[llvm] [LLVM][DAGCombiner][SVE] Fold vselect into merge_pasthru_op. (PR #146917)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Jul 3 08:51:38 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-aarch64
Author: Paul Walker (paulwalker-arm)
<details>
<summary>Changes</summary>
vselect A, (merge_pasthru_op all_active, B,{Bn,} -), C
vselect A, (merge_pasthru_op -, B,{Bn,} undef), C
vselect A, (merge_pasthru_op A, B,{Bn,} -), C
-> merge_pasthru_op A, B,{Bn,} C
---
Patch is 75.08 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/146917.diff
3 Files Affected:
- (modified) llvm/lib/Target/AArch64/AArch64ISelLowering.cpp (+19-3)
- (modified) llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td (+9)
- (modified) llvm/test/CodeGen/AArch64/sve-merging-unary.ll (+141-344)
``````````diff
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index fb8bd81c033af..0d388fc3c787d 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -25523,6 +25523,9 @@ static SDValue performVSelectCombine(SDNode *N, SelectionDAG &DAG) {
return SwapResult;
SDValue N0 = N->getOperand(0);
+ SDValue IfTrue = N->getOperand(1);
+ SDValue IfFalse = N->getOperand(2);
+ EVT ResVT = N->getValueType(0);
EVT CCVT = N0.getValueType();
if (isAllActivePredicate(DAG, N0))
@@ -25531,6 +25534,22 @@ static SDValue performVSelectCombine(SDNode *N, SelectionDAG &DAG) {
if (isAllInactivePredicate(N0))
return N->getOperand(2);
+ if (isMergePassthruOpcode(IfTrue.getOpcode()) && IfTrue.hasOneUse()) {
+ // vselect A, (merge_pasthru_op all_active, B,{Bn,} -), C
+ // vselect A, (merge_pasthru_op -, B,{Bn,} undef), C
+ // vselect A, (merge_pasthru_op A, B,{Bn,} -), C
+ // -> merge_pasthru_op A, B,{Bn,} C
+ if (isAllActivePredicate(DAG, IfTrue->getOperand(0)) ||
+ IfTrue->getOperand(IfTrue.getNumOperands() - 1).isUndef() ||
+ IfTrue->getOperand(0) == N0) {
+ SmallVector<SDValue, 4> Ops(IfTrue->op_values());
+ Ops[0] = N0;
+ Ops[IfTrue.getNumOperands() - 1] = IfFalse;
+
+ return DAG.getNode(IfTrue.getOpcode(), SDLoc(N), ResVT, Ops);
+ }
+ }
+
// Check for sign pattern (VSELECT setgt, iN lhs, -1, 1, -1) and transform
// into (OR (ASR lhs, N-1), 1), which requires less instructions for the
// supported types.
@@ -25570,14 +25589,11 @@ static SDValue performVSelectCombine(SDNode *N, SelectionDAG &DAG) {
CmpVT.getVectorElementType().isFloatingPoint())
return SDValue();
- EVT ResVT = N->getValueType(0);
// Only combine when the result type is of the same size as the compared
// operands.
if (ResVT.getSizeInBits() != CmpVT.getSizeInBits())
return SDValue();
- SDValue IfTrue = N->getOperand(1);
- SDValue IfFalse = N->getOperand(2);
SetCC = DAG.getSetCC(SDLoc(N), CmpVT.changeVectorElementTypeToInteger(),
N0.getOperand(0), N0.getOperand(1),
cast<CondCodeSDNode>(N0.getOperand(2))->get());
diff --git a/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td b/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
index 91a9d21fa7b2c..261df563bb2a9 100644
--- a/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
@@ -2445,14 +2445,23 @@ let Predicates = [HasSVE_or_SME] in {
defm FCVTZU_ZPmZ_DtoD : sve_fp_2op_p_zd< 0b1111111, "fcvtzu", ZPR64, ZPR64, null_frag, AArch64fcvtzu_mt, nxv2i64, nxv2i1, nxv2f64, ElementSizeD>;
//These patterns exist to improve the code quality of conversions on unpacked types.
+ def : Pat<(nxv2f32 (AArch64fcvte_mt nxv2i1:$Pg, nxv2f16:$Zs, nxv2f32:$Zd)),
+ (FCVT_ZPmZ_HtoS ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;
def : Pat<(nxv2f32 (AArch64fcvte_mt (nxv2i1 (SVEAllActive:$Pg)), nxv2f16:$Zs, nxv2f32:$Zd)),
(FCVT_ZPmZ_HtoS_UNDEF ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;
// FP_ROUND has an additional 'precise' flag which indicates the type of rounding.
// This is ignored by the pattern below where it is matched by (i64 timm0_1)
+ def : Pat<(nxv2f16 (AArch64fcvtr_mt nxv2i1:$Pg, nxv2f32:$Zs, (i64 timm0_1), nxv2f16:$Zd)),
+ (FCVT_ZPmZ_StoH ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;
def : Pat<(nxv2f16 (AArch64fcvtr_mt (nxv2i1 (SVEAllActive:$Pg)), nxv2f32:$Zs, (i64 timm0_1), nxv2f16:$Zd)),
(FCVT_ZPmZ_StoH_UNDEF ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;
+ def : Pat<(nxv4f32 (AArch64fcvte_mt nxv4i1:$Pg, nxv4bf16:$Zs, nxv4f32:$Zd)),
+ (SEL_ZPZZ_S $Pg, (LSL_ZZI_S $Zs, (i32 16)), $Zd)>;
+ def : Pat<(nxv2f32 (AArch64fcvte_mt nxv2i1:$Pg, nxv2bf16:$Zs, nxv2f32:$Zd)),
+ (SEL_ZPZZ_D $Pg, (LSL_ZZI_S $Zs, (i32 16)), $Zd)>;
+
def : Pat<(nxv4f32 (AArch64fcvte_mt (SVEAnyPredicate), nxv4bf16:$op, undef)),
(LSL_ZZI_S $op, (i32 16))>;
def : Pat<(nxv2f32 (AArch64fcvte_mt (SVEAnyPredicate), nxv2bf16:$op, undef)),
diff --git a/llvm/test/CodeGen/AArch64/sve-merging-unary.ll b/llvm/test/CodeGen/AArch64/sve-merging-unary.ll
index 9e331a69bcf7c..eec111d3285fe 100644
--- a/llvm/test/CodeGen/AArch64/sve-merging-unary.ll
+++ b/llvm/test/CodeGen/AArch64/sve-merging-unary.ll
@@ -7,9 +7,7 @@ target triple = "aarch64-unknown-linux-gnu"
define <vscale x 16 x i8> @abs_nxv16i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: abs_nxv16i8:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.b
-; CHECK-NEXT: abs z1.b, p1/m, z1.b
-; CHECK-NEXT: mov z0.b, p0/m, z1.b
+; CHECK-NEXT: abs z0.b, p0/m, z1.b
; CHECK-NEXT: ret
%b.op = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> %b, i1 0)
%res = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %b.op, <vscale x 16 x i8> %a
@@ -19,9 +17,7 @@ define <vscale x 16 x i8> @abs_nxv16i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8
define <vscale x 8 x i16> @abs_nxv8i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: abs_nxv8i16:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.h
-; CHECK-NEXT: abs z1.h, p1/m, z1.h
-; CHECK-NEXT: mov z0.h, p0/m, z1.h
+; CHECK-NEXT: abs z0.h, p0/m, z1.h
; CHECK-NEXT: ret
%b.op = call <vscale x 8 x i16> @llvm.abs.nxv8i16(<vscale x 8 x i16> %b, i1 0)
%res = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %b.op, <vscale x 8 x i16> %a
@@ -31,9 +27,7 @@ define <vscale x 8 x i16> @abs_nxv8i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16>
define <vscale x 4 x i32> @abs_nxv4i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: abs_nxv4i32:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.s
-; CHECK-NEXT: abs z1.s, p1/m, z1.s
-; CHECK-NEXT: mov z0.s, p0/m, z1.s
+; CHECK-NEXT: abs z0.s, p0/m, z1.s
; CHECK-NEXT: ret
%b.op = call <vscale x 4 x i32> @llvm.abs.nxv4i32(<vscale x 4 x i32> %b, i1 0)
%res = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %b.op, <vscale x 4 x i32> %a
@@ -43,9 +37,7 @@ define <vscale x 4 x i32> @abs_nxv4i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32>
define <vscale x 2 x i64> @abs_nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: abs_nxv2i64:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.d
-; CHECK-NEXT: abs z1.d, p1/m, z1.d
-; CHECK-NEXT: mov z0.d, p0/m, z1.d
+; CHECK-NEXT: abs z0.d, p0/m, z1.d
; CHECK-NEXT: ret
%b.op = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> %b, i1 0)
%res = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %b.op, <vscale x 2 x i64> %a
@@ -55,9 +47,7 @@ define <vscale x 2 x i64> @abs_nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64>
define <vscale x 16 x i8> @clz_nxv16i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: clz_nxv16i8:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.b
-; CHECK-NEXT: clz z1.b, p1/m, z1.b
-; CHECK-NEXT: mov z0.b, p0/m, z1.b
+; CHECK-NEXT: clz z0.b, p0/m, z1.b
; CHECK-NEXT: ret
%b.op = call <vscale x 16 x i8> @llvm.ctlz.nxv16i8(<vscale x 16 x i8> %b)
%res = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %b.op, <vscale x 16 x i8> %a
@@ -67,9 +57,7 @@ define <vscale x 16 x i8> @clz_nxv16i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8
define <vscale x 8 x i16> @clz_nxv8i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: clz_nxv8i16:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.h
-; CHECK-NEXT: clz z1.h, p1/m, z1.h
-; CHECK-NEXT: mov z0.h, p0/m, z1.h
+; CHECK-NEXT: clz z0.h, p0/m, z1.h
; CHECK-NEXT: ret
%b.op = call <vscale x 8 x i16> @llvm.ctlz.nxv8i16(<vscale x 8 x i16> %b)
%res = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %b.op, <vscale x 8 x i16> %a
@@ -79,9 +67,7 @@ define <vscale x 8 x i16> @clz_nxv8i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16>
define <vscale x 4 x i32> @clz_nxv4i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: clz_nxv4i32:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.s
-; CHECK-NEXT: clz z1.s, p1/m, z1.s
-; CHECK-NEXT: mov z0.s, p0/m, z1.s
+; CHECK-NEXT: clz z0.s, p0/m, z1.s
; CHECK-NEXT: ret
%b.op = call <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32> %b)
%res = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %b.op, <vscale x 4 x i32> %a
@@ -91,9 +77,7 @@ define <vscale x 4 x i32> @clz_nxv4i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32>
define <vscale x 2 x i64> @clz_nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: clz_nxv2i64:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.d
-; CHECK-NEXT: clz z1.d, p1/m, z1.d
-; CHECK-NEXT: mov z0.d, p0/m, z1.d
+; CHECK-NEXT: clz z0.d, p0/m, z1.d
; CHECK-NEXT: ret
%b.op = call <vscale x 2 x i64> @llvm.ctlz.nxv2i64(<vscale x 2 x i64> %b)
%res = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %b.op, <vscale x 2 x i64> %a
@@ -103,9 +87,7 @@ define <vscale x 2 x i64> @clz_nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64>
define <vscale x 16 x i8> @cnt_nxv16i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: cnt_nxv16i8:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.b
-; CHECK-NEXT: cnt z1.b, p1/m, z1.b
-; CHECK-NEXT: mov z0.b, p0/m, z1.b
+; CHECK-NEXT: cnt z0.b, p0/m, z1.b
; CHECK-NEXT: ret
%b.op = call <vscale x 16 x i8> @llvm.ctpop.nxv16i8(<vscale x 16 x i8> %b)
%res = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %b.op, <vscale x 16 x i8> %a
@@ -115,9 +97,7 @@ define <vscale x 16 x i8> @cnt_nxv16i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8
define <vscale x 8 x i16> @cnt_nxv8i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: cnt_nxv8i16:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.h
-; CHECK-NEXT: cnt z1.h, p1/m, z1.h
-; CHECK-NEXT: mov z0.h, p0/m, z1.h
+; CHECK-NEXT: cnt z0.h, p0/m, z1.h
; CHECK-NEXT: ret
%b.op = call <vscale x 8 x i16> @llvm.ctpop.nxv8i16(<vscale x 8 x i16> %b)
%res = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %b.op, <vscale x 8 x i16> %a
@@ -127,9 +107,7 @@ define <vscale x 8 x i16> @cnt_nxv8i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16>
define <vscale x 4 x i32> @cnt_nxv4i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: cnt_nxv4i32:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.s
-; CHECK-NEXT: cnt z1.s, p1/m, z1.s
-; CHECK-NEXT: mov z0.s, p0/m, z1.s
+; CHECK-NEXT: cnt z0.s, p0/m, z1.s
; CHECK-NEXT: ret
%b.op = call <vscale x 4 x i32> @llvm.ctpop.nxv4i32(<vscale x 4 x i32> %b)
%res = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %b.op, <vscale x 4 x i32> %a
@@ -139,9 +117,7 @@ define <vscale x 4 x i32> @cnt_nxv4i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32>
define <vscale x 2 x i64> @cnt_nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: cnt_nxv2i64:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.d
-; CHECK-NEXT: cnt z1.d, p1/m, z1.d
-; CHECK-NEXT: mov z0.d, p0/m, z1.d
+; CHECK-NEXT: cnt z0.d, p0/m, z1.d
; CHECK-NEXT: ret
%b.op = call <vscale x 2 x i64> @llvm.ctpop.nxv2i64(<vscale x 2 x i64> %b)
%res = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %b.op, <vscale x 2 x i64> %a
@@ -151,9 +127,7 @@ define <vscale x 2 x i64> @cnt_nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64>
define <vscale x 2 x half> @fabs_nxv2f16(<vscale x 2 x i1> %pg, <vscale x 2 x half> %a, <vscale x 2 x half> %b) {
; CHECK-LABEL: fabs_nxv2f16:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.d
-; CHECK-NEXT: fabs z1.h, p1/m, z1.h
-; CHECK-NEXT: mov z0.d, p0/m, z1.d
+; CHECK-NEXT: fabs z0.h, p0/m, z1.h
; CHECK-NEXT: ret
%b.op = call <vscale x 2 x half> @llvm.fabs.nxv2f16(<vscale x 2 x half> %b)
%res = select <vscale x 2 x i1> %pg, <vscale x 2 x half> %b.op, <vscale x 2 x half> %a
@@ -163,9 +137,7 @@ define <vscale x 2 x half> @fabs_nxv2f16(<vscale x 2 x i1> %pg, <vscale x 2 x ha
define <vscale x 4 x half> @fabs_nxv4f16(<vscale x 4 x i1> %pg, <vscale x 4 x half> %a, <vscale x 4 x half> %b) {
; CHECK-LABEL: fabs_nxv4f16:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.s
-; CHECK-NEXT: fabs z1.h, p1/m, z1.h
-; CHECK-NEXT: mov z0.s, p0/m, z1.s
+; CHECK-NEXT: fabs z0.h, p0/m, z1.h
; CHECK-NEXT: ret
%b.op = call <vscale x 4 x half> @llvm.fabs.nxv4f16(<vscale x 4 x half> %b)
%res = select <vscale x 4 x i1> %pg, <vscale x 4 x half> %b.op, <vscale x 4 x half> %a
@@ -175,9 +147,7 @@ define <vscale x 4 x half> @fabs_nxv4f16(<vscale x 4 x i1> %pg, <vscale x 4 x ha
define <vscale x 8 x half> @fabs_nxv8f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: fabs_nxv8f16:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.h
-; CHECK-NEXT: fabs z1.h, p1/m, z1.h
-; CHECK-NEXT: mov z0.h, p0/m, z1.h
+; CHECK-NEXT: fabs z0.h, p0/m, z1.h
; CHECK-NEXT: ret
%b.op = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> %b)
%res = select <vscale x 8 x i1> %pg, <vscale x 8 x half> %b.op, <vscale x 8 x half> %a
@@ -187,9 +157,7 @@ define <vscale x 8 x half> @fabs_nxv8f16(<vscale x 8 x i1> %pg, <vscale x 8 x ha
define <vscale x 2 x float> @fabs_nxv2f32(<vscale x 2 x i1> %pg, <vscale x 2 x float> %a, <vscale x 2 x float> %b) {
; CHECK-LABEL: fabs_nxv2f32:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.d
-; CHECK-NEXT: fabs z1.s, p1/m, z1.s
-; CHECK-NEXT: mov z0.d, p0/m, z1.d
+; CHECK-NEXT: fabs z0.s, p0/m, z1.s
; CHECK-NEXT: ret
%b.op = call <vscale x 2 x float> @llvm.fabs.nxv2f32(<vscale x 2 x float> %b)
%res = select <vscale x 2 x i1> %pg, <vscale x 2 x float> %b.op, <vscale x 2 x float> %a
@@ -199,9 +167,7 @@ define <vscale x 2 x float> @fabs_nxv2f32(<vscale x 2 x i1> %pg, <vscale x 2 x f
define <vscale x 4 x float> @fabs_nxv4f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fabs_nxv4f32:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.s
-; CHECK-NEXT: fabs z1.s, p1/m, z1.s
-; CHECK-NEXT: mov z0.s, p0/m, z1.s
+; CHECK-NEXT: fabs z0.s, p0/m, z1.s
; CHECK-NEXT: ret
%b.op = call <vscale x 4 x float> @llvm.fabs.nxv4f32(<vscale x 4 x float> %b)
%res = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %b.op, <vscale x 4 x float> %a
@@ -211,9 +177,7 @@ define <vscale x 4 x float> @fabs_nxv4f32(<vscale x 4 x i1> %pg, <vscale x 4 x f
define <vscale x 2 x double> @fabs_nxv2f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) {
; CHECK-LABEL: fabs_nxv2f64:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.d
-; CHECK-NEXT: fabs z1.d, p1/m, z1.d
-; CHECK-NEXT: mov z0.d, p0/m, z1.d
+; CHECK-NEXT: fabs z0.d, p0/m, z1.d
; CHECK-NEXT: ret
%b.op = call <vscale x 2 x double> @llvm.fabs.nxv2f64(<vscale x 2 x double> %b)
%res = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %b.op, <vscale x 2 x double> %a
@@ -256,9 +220,7 @@ define <vscale x 8 x bfloat> @fabs_nxv8bf16(<vscale x 8 x i1> %pg, <vscale x 8 x
define <vscale x 2 x float> @fcvt_nxv2f16_to_nxv2f32(<vscale x 2 x i1> %pg, <vscale x 2 x float> %a, <vscale x 2 x half> %b) {
; CHECK-LABEL: fcvt_nxv2f16_to_nxv2f32:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.d
-; CHECK-NEXT: fcvt z1.s, p1/m, z1.h
-; CHECK-NEXT: mov z0.d, p0/m, z1.d
+; CHECK-NEXT: fcvt z0.s, p0/m, z1.h
; CHECK-NEXT: ret
%b.op = fpext <vscale x 2 x half> %b to <vscale x 2 x float>
%res = select <vscale x 2 x i1> %pg, <vscale x 2 x float> %b.op, <vscale x 2 x float> %a
@@ -268,9 +230,7 @@ define <vscale x 2 x float> @fcvt_nxv2f16_to_nxv2f32(<vscale x 2 x i1> %pg, <vsc
define <vscale x 2 x double> @fcvt_nxv2f16_to_nxv2f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x half> %b) {
; CHECK-LABEL: fcvt_nxv2f16_to_nxv2f64:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.d
-; CHECK-NEXT: fcvt z1.d, p1/m, z1.h
-; CHECK-NEXT: mov z0.d, p0/m, z1.d
+; CHECK-NEXT: fcvt z0.d, p0/m, z1.h
; CHECK-NEXT: ret
%b.op = fpext <vscale x 2 x half> %b to <vscale x 2 x double>
%res = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %b.op, <vscale x 2 x double> %a
@@ -280,9 +240,7 @@ define <vscale x 2 x double> @fcvt_nxv2f16_to_nxv2f64(<vscale x 2 x i1> %pg, <vs
define <vscale x 4 x float> @fcvt_nxv4f16_to_nxv4f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x half> %b) {
; CHECK-LABEL: fcvt_nxv4f16_to_nxv4f32:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.s
-; CHECK-NEXT: fcvt z1.s, p1/m, z1.h
-; CHECK-NEXT: mov z0.s, p0/m, z1.s
+; CHECK-NEXT: fcvt z0.s, p0/m, z1.h
; CHECK-NEXT: ret
%b.op = fpext <vscale x 4 x half> %b to <vscale x 4 x float>
%res = select <vscale x 4 x i1> %pg, <vscale x 4 x float> %b.op, <vscale x 4 x float> %a
@@ -292,9 +250,7 @@ define <vscale x 4 x float> @fcvt_nxv4f16_to_nxv4f32(<vscale x 4 x i1> %pg, <vsc
define <vscale x 2 x half> @fcvt_nxv2f32_to_nxv2f16(<vscale x 2 x i1> %pg, <vscale x 2 x half> %a, <vscale x 2 x float> %b) {
; CHECK-LABEL: fcvt_nxv2f32_to_nxv2f16:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.d
-; CHECK-NEXT: fcvt z1.h, p1/m, z1.s
-; CHECK-NEXT: mov z0.d, p0/m, z1.d
+; CHECK-NEXT: fcvt z0.h, p0/m, z1.s
; CHECK-NEXT: ret
%b.op = fptrunc <vscale x 2 x float> %b to <vscale x 2 x half>
%res = select <vscale x 2 x i1> %pg, <vscale x 2 x half> %b.op, <vscale x 2 x half> %a
@@ -304,9 +260,7 @@ define <vscale x 2 x half> @fcvt_nxv2f32_to_nxv2f16(<vscale x 2 x i1> %pg, <vsca
define <vscale x 2 x double> @fcvt_nxv2f32_to_nxv2f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x float> %b) {
; CHECK-LABEL: fcvt_nxv2f32_to_nxv2f64:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.d
-; CHECK-NEXT: fcvt z1.d, p1/m, z1.s
-; CHECK-NEXT: mov z0.d, p0/m, z1.d
+; CHECK-NEXT: fcvt z0.d, p0/m, z1.s
; CHECK-NEXT: ret
%b.op = fpext <vscale x 2 x float> %b to <vscale x 2 x double>
%res = select <vscale x 2 x i1> %pg, <vscale x 2 x double> %b.op, <vscale x 2 x double> %a
@@ -316,9 +270,7 @@ define <vscale x 2 x double> @fcvt_nxv2f32_to_nxv2f64(<vscale x 2 x i1> %pg, <vs
define <vscale x 2 x bfloat> @fcvt_nxv2f32_to_nxv2bf16(<vscale x 2 x i1> %pg, <vscale x 2 x bfloat> %a, <vscale x 2 x float> %b) {
; CHECK-LABEL: fcvt_nxv2f32_to_nxv2bf16:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.d
-; CHECK-NEXT: bfcvt z1.h, p1/m, z1.s
-; CHECK-NEXT: mov z0.d, p0/m, z1.d
+; CHECK-NEXT: bfcvt z0.h, p0/m, z1.s
; CHECK-NEXT: ret
%b.op = fptrunc <vscale x 2 x float> %b to <vscale x 2 x bfloat>
%res = select <vscale x 2 x i1> %pg, <vscale x 2 x bfloat> %b.op, <vscale x 2 x bfloat> %a
@@ -328,9 +280,7 @@ define <vscale x 2 x bfloat> @fcvt_nxv2f32_to_nxv2bf16(<vscale x 2 x i1> %pg, <v
define <vscale x 4 x half> @fcvt_nxv4f32_to_nxv4f16(<vscale x 4 x i1> %pg, <vscale x 4 x half> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fcvt_nxv4f32_to_nxv4f16:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.s
-; CHECK-NEXT: fcvt z1.h, p1/m, z1.s
-; CHECK-NEXT: mov z0.s, p0/m, z1.s
+; CHECK-NEXT: fcvt z0.h, p0/m, z1.s
; CHECK-NEXT: ret
%b.op = fptrunc <vscale x 4 x float> %b to <vscale x 4 x half>
%res = select <vscale x 4 x i1> %pg, <vscale x 4 x half> %b.op, <vscale x 4 x half> %a
@@ -340,9 +290,7 @@ define <vscale x 4 x half> @fcvt_nxv4f32_to_nxv4f16(<vscale x 4 x i1> %pg, <vsca
define <vscale x 4 x bfloat> @fcvt_nxv4f32_to_nxv4bf16(<vscale x 4 x i1> %pg, <vscale x 4 x bfloat> %a, <vscale x 4 x float> %b) {
; CHECK-LABEL: fcvt_nxv4f32_to_nxv4bf16:
; CHECK: // %bb.0:
-; CHECK-NEXT: ptrue p1.s
-; CHECK-NEXT: bfcvt z1.h, p1/m, z1.s
-; CHECK-NEXT: mov z0.s, p0/m, z1.s
+; CHECK-NEXT: bfcvt z0.h, p0/m, z1.s
; CHECK-NEXT: ret
%b.op = fptrunc <vscale x 4 x float> %b to <vscale x 4 x bfloat>
%res = select <vscale x 4 x i1> %pg, <vscale x 4 x bfloat> %b.op, <vscale x 4 x bfloat> %a
@@ -352,9 +300,7 @@ define <vscale x 4 x bfloat> @fcvt_nxv4f32_to_nxv4bf16(<vscale x 4 x i1> %pg, <v
define <vscale x 2 x half> @fcvt_nxv2f64_to_nxv2f16(<vscale x 2 x i1> %pg, <vscale x 2 x half> %a...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/146917
More information about the llvm-commits
mailing list