[llvm-branch-commits] [llvm] PR for llvm/llvm-project#79860 (PR #79969)

[via llvm-branch-commits]

https://github.com/llvmbot updated https://github.com/llvm/llvm-project/pull/79969

>From 692f465456fa9e3690bd9b9b28a789f3979ffbe0 Mon Sep 17 00:00:00 2001
From: David Green <david.green at arm.com>
Date: Mon, 29 Jan 2024 16:46:22 +0000
Subject: [PATCH] [AArch64] Don't generate neon integer complex numbers with
 +sve2. NFC (#79829)

The condition for allowing integer complex number support could also
allow neon fixed length complex numbers if +sve2 was specified. This
tightens the condition to only allow integer complex number support for
scalable vectors.

We could generalize this in the future to generate SVE intrinsics for
fixed-length vectors, but for the moment this opts for the simpler fix.

(cherry picked from commit 9520773c46777adbc1d489f831d6c93b8287ca0e)
---
 .../Target/AArch64/AArch64ISelLowering.cpp    |  4 +--
 .../AArch64/complex-deinterleaving-f16-add.ll | 27 +++++++++++++++++++
 2 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index a59b1f2ec3c1c..e97f5e3220148 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -26915,7 +26915,7 @@ bool AArch64TargetLowering::isComplexDeinterleavingOperationSupported(
     return false;
 
   // If the vector is scalable, SVE is enabled, implying support for complex
-  // numbers. Otherwirse, we need to ensure complex number support is avaialble
+  // numbers. Otherwise, we need to ensure complex number support is available
   if (!VTy->isScalableTy() && !Subtarget->hasComplxNum())
     return false;
 
@@ -26931,7 +26931,7 @@ bool AArch64TargetLowering::isComplexDeinterleavingOperationSupported(
       !llvm::isPowerOf2_32(VTyWidth))
     return false;
 
-  if (ScalarTy->isIntegerTy() && Subtarget->hasSVE2()) {
+  if (ScalarTy->isIntegerTy() && Subtarget->hasSVE2() && VTy->isScalableTy()) {
     unsigned ScalarWidth = ScalarTy->getScalarSizeInBits();
     return 8 <= ScalarWidth && ScalarWidth <= 64;
   }
diff --git a/llvm/test/CodeGen/AArch64/complex-deinterleaving-f16-add.ll b/llvm/test/CodeGen/AArch64/complex-deinterleaving-f16-add.ll
index 93497f38063d2..7b8448de2331b 100644
--- a/llvm/test/CodeGen/AArch64/complex-deinterleaving-f16-add.ll
+++ b/llvm/test/CodeGen/AArch64/complex-deinterleaving-f16-add.ll
@@ -1,6 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc < %s --mattr=+complxnum,+neon,+fullfp16 -o - | FileCheck %s
 ; RUN: llc < %s --mattr=+complxnum,+neon,+fullfp16,+sve -o - | FileCheck %s
+; RUN: llc < %s --mattr=+complxnum,+neon,+fullfp16,+sve2 -o - | FileCheck %s
 
 target triple = "aarch64"
 
@@ -158,6 +159,32 @@ entry:
   ret <16 x half> %interleaved.vec
 }
 
+
+; Expected not to transform as it is integer
+define <16 x i16> @complex_add_v16i16(<16 x i16> %a, <16 x i16> %b) {
+; CHECK-LABEL: complex_add_v16i16:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    uzp1 v4.8h, v2.8h, v3.8h
+; CHECK-NEXT:    uzp1 v5.8h, v0.8h, v1.8h
+; CHECK-NEXT:    uzp2 v0.8h, v0.8h, v1.8h
+; CHECK-NEXT:    uzp2 v1.8h, v2.8h, v3.8h
+; CHECK-NEXT:    sub v2.8h, v4.8h, v0.8h
+; CHECK-NEXT:    add v1.8h, v1.8h, v5.8h
+; CHECK-NEXT:    zip1 v0.8h, v2.8h, v1.8h
+; CHECK-NEXT:    zip2 v1.8h, v2.8h, v1.8h
+; CHECK-NEXT:    ret
+entry:
+  %a.real = shufflevector <16 x i16> %a, <16 x i16> zeroinitializer, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
+  %a.imag = shufflevector <16 x i16> %a, <16 x i16> zeroinitializer, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
+  %b.real = shufflevector <16 x i16> %b, <16 x i16> zeroinitializer, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
+  %b.imag = shufflevector <16 x i16> %b, <16 x i16> zeroinitializer, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
+  %0 = sub <8 x i16> %b.real, %a.imag
+  %1 = add <8 x i16> %b.imag, %a.real
+  %interleaved.vec = shufflevector <8 x i16> %0, <8 x i16> %1, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
+  ret <16 x i16> %interleaved.vec
+}
+
+
 declare { <2 x half>, <2 x half> } @llvm.experimental.vector.deinterleave2.v4f16(<4 x half>)
 declare <4 x half> @llvm.experimental.vector.interleave2.v4f16(<2 x half>, <2 x half>)