalBinaryPattern<vt, and>.opPat, vt:$vC),
+ baseImm>;
+ // Ternary(A, nor(B,C), C) => imm: baseImm + 7
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalBinaryPattern<vt, or, 1>.opPat, vt:$vC),
+ !add(baseImm, 7)>;
+ // Ternary(A, eqv(B,C), C) => imm: baseImm + 8
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalBinaryPattern<vt, xor, 1>.opPat, vt:$vC),
+ !add(baseImm, 8)>;
+ // Ternary(A, nand(B,C), C) => imm: baseImm + 13
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalBinaryPattern<vt, and, 1>.opPat, vt:$vC),
+ !add(baseImm, 13)>;
+}
+
+multiclass XXEvalVSelectWithXXor<ValueType vt, bits<8> baseImm>{
+ // Multiclass for Ternary(A, X, xor(B,C)) style patterns
+ // Ternary(A, and(B,C), xor(B,C)) => imm: baseImm
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalBinaryPattern<vt, and>.opPat, XXEvalBinaryPattern<vt, xor>.opPat),
+ baseImm>;
+ // Ternary(A, B, xor(B,C)) => imm: baseImm + 2
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, vt:$vB, XXEvalBinaryPattern<vt, xor>.opPat),
+ !add(baseImm, 2)>;
+ // Ternary(A, C, xor(B,C)) => imm: baseImm + 4
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, vt:$vC, XXEvalBinaryPattern<vt, xor>.opPat),
+ !add(baseImm, 4)>;
+ // Ternary(A, or(B,C), xor(B,C)) => imm: baseImm + 6
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalBinaryPattern<vt, or>.opPat, XXEvalBinaryPattern<vt, xor>.opPat),
+ !add(baseImm, 6)>;
+ // Ternary(A, nor(B,C), xor(B,C)) => imm: baseImm + 7
+ def : xxevalPattern<vt,
+ (vselect vt:$vA, XXEvalBinaryPattern<vt, or, 1>.opPat, XXEvalBinaryPattern<vt, xor>.opPat),
+ !add(baseImm, 7)>;
+}
let Predicates = [PrefixInstrs, HasP10Vector] in {
let AddedComplexity = 400 in {
@@ -2192,83 +2315,96 @@ let Predicates = [PrefixInstrs, HasP10Vector] in {
// Anonymous patterns for XXEVAL
// AND
// and(A, B, C)
- def : xxevalPattern<(and v4i32:$vA, (and v4i32:$vB, v4i32:$vC)), 1>;
+ def : xxevalPattern<v4i32, (and v4i32:$vA, (and v4i32:$vB, v4i32:$vC)), 1>;
// and(A, xor(B, C))
- def : xxevalPattern<(and v4i32:$vA, (xor v4i32:$vB, v4i32:$vC)), 6>;
+ def : xxevalPattern<v4i32, (and v4i32:$vA, (xor v4i32:$vB, v4i32:$vC)), 6>;
// and(A, or(B, C))
- def : xxevalPattern<(and v4i32:$vA, (or v4i32:$vB, v4i32:$vC)), 7>;
+ def : xxevalPattern<v4i32, (and v4i32:$vA, (or v4i32:$vB, v4i32:$vC)), 7>;
// and(A, nor(B, C))
- def : xxevalPattern<(and v4i32:$vA, (vnot (or v4i32:$vB, v4i32:$vC))), 8>;
+ def : xxevalPattern<v4i32, (and v4i32:$vA, (vnot (or v4i32:$vB, v4i32:$vC))), 8>;
// and(A, eqv(B, C))
- def : xxevalPattern<(and v4i32:$vA, (vnot (xor v4i32:$vB, v4i32:$vC))), 9>;
+ def : xxevalPattern<v4i32, (and v4i32:$vA, (vnot (xor v4i32:$vB, v4i32:$vC))), 9>;
// and(A, nand(B, C))
- def : xxevalPattern<(and v4i32:$vA, (vnot (and v4i32:$vB, v4i32:$vC))), 14>;
+ def : xxevalPattern<v4i32, (and v4i32:$vA, (vnot (and v4i32:$vB, v4i32:$vC))), 14>;
// NAND
// nand(A, B, C)
- def : xxevalPattern<(vnot (and v4i32:$vA, (and v4i32:$vB, v4i32:$vC))),
+ def : xxevalPattern<v4i32, (vnot (and v4i32:$vA, (and v4i32:$vB, v4i32:$vC))),
!sub(255, 1)>;
// nand(A, xor(B, C))
- def : xxevalPattern<(vnot (and v4i32:$vA, (xor v4i32:$vB, v4i32:$vC))),
+ def : xxevalPattern<v4i32, (vnot (and v4i32:$vA, (xor v4i32:$vB, v4i32:$vC))),
!sub(255, 6)>;
// nand(A, or(B, C))
- def : xxevalPattern<(vnot (and v4i32:$vA, (or v4i32:$vB, v4i32:$vC))),
+ def : xxevalPattern<v4i32, (vnot (and v4i32:$vA, (or v4i32:$vB, v4i32:$vC))),
!sub(255, 7)>;
// nand(A, nor(B, C))
- def : xxevalPattern<(or (vnot v4i32:$vA), (or v4i32:$vB, v4i32:$vC)),
+ def : xxevalPattern<v4i32, (or (vnot v4i32:$vA), (or v4i32:$vB, v4i32:$vC)),
!sub(255, 8)>;
// nand(A, eqv(B, C))
- def : xxevalPattern<(or (vnot v4i32:$vA), (xor v4i32:$vB, v4i32:$vC)),
+ def : xxevalPattern<v4i32, (or (vnot v4i32:$vA), (xor v4i32:$vB, v4i32:$vC)),
!sub(255, 9)>;
// nand(A, nand(B, C))
- def : xxevalPattern<(or (vnot v4i32:$vA), (and v4i32:$vB, v4i32:$vC)),
+ def : xxevalPattern<v4i32, (or (vnot v4i32:$vA), (and v4i32:$vB, v4i32:$vC)),
!sub(255, 14)>;
// EQV
// (eqv A, B, C)
- def : xxevalPattern<(or (and v4i32:$vA, (and v4i32:$vB, v4i32:$vC)),
+ def : xxevalPattern<v4i32, (or (and v4i32:$vA, (and v4i32:$vB, v4i32:$vC)),
(vnot (or v4i32:$vA, (or v4i32:$vB, v4i32:$vC)))),
150>;
// (eqv A, (and B, C))
- def : xxevalPattern<(vnot (xor v4i32:$vA, (and v4i32:$vB, v4i32:$vC))), 225>;
+ def : xxevalPattern<v4i32, (vnot (xor v4i32:$vA, (and v4i32:$vB, v4i32:$vC))), 225>;
// (eqv A, (or B, C))
- def : xxevalPattern<(vnot (xor v4i32:$vA, (or v4i32:$vB, v4i32:$vC))), 135>;
+ def : xxevalPattern<v4i32, (vnot (xor v4i32:$vA, (or v4i32:$vB, v4i32:$vC))), 135>;
// NOR
// (nor A, B, C)
- def : xxevalPattern<(vnot (or v4i32:$vA, (or v4i32:$vB, v4i32:$vC))), 128>;
+ def : xxevalPattern<v4i32, (vnot (or v4i32:$vA, (or v4i32:$vB, v4i32:$vC))), 128>;
// (nor A, (and B, C))
- def : xxevalPattern<(vnot (or v4i32:$vA, (and v4i32:$vB, v4i32:$vC))), 224>;
+ def : xxevalPattern<v4i32, (vnot (or v4i32:$vA, (and v4i32:$vB, v4i32:$vC))), 224>;
// (nor A, (eqv B, C))
- def : xxevalPattern<(and (vnot v4i32:$vA), (xor v4i32:$vB, v4i32:$vC)), 96>;
+ def : xxevalPattern<v4i32, (and (vnot v4i32:$vA), (xor v4i32:$vB, v4i32:$vC)), 96>;
// (nor A, (nand B, C))
- def : xxevalPattern<(and (vnot v4i32:$vA), (and v4i32:$vB, v4i32:$vC)), 16>;
+ def : xxevalPattern<v4i32, (and (vnot v4i32:$vA), (and v4i32:$vB, v4i32:$vC)), 16>;
// (nor A, (nor B, C))
- def : xxevalPattern<(and (vnot v4i32:$vA), (or v4i32:$vB, v4i32:$vC)), 112>;
+ def : xxevalPattern<v4i32, (and (vnot v4i32:$vA), (or v4i32:$vB, v4i32:$vC)), 112>;
// (nor A, (xor B, C))
- def : xxevalPattern<(vnot (or v4i32:$vA, (xor v4i32:$vB, v4i32:$vC))), 144>;
+ def : xxevalPattern<v4i32, (vnot (or v4i32:$vA, (xor v4i32:$vB, v4i32:$vC))), 144>;
// OR
// (or A, B, C)
- def : xxevalPattern<(or v4i32:$vA, (or v4i32:$vB, v4i32:$vC)), 127>;
+ def : xxevalPattern<v4i32, (or v4i32:$vA, (or v4i32:$vB, v4i32:$vC)), 127>;
// (or A, (and B, C))
- def : xxevalPattern<(or v4i32:$vA, (and v4i32:$vB, v4i32:$vC)), 31>;
+ def : xxevalPattern<v4i32, (or v4i32:$vA, (and v4i32:$vB, v4i32:$vC)), 31>;
// (or A, (eqv B, C))
- def : xxevalPattern<(or v4i32:$vA, (vnot (xor v4i32:$vB, v4i32:$vC))), 159>;
+ def : xxevalPattern<v4i32, (or v4i32:$vA, (vnot (xor v4i32:$vB, v4i32:$vC))), 159>;
// (or A, (nand B, C))
- def : xxevalPattern<(or v4i32:$vA, (vnot (and v4i32:$vB, v4i32:$vC))), 239>;
+ def : xxevalPattern<v4i32, (or v4i32:$vA, (vnot (and v4i32:$vB, v4i32:$vC))), 239>;
// (or A, (nor B, C))
- def : xxevalPattern<(or v4i32:$vA, (vnot (or v4i32:$vB, v4i32:$vC))), 143>;
+ def : xxevalPattern<v4i32, (or v4i32:$vA, (vnot (or v4i32:$vB, v4i32:$vC))), 143>;
// (or A, (xor B, C))
- def : xxevalPattern<(or v4i32:$vA, (xor v4i32:$vB, v4i32:$vC)), 111>;
+ def : xxevalPattern<v4i32, (or v4i32:$vA, (xor v4i32:$vB, v4i32:$vC)), 111>;
// XOR
// (xor A, B, C)
- def : xxevalPattern<(xor v4i32:$vA, (xor v4i32:$vB, v4i32:$vC)), 105>;
+ def : xxevalPattern<v4i32, (xor v4i32:$vA, (xor v4i32:$vB, v4i32:$vC)), 105>;
// (xor A, (and B, C))
- def : xxevalPattern<(xor v4i32:$vA, (and v4i32:$vB, v4i32:$vC)), 30>;
+ def : xxevalPattern<v4i32, (xor v4i32:$vA, (and v4i32:$vB, v4i32:$vC)), 30>;
// (xor A, (or B, C))
- def : xxevalPattern<(xor v4i32:$vA, (or v4i32:$vB, v4i32:$vC)), 120>;
+ def : xxevalPattern<v4i32, (xor v4i32:$vA, (or v4i32:$vB, v4i32:$vC)), 120>;
+
+ // Utilize xxeval instruction for ternary vector expressions.
+ defm : XXEvalVSelectWithXAnd<v4i32, 22>;
+ defm : XXEvalVSelectWithXAnd<v2i64, 22>;
+
+ defm : XXEvalVSelectWithXB<v4i32, 49>;
+ defm : XXEvalVSelectWithXB<v2i64, 49>;
+
+ defm : XXEvalVSelectWithXC<v4i32, 81>;
+ defm : XXEvalVSelectWithXC<v2i64, 81>;
+
+ defm : XXEvalVSelectWithXXor<v4i32, 97>;
+ defm : XXEvalVSelectWithXXor<v2i64, 97>;
// Anonymous patterns to select prefixed VSX loads and stores.
// Load / Store f128
diff --git a/llvm/test/CodeGen/PowerPC/xxeval-vselect-x-and.ll b/llvm/test/CodeGen/PowerPC/xxeval-vselect-x-and.ll
index 2868669c52ce6..19305336f78df 100644
--- a/llvm/test/CodeGen/PowerPC/xxeval-vselect-x-and.ll
+++ b/llvm/test/CodeGen/PowerPC/xxeval-vselect-x-and.ll
@@ -1,5 +1,5 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; Test file to verify the emission of Vector selection instructions when ternary operators are used.
+; Test file to verify the emission of Vector Evaluate instructions when ternary operators are used.
; RUN: llc -verify-machineinstrs -mcpu=pwr10 -mtriple=powerpc64le-unknown-unknown \
; RUN: -ppc-asm-full-reg-names --ppc-vsr-nums-as-vr < %s | FileCheck %s
@@ -15,11 +15,9 @@ define <4 x i32> @ternary_A_xor_BC_and_BC_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i
; CHECK-LABEL: ternary_A_xor_BC_and_BC_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxlxor vs0, v3, v4
-; CHECK-NEXT: xxland vs1, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs1, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 22
; CHECK-NEXT: blr
entry:
%xor = xor <4 x i32> %B, %C
@@ -33,12 +31,10 @@ define <2 x i64> @ternary_A_xor_BC_and_BC_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i
; CHECK-LABEL: ternary_A_xor_BC_and_BC_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxlxor vs0, v3, v4
-; CHECK-NEXT: xxland vs1, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs1, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 22
; CHECK-NEXT: blr
entry:
%xor = xor <2 x i64> %B, %C
@@ -52,11 +48,9 @@ define <4 x i32> @ternary_A_nor_BC_and_BC_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i
; CHECK-LABEL: ternary_A_nor_BC_and_BC_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxlnor vs0, v3, v4
-; CHECK-NEXT: xxland vs1, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs1, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 24
; CHECK-NEXT: blr
entry:
%or = or <4 x i32> %B, %C
@@ -71,12 +65,10 @@ define <2 x i64> @ternary_A_nor_BC_and_BC_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i
; CHECK-LABEL: ternary_A_nor_BC_and_BC_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxlnor vs0, v3, v4
-; CHECK-NEXT: xxland vs1, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs1, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 24
; CHECK-NEXT: blr
entry:
%or = or <2 x i64> %B, %C
@@ -91,11 +83,9 @@ define <4 x i32> @ternary_A_eqv_BC_and_BC_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i
; CHECK-LABEL: ternary_A_eqv_BC_and_BC_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxleqv vs0, v3, v4
-; CHECK-NEXT: xxland vs1, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs1, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 25
; CHECK-NEXT: blr
entry:
%xor = xor <4 x i32> %B, %C
@@ -110,12 +100,10 @@ define <2 x i64> @ternary_A_eqv_BC_and_BC_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i
; CHECK-LABEL: ternary_A_eqv_BC_and_BC_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxleqv vs0, v3, v4
-; CHECK-NEXT: xxland vs1, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs1, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 25
; CHECK-NEXT: blr
entry:
%xor = xor <2 x i64> %B, %C
@@ -130,11 +118,9 @@ define <4 x i32> @ternary_A_not_C_and_BC_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i3
; CHECK-LABEL: ternary_A_not_C_and_BC_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxlnor vs0, v4, v4
-; CHECK-NEXT: xxland vs1, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs1, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 26
; CHECK-NEXT: blr
entry:
%not = xor <4 x i32> %C, <i32 -1, i32 -1, i32 -1, i32 -1> ; Vector not operation
@@ -148,12 +134,10 @@ define <2 x i64> @ternary_A_not_C_and_BC_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i6
; CHECK-LABEL: ternary_A_not_C_and_BC_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxlnor vs0, v4, v4
-; CHECK-NEXT: xxland vs1, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs1, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 26
; CHECK-NEXT: blr
entry:
%not = xor <2 x i64> %C, <i64 -1, i64 -1> ; Vector not operation
@@ -167,11 +151,9 @@ define <4 x i32> @ternary_A_not_B_and_BC_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i3
; CHECK-LABEL: ternary_A_not_B_and_BC_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxlnor vs0, v3, v3
-; CHECK-NEXT: xxland vs1, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs1, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 28
; CHECK-NEXT: blr
entry:
%not = xor <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 -1> ; Vector not operation
@@ -185,12 +167,10 @@ define <2 x i64> @ternary_A_not_B_and_BC_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i6
; CHECK-LABEL: ternary_A_not_B_and_BC_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxlnor vs0, v3, v3
-; CHECK-NEXT: xxland vs1, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs1, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 28
; CHECK-NEXT: blr
entry:
%not = xor <2 x i64> %B, <i64 -1, i64 -1> ; Vector not operation
diff --git a/llvm/test/CodeGen/PowerPC/xxeval-vselect-x-b.ll b/llvm/test/CodeGen/PowerPC/xxeval-vselect-x-b.ll
index 37a0edb14b78f..c36fd68ba0ece 100644
--- a/llvm/test/CodeGen/PowerPC/xxeval-vselect-x-b.ll
+++ b/llvm/test/CodeGen/PowerPC/xxeval-vselect-x-b.ll
@@ -1,5 +1,5 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; Test file to verify the emission of Vector selection instructions when ternary operators are used.
+; Test file to verify the emission of Vector Evaluate instructions when ternary operators are used.
; RUN: llc -verify-machineinstrs -mcpu=pwr10 -mtriple=powerpc64le-unknown-unknown \
; RUN: -ppc-asm-full-reg-names --ppc-vsr-nums-as-vr < %s | FileCheck %s
@@ -15,10 +15,9 @@ define <4 x i32> @ternary_A_and_BC_B_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i32> %
; CHECK-LABEL: ternary_A_and_BC_B_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxland vs0, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, v3, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 49
; CHECK-NEXT: blr
entry:
%and = and <4 x i32> %B, %C
@@ -31,11 +30,10 @@ define <2 x i64> @ternary_A_and_BC_B_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i64> %
; CHECK-LABEL: ternary_A_and_BC_B_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxland vs0, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, v3, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 49
; CHECK-NEXT: blr
entry:
%and = and <2 x i64> %B, %C
@@ -48,10 +46,9 @@ define <4 x i32> @ternary_A_nor_BC_B_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i32> %
; CHECK-LABEL: ternary_A_nor_BC_B_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxlnor vs0, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, v3, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 56
; CHECK-NEXT: blr
entry:
%or = or <4 x i32> %B, %C
@@ -65,11 +62,10 @@ define <2 x i64> @ternary_A_nor_BC_B_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i64> %
; CHECK-LABEL: ternary_A_nor_BC_B_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxlnor vs0, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, v3, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 56
; CHECK-NEXT: blr
entry:
%or = or <2 x i64> %B, %C
@@ -83,10 +79,9 @@ define <4 x i32> @ternary_A_eqv_BC_B_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i32> %
; CHECK-LABEL: ternary_A_eqv_BC_B_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxleqv vs0, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, v3, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 57
; CHECK-NEXT: blr
entry:
%xor = xor <4 x i32> %B, %C
@@ -100,11 +95,10 @@ define <2 x i64> @ternary_A_eqv_BC_B_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i64> %
; CHECK-LABEL: ternary_A_eqv_BC_B_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxleqv vs0, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, v3, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 57
; CHECK-NEXT: blr
entry:
%xor = xor <2 x i64> %B, %C
@@ -118,10 +112,9 @@ define <4 x i32> @ternary_A_not_C_B_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i32> %C
; CHECK-LABEL: ternary_A_not_C_B_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxlnor vs0, v4, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, v3, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 58
; CHECK-NEXT: blr
entry:
%not = xor <4 x i32> %C, <i32 -1, i32 -1, i32 -1, i32 -1> ; Vector not operation
@@ -134,11 +127,10 @@ define <2 x i64> @ternary_A_not_C_B_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i64> %C
; CHECK-LABEL: ternary_A_not_C_B_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxlnor vs0, v4, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, v3, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 58
; CHECK-NEXT: blr
entry:
%not = xor <2 x i64> %C, <i64 -1, i64 -1> ; Vector not operation
@@ -151,10 +143,9 @@ define <4 x i32> @ternary_A_nand_BC_B_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i32>
; CHECK-LABEL: ternary_A_nand_BC_B_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxlnand vs0, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, v3, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 62
; CHECK-NEXT: blr
entry:
%and = and <4 x i32> %B, %C
@@ -168,11 +159,10 @@ define <2 x i64> @ternary_A_nand_BC_B_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i64>
; CHECK-LABEL: ternary_A_nand_BC_B_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxlnand vs0, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, v3, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 62
; CHECK-NEXT: blr
entry:
%and = and <2 x i64> %B, %C
diff --git a/llvm/test/CodeGen/PowerPC/xxeval-vselect-x-c.ll b/llvm/test/CodeGen/PowerPC/xxeval-vselect-x-c.ll
index 411aa27a61861..54fda6063bfac 100644
--- a/llvm/test/CodeGen/PowerPC/xxeval-vselect-x-c.ll
+++ b/llvm/test/CodeGen/PowerPC/xxeval-vselect-x-c.ll
@@ -1,5 +1,5 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; Test file to verify the emission of Vector selection instructions when ternary operators are used.
+; Test file to verify the emission of Vector Evaluate instructions when ternary operators are used.
; RUN: llc -verify-machineinstrs -mcpu=pwr10 -mtriple=powerpc64le-unknown-unknown \
; RUN: -ppc-asm-full-reg-names --ppc-vsr-nums-as-vr < %s | FileCheck %s
@@ -15,10 +15,9 @@ define <4 x i32> @ternary_A_and_BC_C_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i32> %
; CHECK-LABEL: ternary_A_and_BC_C_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxland vs0, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, v4, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 81
; CHECK-NEXT: blr
entry:
%and = and <4 x i32> %B, %C
@@ -31,11 +30,10 @@ define <2 x i64> @ternary_A_and_BC_C_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i64> %
; CHECK-LABEL: ternary_A_and_BC_C_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxland vs0, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, v4, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 81
; CHECK-NEXT: blr
entry:
%and = and <2 x i64> %B, %C
@@ -48,10 +46,9 @@ define <4 x i32> @ternary_A_nor_BC_C_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i32> %
; CHECK-LABEL: ternary_A_nor_BC_C_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxlnor vs0, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, v4, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 88
; CHECK-NEXT: blr
entry:
%or = or <4 x i32> %B, %C
@@ -65,11 +62,10 @@ define <2 x i64> @ternary_A_nor_BC_C_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i64> %
; CHECK-LABEL: ternary_A_nor_BC_C_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxlnor vs0, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, v4, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 88
; CHECK-NEXT: blr
entry:
%or = or <2 x i64> %B, %C
@@ -83,10 +79,9 @@ define <4 x i32> @ternary_A_eqv_BC_C_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i32> %
; CHECK-LABEL: ternary_A_eqv_BC_C_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxleqv vs0, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, v4, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 89
; CHECK-NEXT: blr
entry:
%xor = xor <4 x i32> %B, %C
@@ -100,11 +95,10 @@ define <2 x i64> @ternary_A_eqv_BC_C_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i64> %
; CHECK-LABEL: ternary_A_eqv_BC_C_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxleqv vs0, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, v4, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 89
; CHECK-NEXT: blr
entry:
%xor = xor <2 x i64> %B, %C
@@ -118,10 +112,9 @@ define <4 x i32> @ternary_A_nand_BC_C_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i32>
; CHECK-LABEL: ternary_A_nand_BC_C_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxlnand vs0, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, v4, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 94
; CHECK-NEXT: blr
entry:
%and = and <4 x i32> %B, %C
@@ -135,11 +128,10 @@ define <2 x i64> @ternary_A_nand_BC_C_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i64>
; CHECK-LABEL: ternary_A_nand_BC_C_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxlnand vs0, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, v4, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 94
; CHECK-NEXT: blr
entry:
%and = and <2 x i64> %B, %C
diff --git a/llvm/test/CodeGen/PowerPC/xxeval-vselect-x-xor.ll b/llvm/test/CodeGen/PowerPC/xxeval-vselect-x-xor.ll
index f8a8b6e9a0486..74d3a3bf6196e 100644
--- a/llvm/test/CodeGen/PowerPC/xxeval-vselect-x-xor.ll
+++ b/llvm/test/CodeGen/PowerPC/xxeval-vselect-x-xor.ll
@@ -1,5 +1,5 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; Test file to verify the emission of Vector selection instructions when ternary operators are used.
+; Test file to verify the emission of Vector Evaluate instructions when ternary operators are used.
; RUN: llc -verify-machineinstrs -mcpu=pwr10 -mtriple=powerpc64le-unknown-unknown \
; RUN: -ppc-asm-full-reg-names --ppc-vsr-nums-as-vr < %s | FileCheck %s
@@ -15,11 +15,9 @@ define <4 x i32> @ternary_A_and_BC_xor_BC_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i
; CHECK-LABEL: ternary_A_and_BC_xor_BC_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxland vs0, v3, v4
-; CHECK-NEXT: xxlxor vs1, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs1, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 97
; CHECK-NEXT: blr
entry:
%and = and <4 x i32> %B, %C
@@ -33,12 +31,10 @@ define <2 x i64> @ternary_A_and_BC_xor_BC_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i
; CHECK-LABEL: ternary_A_and_BC_xor_BC_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxland vs0, v3, v4
-; CHECK-NEXT: xxlxor vs1, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs1, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 97
; CHECK-NEXT: blr
entry:
%and = and <2 x i64> %B, %C
@@ -52,10 +48,9 @@ define <4 x i32> @ternary_A_B_xor_BC_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i32> %
; CHECK-LABEL: ternary_A_B_xor_BC_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxlxor vs0, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs0, v3, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 99
; CHECK-NEXT: blr
entry:
%xor = xor <4 x i32> %B, %C
@@ -68,11 +63,10 @@ define <2 x i64> @ternary_A_B_xor_BC_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i64> %
; CHECK-LABEL: ternary_A_B_xor_BC_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxlxor vs0, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs0, v3, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 99
; CHECK-NEXT: blr
entry:
%xor = xor <2 x i64> %B, %C
@@ -85,10 +79,9 @@ define <4 x i32> @ternary_A_C_xor_BC_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i32> %
; CHECK-LABEL: ternary_A_C_xor_BC_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxlxor vs0, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs0, v4, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 101
; CHECK-NEXT: blr
entry:
%xor = xor <4 x i32> %B, %C
@@ -101,11 +94,10 @@ define <2 x i64> @ternary_A_C_xor_BC_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i64> %
; CHECK-LABEL: ternary_A_C_xor_BC_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxlxor vs0, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs0, v4, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 101
; CHECK-NEXT: blr
entry:
%xor = xor <2 x i64> %B, %C
@@ -118,11 +110,9 @@ define <4 x i32> @ternary_A_or_BC_xor_BC_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i3
; CHECK-LABEL: ternary_A_or_BC_xor_BC_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxlor vs0, v3, v4
-; CHECK-NEXT: xxlxor vs1, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs1, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 103
; CHECK-NEXT: blr
entry:
%or = or <4 x i32> %B, %C
@@ -136,12 +126,10 @@ define <2 x i64> @ternary_A_or_BC_xor_BC_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i6
; CHECK-LABEL: ternary_A_or_BC_xor_BC_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxlor vs0, v3, v4
-; CHECK-NEXT: xxlxor vs1, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs1, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 103
; CHECK-NEXT: blr
entry:
%or = or <2 x i64> %B, %C
@@ -155,11 +143,9 @@ define <4 x i32> @ternary_A_nor_BC_xor_BC_4x32(<4 x i1> %A, <4 x i32> %B, <4 x i
; CHECK-LABEL: ternary_A_nor_BC_xor_BC_4x32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxleqv v5, v5, v5
-; CHECK-NEXT: xxlnor vs0, v3, v4
-; CHECK-NEXT: xxlxor vs1, v3, v4
; CHECK-NEXT: vslw v2, v2, v5
; CHECK-NEXT: vsraw v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs1, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 104
; CHECK-NEXT: blr
entry:
%or = or <4 x i32> %B, %C
@@ -174,12 +160,10 @@ define <2 x i64> @ternary_A_nor_BC_xor_BC_2x64(<2 x i1> %A, <2 x i64> %B, <2 x i
; CHECK-LABEL: ternary_A_nor_BC_xor_BC_2x64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: xxlxor v5, v5, v5
-; CHECK-NEXT: xxlnor vs0, v3, v4
-; CHECK-NEXT: xxlxor vs1, v3, v4
; CHECK-NEXT: xxsplti32dx v5, 1, 63
; CHECK-NEXT: vsld v2, v2, v5
; CHECK-NEXT: vsrad v2, v2, v5
-; CHECK-NEXT: xxsel v2, vs1, vs0, v2
+; CHECK-NEXT: xxeval v2, v2, v3, v4, 104
; CHECK-NEXT: blr
entry:
%or = or <2 x i64> %B, %C
- Previous message: [llvm] [PowerPC10][XXEVAL] Exploit xxeval instruction for cases of the ternary(A,X, and(B,C)), ternary(A,X,B), ternary(A,X,C), ternary(A,X,xor(B,C)) forms. (PR #141733)
- Next message: [llvm] [PowerPC10][XXEVAL] Exploit xxeval instruction for cases of the ternary(A,X, and(B,C)), ternary(A,X,B), ternary(A,X,C), ternary(A,X,xor(B,C)) forms. (PR #141733)
- Messages sorted by:
[ date ]
[ thread ]
[ subject ]
[ author ]
More information about the llvm-commits
mailing list