[llvm] [LLVM]: codegen `llvm.roundeven.v*` for `ARM` (PR #141786)
Folkert de Vries via llvm-commits
llvm-commits at lists.llvm.org
Wed May 28 08:05:54 PDT 2025
https://github.com/folkertdev created https://github.com/llvm/llvm-project/pull/141786
fixes https://github.com/llvm/llvm-project/issues/73588
The aarch64 version of `frintn.ll` notes the intention to auto-upgrade `frintn` to `roundeven`. I haven't been able to figure out how to make that happen though (either for arm or aarch64).
>From 44ea91878d575cdad43cc8812ed6f50e77bd1ab6 Mon Sep 17 00:00:00 2001
From: Folkert de Vries <folkert at folkertdev.nl>
Date: Wed, 28 May 2025 16:54:41 +0200
Subject: [PATCH] [ARM]: codegen `llvm.roundeven.v*`
---
llvm/lib/Target/ARM/ARMISelLowering.cpp | 6 ++
llvm/lib/Target/ARM/ARMInstrVFP.td | 2 +-
llvm/test/CodeGen/ARM/arm32-rounding.ll | 18 ++++++
llvm/test/CodeGen/ARM/frintn.ll | 78 +++++++++++++++++++++++++
4 files changed, 103 insertions(+), 1 deletion(-)
create mode 100644 llvm/test/CodeGen/ARM/frintn.ll
diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
index afbf1b4c55e70..8b65d3eeafa06 100644
--- a/llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -905,6 +905,7 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM,
setOperationAction(ISD::FCEIL, MVT::v2f64, Expand);
setOperationAction(ISD::FTRUNC, MVT::v2f64, Expand);
setOperationAction(ISD::FRINT, MVT::v2f64, Expand);
+ setOperationAction(ISD::FROUNDEVEN, MVT::v2f64, Expand);
setOperationAction(ISD::FNEARBYINT, MVT::v2f64, Expand);
setOperationAction(ISD::FFLOOR, MVT::v2f64, Expand);
setOperationAction(ISD::FMA, MVT::v2f64, Expand);
@@ -927,6 +928,7 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM,
setOperationAction(ISD::FCEIL, MVT::v4f32, Expand);
setOperationAction(ISD::FTRUNC, MVT::v4f32, Expand);
setOperationAction(ISD::FRINT, MVT::v4f32, Expand);
+ setOperationAction(ISD::FROUNDEVEN, MVT::v4f32, Expand);
setOperationAction(ISD::FNEARBYINT, MVT::v4f32, Expand);
setOperationAction(ISD::FFLOOR, MVT::v4f32, Expand);
@@ -945,6 +947,7 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM,
setOperationAction(ISD::FCEIL, MVT::v2f32, Expand);
setOperationAction(ISD::FTRUNC, MVT::v2f32, Expand);
setOperationAction(ISD::FRINT, MVT::v2f32, Expand);
+ setOperationAction(ISD::FROUNDEVEN, MVT::v2f32, Expand);
setOperationAction(ISD::FNEARBYINT, MVT::v2f32, Expand);
setOperationAction(ISD::FFLOOR, MVT::v2f32, Expand);
@@ -1087,6 +1090,7 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM,
setOperationAction(ISD::FCEIL, MVT::f64, Expand);
setOperationAction(ISD::FTRUNC, MVT::f64, Expand);
setOperationAction(ISD::FRINT, MVT::f64, Expand);
+ setOperationAction(ISD::FROUNDEVEN, MVT::f64, Expand);
setOperationAction(ISD::FNEARBYINT, MVT::f64, Expand);
setOperationAction(ISD::FFLOOR, MVT::f64, Expand);
setOperationAction(ISD::SINT_TO_FP, MVT::i32, Custom);
@@ -1534,6 +1538,7 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM,
setOperationAction(ISD::FTRUNC, MVT::f32, Legal);
setOperationAction(ISD::FNEARBYINT, MVT::f32, Legal);
setOperationAction(ISD::FRINT, MVT::f32, Legal);
+ setOperationAction(ISD::FROUNDEVEN, MVT::f32, Legal);
setOperationAction(ISD::FMINNUM, MVT::f32, Legal);
setOperationAction(ISD::FMAXNUM, MVT::f32, Legal);
if (Subtarget->hasNEON()) {
@@ -1550,6 +1555,7 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM,
setOperationAction(ISD::FTRUNC, MVT::f64, Legal);
setOperationAction(ISD::FNEARBYINT, MVT::f64, Legal);
setOperationAction(ISD::FRINT, MVT::f64, Legal);
+ setOperationAction(ISD::FROUNDEVEN, MVT::f64, Legal);
setOperationAction(ISD::FMINNUM, MVT::f64, Legal);
setOperationAction(ISD::FMAXNUM, MVT::f64, Legal);
}
diff --git a/llvm/lib/Target/ARM/ARMInstrVFP.td b/llvm/lib/Target/ARM/ARMInstrVFP.td
index 2ee2cb2fda4a0..483786a88d28c 100644
--- a/llvm/lib/Target/ARM/ARMInstrVFP.td
+++ b/llvm/lib/Target/ARM/ARMInstrVFP.td
@@ -1095,7 +1095,7 @@ multiclass vrint_inst_zrx<string opc, bit op, bit op2, SDPatternOperator node> {
defm VRINTZ : vrint_inst_zrx<"z", 0, 1, ftrunc>;
defm VRINTR : vrint_inst_zrx<"r", 0, 0, fnearbyint>;
-defm VRINTX : vrint_inst_zrx<"x", 1, 0, frint>;
+defm VRINTX : vrint_inst_zrx<"x", 1, 0, any_froundeven>;
multiclass vrint_inst_anpm<string opc, bits<2> rm,
SDPatternOperator node = null_frag> {
diff --git a/llvm/test/CodeGen/ARM/arm32-rounding.ll b/llvm/test/CodeGen/ARM/arm32-rounding.ll
index b0a9f54e42404..3b9aced91143e 100644
--- a/llvm/test/CodeGen/ARM/arm32-rounding.ll
+++ b/llvm/test/CodeGen/ARM/arm32-rounding.ll
@@ -104,6 +104,22 @@ entry:
ret double %call
}
+; CHECK-LABEL: test13
+; CHECK: b roundevenf
+define float @test13(float %a) {
+entry:
+ %round = call float @llvm.roundeven.f32(float %a)
+ ret float %round
+}
+
+; CHECK-LABEL: test14
+; CHECK: b roundeven
+define double @test14(double %a) {
+entry:
+ %round = call double @llvm.roundeven.f64(double %a)
+ ret double %round
+}
+
declare float @floorf(float) nounwind readnone
declare double @floor(double) nounwind readnone
declare float @ceilf(float) nounwind readnone
@@ -116,3 +132,5 @@ declare float @nearbyintf(float) nounwind readnone
declare double @nearbyint(double) nounwind readnone
declare float @rintf(float) nounwind readnone
declare double @rint(double) nounwind readnone
+declare float @llvm.roundeven.f32(float)
+declare double @llvm.roundeven.f64(double)
diff --git a/llvm/test/CodeGen/ARM/frintn.ll b/llvm/test/CodeGen/ARM/frintn.ll
new file mode 100644
index 0000000000000..e801b8ea0a707
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/frintn.ll
@@ -0,0 +1,78 @@
+; RUN: llc -mtriple=armv8 -mattr=+neon %s -o - | FileCheck %s
+
+; The llvm.arm.neon.frintn intrinsic should be auto-upgraded to the
+; target-independent roundeven intrinsic.
+
+define <4 x half> @frintn_4h(<4 x half> %A) nounwind {
+;CHECK-LABEL: frintn_4h:
+;CHECK: bl llvm.arm.neon.frintn.v4f16
+ %tmp3 = call <4 x half> @llvm.arm.neon.frintn.v4f16(<4 x half> %A)
+ ret <4 x half> %tmp3
+}
+
+define <2 x float> @frintn_2s(<2 x float> %A) nounwind {
+;CHECK-LABEL: frintn_2s:
+;CHECK: bl llvm.arm.neon.frintn.v2f32
+ %tmp3 = call <2 x float> @llvm.arm.neon.frintn.v2f32(<2 x float> %A)
+ ret <2 x float> %tmp3
+}
+
+define <4 x float> @frintn_4s(<4 x float> %A) nounwind {
+;CHECK-LABEL: frintn_4s:
+;CHECK: bl llvm.arm.neon.frintn.v4f32
+ %tmp3 = call <4 x float> @llvm.arm.neon.frintn.v4f32(<4 x float> %A)
+ ret <4 x float> %tmp3
+}
+
+define <2 x double> @frintn_2d(<2 x double> %A) nounwind {
+;CHECK-LABEL: frintn_2d:
+;CHECK: bl llvm.arm.neon.frintn.v2f64
+ %tmp3 = call <2 x double> @llvm.arm.neon.frintn.v2f64(<2 x double> %A)
+ ret <2 x double> %tmp3
+}
+
+declare <4 x half> @llvm.arm.neon.frintn.v4f16(<4 x half>) nounwind readnone
+declare <2 x float> @llvm.arm.neon.frintn.v2f32(<2 x float>) nounwind readnone
+declare <4 x float> @llvm.arm.neon.frintn.v4f32(<4 x float>) nounwind readnone
+declare <2 x double> @llvm.arm.neon.frintn.v2f64(<2 x double>) nounwind readnone
+
+define <4 x half> @roundeven_4h(<4 x half> %A) nounwind {
+;CHECK-LABEL: roundeven_4h:
+;CHECK: vcvtb.f16.f32 s0, s0
+;CHECK: vrintx.f32 s2, s2
+;CHECK: vmov r0, s0
+;CHECK: vcvtb.f16.f32 s2, s2
+ %tmp3 = call <4 x half> @llvm.roundeven.v4f16(<4 x half> %A)
+ ret <4 x half> %tmp3
+}
+
+define <2 x float> @roundeven_2s(<2 x float> %A) nounwind {
+;CHECK-LABEL: roundeven_2s:
+;CHECK: vrintx.f32 s3, s1
+;CHECK: vrintx.f32 s2, s0
+ %tmp3 = call <2 x float> @llvm.roundeven.v2f32(<2 x float> %A)
+ ret <2 x float> %tmp3
+}
+
+define <4 x float> @roundeven_4s(<4 x float> %A) nounwind {
+;CHECK-LABEL: roundeven_4s:
+;CHECK: vrintx.f32 s7, s3
+;CHECK: vrintx.f32 s6, s2
+;CHECK: vrintx.f32 s5, s1
+;CHECK: vrintx.f32 s4, s0
+ %tmp3 = call <4 x float> @llvm.roundeven.v4f32(<4 x float> %A)
+ ret <4 x float> %tmp3
+}
+
+define <2 x double> @roundeven_2d(<2 x double> %A) nounwind {
+;CHECK-LABEL: roundeven_2d:
+;CHECK: vrintx.f64 d16, d16
+;CHECK: vrintx.f64 d17, d17
+ %tmp3 = call <2 x double> @llvm.roundeven.v2f64(<2 x double> %A)
+ ret <2 x double> %tmp3
+}
+
+declare <4 x half> @llvm.roundeven.v4f16(<4 x half>) nounwind readnone
+declare <2 x float> @llvm.roundeven.v2f32(<2 x float>) nounwind readnone
+declare <4 x float> @llvm.roundeven.v4f32(<4 x float>) nounwind readnone
+declare <2 x double> @llvm.roundeven.v2f64(<2 x double>) nounwind readnone
More information about the llvm-commits
mailing list