[llvm] [AArch64] Tighten conditions for expanding GET_ACTIVE_LANE_MASK (PR #208962)
Usman Nadeem via llvm-commits
llvm-commits at lists.llvm.org
Sat Jul 11 15:50:21 PDT 2026
https://github.com/UsmanNadeem created https://github.com/llvm/llvm-project/pull/208962
Don't expand for fixed vectors if the operands are <32 bits. Expanding is going to be more expensive compared to promoting the operands from a smaller type.
>From 6f92ae622cfb3503e134e6a71bf5ae9b04c451fc Mon Sep 17 00:00:00 2001
From: Usman Nadeem <mnadeem at qti.qualcomm.com>
Date: Sat, 11 Jul 2026 15:35:18 -0700
Subject: [PATCH] [AArch64] Tighten conditions for expanding
GET_ACTIVE_LANE_MASK
Expanding to NEON is going to be more expensive compared to
promoting the operands from a smaller type.
Change-Id: I80cf668a90eec6a48d0909025df4472a43cf41cc
---
.../Target/AArch64/AArch64ISelLowering.cpp | 3 +-
llvm/test/CodeGen/AArch64/active_lane_mask.ll | 123 +++++-------------
2 files changed, 32 insertions(+), 94 deletions(-)
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index f33d953eec747..387f5d0158662 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -2449,8 +2449,7 @@ bool AArch64TargetLowering::shouldExpandGetActiveLaneMask(EVT ResVT,
// Only support illegal types if the result is scalable and min elements > 1.
if (ResVT.getVectorMinNumElements() == 1 ||
- (ResVT.isFixedLengthVector() && (ResVT.getVectorNumElements() > 16 ||
- (OpVT != MVT::i32 && OpVT != MVT::i64))))
+ (ResVT.isFixedLengthVector() && (ResVT.getVectorNumElements() > 16)))
return true;
// 32 & 64 bit operands are supported. We can promote anything < 64 bits,
diff --git a/llvm/test/CodeGen/AArch64/active_lane_mask.ll b/llvm/test/CodeGen/AArch64/active_lane_mask.ll
index 778be79038a78..a1cd950cba7cb 100644
--- a/llvm/test/CodeGen/AArch64/active_lane_mask.ll
+++ b/llvm/test/CodeGen/AArch64/active_lane_mask.ll
@@ -285,113 +285,49 @@ define <2 x i1> @lane_mask_v2i1_i64(i64 %index, i64 %TC) {
}
define <16 x i1> @lane_mask_v16i1_i8(i8 %index, i8 %TC) {
-; CHECK-SVE-LABEL: lane_mask_v16i1_i8:
-; CHECK-SVE: // %bb.0:
-; CHECK-SVE-NEXT: index z0.b, #0, #1
-; CHECK-SVE-NEXT: dup v1.16b, w0
-; CHECK-SVE-NEXT: uqadd v0.16b, v1.16b, v0.16b
-; CHECK-SVE-NEXT: dup v1.16b, w1
-; CHECK-SVE-NEXT: cmhi v0.16b, v1.16b, v0.16b
-; CHECK-SVE-NEXT: ret
-;
-; CHECK-STREAMING-LABEL: lane_mask_v16i1_i8:
-; CHECK-STREAMING: // %bb.0:
-; CHECK-STREAMING-NEXT: index z0.b, w0, #1
-; CHECK-STREAMING-NEXT: mov z1.b, w0
-; CHECK-STREAMING-NEXT: ptrue p0.b, vl16
-; CHECK-STREAMING-NEXT: cmphi p1.b, p0/z, z1.b, z0.b
-; CHECK-STREAMING-NEXT: mov z1.b, p1/z, #-1 // =0xffffffffffffffff
-; CHECK-STREAMING-NEXT: orr z0.d, z0.d, z1.d
-; CHECK-STREAMING-NEXT: mov z1.b, w1
-; CHECK-STREAMING-NEXT: cmphi p1.b, p0/z, z1.b, z0.b
-; CHECK-STREAMING-NEXT: mov z0.b, p1/z, #-1 // =0xffffffffffffffff
-; CHECK-STREAMING-NEXT: ret
+; CHECK-LABEL: lane_mask_v16i1_i8:
+; CHECK: // %bb.0:
+; CHECK-NEXT: and w8, w1, #0xff
+; CHECK-NEXT: and w9, w0, #0xff
+; CHECK-NEXT: whilelo p0.b, w9, w8
+; CHECK-NEXT: mov z0.b, p0/z, #-1 // =0xffffffffffffffff
+; CHECK-NEXT: ret
%active.lane.mask = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i8(i8 %index, i8 %TC)
ret <16 x i1> %active.lane.mask
}
define <8 x i1> @lane_mask_v8i1_i8(i8 %index, i8 %TC) {
-; CHECK-SVE-LABEL: lane_mask_v8i1_i8:
-; CHECK-SVE: // %bb.0:
-; CHECK-SVE-NEXT: index z0.b, #0, #1
-; CHECK-SVE-NEXT: dup v1.8b, w0
-; CHECK-SVE-NEXT: uqadd v0.8b, v1.8b, v0.8b
-; CHECK-SVE-NEXT: dup v1.8b, w1
-; CHECK-SVE-NEXT: cmhi v0.8b, v1.8b, v0.8b
-; CHECK-SVE-NEXT: ret
-;
-; CHECK-STREAMING-LABEL: lane_mask_v8i1_i8:
-; CHECK-STREAMING: // %bb.0:
-; CHECK-STREAMING-NEXT: index z0.b, w0, #1
-; CHECK-STREAMING-NEXT: mov z1.b, w0
-; CHECK-STREAMING-NEXT: ptrue p0.b, vl8
-; CHECK-STREAMING-NEXT: cmphi p1.b, p0/z, z1.b, z0.b
-; CHECK-STREAMING-NEXT: mov z1.b, p1/z, #-1 // =0xffffffffffffffff
-; CHECK-STREAMING-NEXT: orr z0.d, z0.d, z1.d
-; CHECK-STREAMING-NEXT: mov z1.b, w1
-; CHECK-STREAMING-NEXT: cmphi p1.b, p0/z, z1.b, z0.b
-; CHECK-STREAMING-NEXT: mov z0.b, p1/z, #-1 // =0xffffffffffffffff
-; CHECK-STREAMING-NEXT: ret
+; CHECK-LABEL: lane_mask_v8i1_i8:
+; CHECK: // %bb.0:
+; CHECK-NEXT: and w8, w1, #0xff
+; CHECK-NEXT: and w9, w0, #0xff
+; CHECK-NEXT: whilelo p0.b, w9, w8
+; CHECK-NEXT: mov z0.b, p0/z, #-1 // =0xffffffffffffffff
+; CHECK-NEXT: ret
%active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i8(i8 %index, i8 %TC)
ret <8 x i1> %active.lane.mask
}
define <4 x i1> @lane_mask_v4i1_i8(i8 %index, i8 %TC) {
-; CHECK-SVE-LABEL: lane_mask_v4i1_i8:
-; CHECK-SVE: // %bb.0:
-; CHECK-SVE-NEXT: dup v0.4h, w0
-; CHECK-SVE-NEXT: index z1.h, #0, #1
-; CHECK-SVE-NEXT: movi d2, #0xff00ff00ff00ff
-; CHECK-SVE-NEXT: dup v3.4h, w1
-; CHECK-SVE-NEXT: bic v0.4h, #255, lsl #8
-; CHECK-SVE-NEXT: bic v3.4h, #255, lsl #8
-; CHECK-SVE-NEXT: add v0.4h, v0.4h, v1.4h
-; CHECK-SVE-NEXT: umin v0.4h, v0.4h, v2.4h
-; CHECK-SVE-NEXT: cmhi v0.4h, v3.4h, v0.4h
-; CHECK-SVE-NEXT: ret
-;
-; CHECK-STREAMING-LABEL: lane_mask_v4i1_i8:
-; CHECK-STREAMING: // %bb.0:
-; CHECK-STREAMING-NEXT: mov z1.h, w0
-; CHECK-STREAMING-NEXT: index z0.h, #0, #1
-; CHECK-STREAMING-NEXT: ptrue p0.h, vl4
-; CHECK-STREAMING-NEXT: and z1.h, z1.h, #0xff
-; CHECK-STREAMING-NEXT: add z0.h, z1.h, z0.h
-; CHECK-STREAMING-NEXT: mov z1.h, w1
-; CHECK-STREAMING-NEXT: umin z0.h, z0.h, #255
-; CHECK-STREAMING-NEXT: and z1.h, z1.h, #0xff
-; CHECK-STREAMING-NEXT: cmphi p1.h, p0/z, z1.h, z0.h
-; CHECK-STREAMING-NEXT: mov z0.h, p1/z, #-1 // =0xffffffffffffffff
-; CHECK-STREAMING-NEXT: ret
+; CHECK-LABEL: lane_mask_v4i1_i8:
+; CHECK: // %bb.0:
+; CHECK-NEXT: and w8, w1, #0xff
+; CHECK-NEXT: and w9, w0, #0xff
+; CHECK-NEXT: whilelo p0.h, w9, w8
+; CHECK-NEXT: mov z0.h, p0/z, #-1 // =0xffffffffffffffff
+; CHECK-NEXT: ret
%active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i8(i8 %index, i8 %TC)
ret <4 x i1> %active.lane.mask
}
define <2 x i1> @lane_mask_v2i1_i8(i8 %index, i8 %TC) {
-; CHECK-SVE-LABEL: lane_mask_v2i1_i8:
-; CHECK-SVE: // %bb.0:
-; CHECK-SVE-NEXT: movi d0, #0x0000ff000000ff
-; CHECK-SVE-NEXT: dup v1.2s, w0
-; CHECK-SVE-NEXT: index z2.s, #0, #1
-; CHECK-SVE-NEXT: dup v3.2s, w1
-; CHECK-SVE-NEXT: and v1.8b, v1.8b, v0.8b
-; CHECK-SVE-NEXT: add v1.2s, v1.2s, v2.2s
-; CHECK-SVE-NEXT: and v2.8b, v3.8b, v0.8b
-; CHECK-SVE-NEXT: umin v0.2s, v1.2s, v0.2s
-; CHECK-SVE-NEXT: cmhi v0.2s, v2.2s, v0.2s
-; CHECK-SVE-NEXT: ret
-;
-; CHECK-STREAMING-LABEL: lane_mask_v2i1_i8:
-; CHECK-STREAMING: // %bb.0:
-; CHECK-STREAMING-NEXT: and w8, w0, #0xff
-; CHECK-STREAMING-NEXT: ptrue p0.s, vl2
-; CHECK-STREAMING-NEXT: index z0.s, w8, #1
-; CHECK-STREAMING-NEXT: and w8, w1, #0xff
-; CHECK-STREAMING-NEXT: mov z1.s, w8
-; CHECK-STREAMING-NEXT: umin z0.s, z0.s, #255
-; CHECK-STREAMING-NEXT: cmphi p1.s, p0/z, z1.s, z0.s
-; CHECK-STREAMING-NEXT: mov z0.s, p1/z, #-1 // =0xffffffffffffffff
-; CHECK-STREAMING-NEXT: ret
+; CHECK-LABEL: lane_mask_v2i1_i8:
+; CHECK: // %bb.0:
+; CHECK-NEXT: and w8, w1, #0xff
+; CHECK-NEXT: and w9, w0, #0xff
+; CHECK-NEXT: whilelo p0.s, w9, w8
+; CHECK-NEXT: mov z0.s, p0/z, #-1 // =0xffffffffffffffff
+; CHECK-NEXT: ret
%active.lane.mask = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i8(i8 %index, i8 %TC)
ret <2 x i1> %active.lane.mask
}
@@ -494,3 +430,6 @@ declare <16 x i1> @llvm.get.active.lane.mask.v16i1.i8(i8, i8)
declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i8(i8, i8)
declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i8(i8, i8)
declare <2 x i1> @llvm.get.active.lane.mask.v2i1.i8(i8, i8)
+;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
+; CHECK-STREAMING: {{.*}}
+; CHECK-SVE: {{.*}}
More information about the llvm-commits
mailing list