[clang] [llvm] [AArch64] Implement NEON vamin/vamax intrinsics (PR #99041)
Momchil Velikov via cfe-commits
cfe-commits at lists.llvm.org
Mon Sep 9 02:31:22 PDT 2024
https://github.com/momchil-velikov updated https://github.com/llvm/llvm-project/pull/99041
>From 0cca71a770750e34474d7734c8f803fb31feacee Mon Sep 17 00:00:00 2001
From: Momchil Velikov <momchil.velikov at arm.com>
Date: Mon, 15 Jul 2024 17:50:43 +0100
Subject: [PATCH 1/4] [AArch64] Implement NEON vamin/vamax intrinsics
This patch implements the intrinsics of the form
floatNxM_t vamin[q]_fN(floatNxM_t vn, floatNxM_t vm);
floatNxM_t vamax[q]_fN(floatNxM_t vn, floatNxM_t vm);
as defined in https://github.com/ARM-software/acle/pull/324
Co-authored-by: Hassnaa Hamdi <hassnaa.hamdi at arm.com>
---
clang/include/clang/Basic/arm_neon.td | 7 +-
clang/lib/CodeGen/CGBuiltin.cpp | 17 +++
.../aarch64-neon-faminmax-intrinsics.c | 112 ++++++++++++++++++
llvm/include/llvm/IR/IntrinsicsAArch64.td | 3 +
.../lib/Target/AArch64/AArch64InstrFormats.td | 20 ++++
llvm/lib/Target/AArch64/AArch64InstrInfo.td | 6 +-
llvm/test/CodeGen/AArch64/neon-famin-famax.ll | 96 +++++++++++++++
7 files changed, 258 insertions(+), 3 deletions(-)
create mode 100644 clang/test/CodeGen/aarch64-neon-faminmax-intrinsics.c
create mode 100644 llvm/test/CodeGen/AArch64/neon-famin-famax.ll
diff --git a/clang/include/clang/Basic/arm_neon.td b/clang/include/clang/Basic/arm_neon.td
index 875ec6e90b685b..4f6dc314941200 100644
--- a/clang/include/clang/Basic/arm_neon.td
+++ b/clang/include/clang/Basic/arm_neon.td
@@ -2120,4 +2120,9 @@ let ArchGuard = "defined(__aarch64__)", TargetGuard = "lut" in {
def VLUTI4_BF_X2_Q : SInst<"vluti4_laneq_x2", ".2(<U)I", "Qb",
[ImmCheck<3, ImmCheck0_3>]>;
}
-}
\ No newline at end of file
+}
+
+let ArchGuard = "defined(__aarch64__)", TargetGuard = "faminmax" in {
+ def FAMIN : WInst<"vamin", "...", "fhQdQfQh">;
+ def FAMAX : WInst<"vamax", "...", "fhQdQfQh">;
+}
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index da7a1a55da5313..b0dd299edaf9cc 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -13573,6 +13573,23 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
Int = Intrinsic::aarch64_neon_vluti4q_laneq_x2;
return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vluti4q_laneq_x2");
}
+
+ case NEON::BI__builtin_neon_vamin_f16:
+ case NEON::BI__builtin_neon_vaminq_f16:
+ case NEON::BI__builtin_neon_vamin_f32:
+ case NEON::BI__builtin_neon_vaminq_f32:
+ case NEON::BI__builtin_neon_vaminq_f64: {
+ Int = Intrinsic::aarch64_neon_famin;
+ return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "famin");
+ }
+ case NEON::BI__builtin_neon_vamax_f16:
+ case NEON::BI__builtin_neon_vamaxq_f16:
+ case NEON::BI__builtin_neon_vamax_f32:
+ case NEON::BI__builtin_neon_vamaxq_f32:
+ case NEON::BI__builtin_neon_vamaxq_f64: {
+ Int = Intrinsic::aarch64_neon_famax;
+ return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "famax");
+ }
}
}
diff --git a/clang/test/CodeGen/aarch64-neon-faminmax-intrinsics.c b/clang/test/CodeGen/aarch64-neon-faminmax-intrinsics.c
new file mode 100644
index 00000000000000..631e9738b85c5f
--- /dev/null
+++ b/clang/test/CodeGen/aarch64-neon-faminmax-intrinsics.c
@@ -0,0 +1,112 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5
+#include <arm_neon.h>
+
+// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +faminmax -O3 -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +faminmax -S -O3 -Werror -Wall -o /dev/null %s
+
+// CHECK-LABEL: define dso_local <4 x half> @test_vamin_f16(
+// CHECK-SAME: <4 x half> noundef [[VN:%.*]], <4 x half> noundef [[VM:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[FAMIN2_I:%.*]] = tail call <4 x half> @llvm.aarch64.neon.famin.v4f16(<4 x half> [[VN]], <4 x half> [[VM]])
+// CHECK-NEXT: ret <4 x half> [[FAMIN2_I]]
+//
+float16x4_t test_vamin_f16(float16x4_t vn, float16x4_t vm) {
+ return vamin_f16(vn, vm);
+}
+
+// CHECK-LABEL: define dso_local <8 x half> @test_vaminq_f16(
+// CHECK-SAME: <8 x half> noundef [[VN:%.*]], <8 x half> noundef [[VM:%.*]]) local_unnamed_addr #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[FAMIN2_I:%.*]] = tail call <8 x half> @llvm.aarch64.neon.famin.v8f16(<8 x half> [[VN]], <8 x half> [[VM]])
+// CHECK-NEXT: ret <8 x half> [[FAMIN2_I]]
+//
+float16x8_t test_vaminq_f16(float16x8_t vn, float16x8_t vm) {
+ return vaminq_f16(vn, vm);
+
+}
+
+// CHECK-LABEL: define dso_local <2 x float> @test_vamin_f32(
+// CHECK-SAME: <2 x float> noundef [[VN:%.*]], <2 x float> noundef [[VM:%.*]]) local_unnamed_addr #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[FAMIN2_I:%.*]] = tail call <2 x float> @llvm.aarch64.neon.famin.v2f32(<2 x float> [[VN]], <2 x float> [[VM]])
+// CHECK-NEXT: ret <2 x float> [[FAMIN2_I]]
+//
+float32x2_t test_vamin_f32(float32x2_t vn, float32x2_t vm) {
+ return vamin_f32(vn, vm);
+
+}
+
+// CHECK-LABEL: define dso_local <4 x float> @test_vaminq_f32(
+// CHECK-SAME: <4 x float> noundef [[VN:%.*]], <4 x float> noundef [[VM:%.*]]) local_unnamed_addr #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[FAMIN2_I:%.*]] = tail call <4 x float> @llvm.aarch64.neon.famin.v4f32(<4 x float> [[VN]], <4 x float> [[VM]])
+// CHECK-NEXT: ret <4 x float> [[FAMIN2_I]]
+//
+float32x4_t test_vaminq_f32(float32x4_t vn, float32x4_t vm) {
+ return vaminq_f32(vn, vm);
+
+}
+
+// CHECK-LABEL: define dso_local <2 x double> @test_vaminq_f64(
+// CHECK-SAME: <2 x double> noundef [[VN:%.*]], <2 x double> noundef [[VM:%.*]]) local_unnamed_addr #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[FAMIN2_I:%.*]] = tail call <2 x double> @llvm.aarch64.neon.famin.v2f64(<2 x double> [[VN]], <2 x double> [[VM]])
+// CHECK-NEXT: ret <2 x double> [[FAMIN2_I]]
+//
+float64x2_t test_vaminq_f64(float64x2_t vn, float64x2_t vm) {
+ return vaminq_f64(vn, vm);
+}
+
+
+// CHECK-LABEL: define dso_local <4 x half> @test_vamax_f16(
+// CHECK-SAME: <4 x half> noundef [[VN:%.*]], <4 x half> noundef [[VM:%.*]]) local_unnamed_addr #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[FAMAX2_I:%.*]] = tail call <4 x half> @llvm.aarch64.neon.famax.v4f16(<4 x half> [[VN]], <4 x half> [[VM]])
+// CHECK-NEXT: ret <4 x half> [[FAMAX2_I]]
+//
+float16x4_t test_vamax_f16(float16x4_t vn, float16x4_t vm) {
+ return vamax_f16(vn, vm);
+}
+
+// CHECK-LABEL: define dso_local <8 x half> @test_vamaxq_f16(
+// CHECK-SAME: <8 x half> noundef [[VN:%.*]], <8 x half> noundef [[VM:%.*]]) local_unnamed_addr #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[FAMAX2_I:%.*]] = tail call <8 x half> @llvm.aarch64.neon.famax.v8f16(<8 x half> [[VN]], <8 x half> [[VM]])
+// CHECK-NEXT: ret <8 x half> [[FAMAX2_I]]
+//
+float16x8_t test_vamaxq_f16(float16x8_t vn, float16x8_t vm) {
+ return vamaxq_f16(vn, vm);
+
+}
+
+// CHECK-LABEL: define dso_local <2 x float> @test_vamax_f32(
+// CHECK-SAME: <2 x float> noundef [[VN:%.*]], <2 x float> noundef [[VM:%.*]]) local_unnamed_addr #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[FAMAX2_I:%.*]] = tail call <2 x float> @llvm.aarch64.neon.famax.v2f32(<2 x float> [[VN]], <2 x float> [[VM]])
+// CHECK-NEXT: ret <2 x float> [[FAMAX2_I]]
+//
+float32x2_t test_vamax_f32(float32x2_t vn, float32x2_t vm) {
+ return vamax_f32(vn, vm);
+
+}
+
+// CHECK-LABEL: define dso_local <4 x float> @test_vamaxq_f32(
+// CHECK-SAME: <4 x float> noundef [[VN:%.*]], <4 x float> noundef [[VM:%.*]]) local_unnamed_addr #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[FAMAX2_I:%.*]] = tail call <4 x float> @llvm.aarch64.neon.famax.v4f32(<4 x float> [[VN]], <4 x float> [[VM]])
+// CHECK-NEXT: ret <4 x float> [[FAMAX2_I]]
+//
+float32x4_t test_vamaxq_f32(float32x4_t vn, float32x4_t vm) {
+ return vamaxq_f32(vn, vm);
+
+}
+
+// CHECK-LABEL: define dso_local <2 x double> @test_vamaxq_f64(
+// CHECK-SAME: <2 x double> noundef [[VN:%.*]], <2 x double> noundef [[VM:%.*]]) local_unnamed_addr #[[ATTR0]] {
+// CHECK-NEXT: [[ENTRY:.*:]]
+// CHECK-NEXT: [[FAMAX2_I:%.*]] = tail call <2 x double> @llvm.aarch64.neon.famax.v2f64(<2 x double> [[VN]], <2 x double> [[VM]])
+// CHECK-NEXT: ret <2 x double> [[FAMAX2_I]]
+//
+float64x2_t test_vamaxq_f64(float64x2_t vn, float64x2_t vm) {
+ return vamaxq_f64(vn, vm);
+}
diff --git a/llvm/include/llvm/IR/IntrinsicsAArch64.td b/llvm/include/llvm/IR/IntrinsicsAArch64.td
index 8ac1d67e162f70..8ffa2d0878e116 100644
--- a/llvm/include/llvm/IR/IntrinsicsAArch64.td
+++ b/llvm/include/llvm/IR/IntrinsicsAArch64.td
@@ -3801,3 +3801,6 @@ def int_aarch64_sve_famax_u : AdvSIMD_Pred2VectorArg_Intrinsic;
def int_aarch64_sve_famin : AdvSIMD_Pred2VectorArg_Intrinsic;
def int_aarch64_sve_famin_u : AdvSIMD_Pred2VectorArg_Intrinsic;
+// Neon absolute maximum and minimum
+def int_aarch64_neon_famax : AdvSIMD_2VectorArg_Intrinsic;
+def int_aarch64_neon_famin : AdvSIMD_2VectorArg_Intrinsic;
diff --git a/llvm/lib/Target/AArch64/AArch64InstrFormats.td b/llvm/lib/Target/AArch64/AArch64InstrFormats.td
index 16002011aedfbe..1777f65e378603 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrFormats.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrFormats.td
@@ -5992,6 +5992,26 @@ multiclass SIMDThreeSameVectorFP<bit U, bit S, bits<3> opc,
[(set (v2f64 V128:$Rd), (OpNode (v2f64 V128:$Rn), (v2f64 V128:$Rm)))]>;
}
+let mayRaiseFPException = 1, Uses = [FPCR] in
+multiclass SIMDThreeVectorFP<bit U, bit S, bits<3> opc,
+ string asm, SDPatternOperator OpNode> {
+ def v4f16 : BaseSIMDThreeSameVector<0, U, {S,0b10}, {0b00,opc}, V64,
+ asm, ".4h",
+ [(set (v4f16 V64:$Rd), (OpNode (v4f16 V64:$Rn), (v4i16 V64:$Rm)))]>;
+ def v8f16 : BaseSIMDThreeSameVector<1, U, {S,0b10}, {0b00,opc}, V128,
+ asm, ".8h",
+ [(set (v8f16 V128:$Rd), (OpNode (v8f16 V128:$Rn), (v8i16 V128:$Rm)))]>;
+ def v2f32 : BaseSIMDThreeSameVector<0, U, {S,0b01}, {0b11,opc}, V64,
+ asm, ".2s",
+ [(set (v2f32 V64:$Rd), (OpNode (v2f32 V64:$Rn), (v2i32 V64:$Rm)))]>;
+ def v4f32 : BaseSIMDThreeSameVector<1, U, {S,0b01}, {0b11,opc}, V128,
+ asm, ".4s",
+ [(set (v4f32 V128:$Rd), (OpNode (v4f32 V128:$Rn), (v4i32 V128:$Rm)))]>;
+ def v2f64 : BaseSIMDThreeSameVector<1, U, {S,0b11}, {0b11,opc}, V128,
+ asm, ".2d",
+ [(set (v2f64 V128:$Rd), (OpNode (v2f64 V128:$Rn), (v2i64 V128:$Rm)))]>;
+}
+
let mayRaiseFPException = 1, Uses = [FPCR] in
multiclass SIMDThreeSameVectorFPCmp<bit U, bit S, bits<3> opc,
string asm,
diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.td b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
index ccef85bfaa8afc..7790cabd6db138 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -10134,13 +10134,15 @@ let Uses = [FPMR, FPCR], Predicates = [HasFP8] in {
// fminimum(abs(a), abs(b)) -> famin(a, b)
// fminnum[nnan](abs(a), abs(b)) -> famin(a, b)
def AArch64famin : PatFrags<(ops node:$Rn, node:$Rm),
- [(fminimum (fabs node:$Rn), (fabs node:$Rm)),
+ [(int_aarch64_neon_famin node:$Rn, node:$Rm),
+ (fminimum (fabs node:$Rn), (fabs node:$Rm)),
(fminnum_nnan (fabs node:$Rn), (fabs node:$Rm))]>;
// fmaximum(abs(a), abs(b)) -> famax(a, b)
// fmaxnum[nnan](abs(a), abs(b)) -> famax(a, b)
def AArch64famax : PatFrags<(ops node:$Rn, node:$Rm),
- [(fmaximum (fabs node:$Rn), (fabs node:$Rm)),
+ [(int_aarch64_neon_famax node:$Rn, node:$Rm),
+ (fmaximum (fabs node:$Rn), (fabs node:$Rm)),
(fmaxnum_nnan (fabs node:$Rn), (fabs node:$Rm))]>;
let Predicates = [HasNEON, HasFAMINMAX] in {
diff --git a/llvm/test/CodeGen/AArch64/neon-famin-famax.ll b/llvm/test/CodeGen/AArch64/neon-famin-famax.ll
new file mode 100644
index 00000000000000..97fb0a08914524
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/neon-famin-famax.ll
@@ -0,0 +1,96 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc < %s | FileCheck %s
+
+target triple = "aarch64-linux"
+
+define <4 x half> @test_famin_f16(<4 x half> %vn, <4 x half> %vm) #0 {
+; CHECK-LABEL: test_famin_f16:
+; CHECK: // %bb.0:
+; CHECK-NEXT: famin v0.4h, v0.4h, v1.4h
+; CHECK-NEXT: ret
+ %res = call <4 x half> @llvm.aarch64.neon.famin.v4f16(<4 x half> %vn, <4 x half> %vm)
+ ret <4 x half> %res
+}
+
+define <8 x half> @test_famin2_f16(<8 x half> %vn, <8 x half> %vm) #0 {
+; CHECK-LABEL: test_famin2_f16:
+; CHECK: // %bb.0:
+; CHECK-NEXT: famin v0.8h, v0.8h, v1.8h
+; CHECK-NEXT: ret
+ %res = call <8 x half> @llvm.aarch64.neon.famin.v8f16(<8 x half> %vn, <8 x half> %vm)
+ ret <8 x half> %res
+}
+
+define <2 x float> @test_famin_f32(<2 x float> %vn, <2 x float> %vm) #0 {
+; CHECK-LABEL: test_famin_f32:
+; CHECK: // %bb.0:
+; CHECK-NEXT: famin v0.2s, v0.2s, v1.2s
+; CHECK-NEXT: ret
+ %res = call <2 x float> @llvm.aarch64.neon.famin.v2f32(<2 x float> %vn, <2 x float> %vm)
+ ret <2 x float> %res
+}
+
+define <4 x float> @test_famin2_f32(<4 x float> %vn, <4 x float> %vm) #0 {
+; CHECK-LABEL: test_famin2_f32:
+; CHECK: // %bb.0:
+; CHECK-NEXT: famin v0.4s, v0.4s, v1.4s
+; CHECK-NEXT: ret
+ %res = call <4 x float> @llvm.aarch64.neon.famin.v4f32(<4 x float> %vn, <4 x float> %vm)
+ ret <4 x float> %res
+}
+
+define <2 x double> @test_famin_f64(<2 x double> %vn, <2 x double> %vm) #0 {
+; CHECK-LABEL: test_famin_f64:
+; CHECK: // %bb.0:
+; CHECK-NEXT: famin v0.2d, v0.2d, v1.2d
+; CHECK-NEXT: ret
+ %res = call <2 x double> @llvm.aarch64.neon.famin.v2f64(<2 x double> %vn, <2 x double> %vm)
+ ret <2 x double> %res
+}
+
+define <4 x half> @test_famax_f16(<4 x half> %vn, <4 x half> %vm) #0 {
+; CHECK-LABEL: test_famax_f16:
+; CHECK: // %bb.0:
+; CHECK-NEXT: famax v0.4h, v0.4h, v1.4h
+; CHECK-NEXT: ret
+ %res = call <4 x half> @llvm.aarch64.neon.famax.v4f16(<4 x half> %vn, <4 x half> %vm)
+ ret <4 x half> %res
+}
+
+define <8 x half> @test_famax2_f16(<8 x half> %vn, <8 x half> %vm) #0 {
+; CHECK-LABEL: test_famax2_f16:
+; CHECK: // %bb.0:
+; CHECK-NEXT: famax v0.8h, v0.8h, v1.8h
+; CHECK-NEXT: ret
+ %res = call <8 x half> @llvm.aarch64.neon.famax.v8f16(<8 x half> %vn, <8 x half> %vm)
+ ret <8 x half> %res
+}
+
+define <2 x float> @test_famax_f32(<2 x float> %vn, <2 x float> %vm) #0 {
+; CHECK-LABEL: test_famax_f32:
+; CHECK: // %bb.0:
+; CHECK-NEXT: famax v0.2s, v0.2s, v1.2s
+; CHECK-NEXT: ret
+ %res = call <2 x float> @llvm.aarch64.neon.famax.v2f32(<2 x float> %vn, <2 x float> %vm)
+ ret <2 x float> %res
+}
+
+define <4 x float> @test_famax2_f32(<4 x float> %vn, <4 x float> %vm) #0 {
+; CHECK-LABEL: test_famax2_f32:
+; CHECK: // %bb.0:
+; CHECK-NEXT: famax v0.4s, v0.4s, v1.4s
+; CHECK-NEXT: ret
+ %res = call <4 x float> @llvm.aarch64.neon.famax.v4f32(<4 x float> %vn, <4 x float> %vm)
+ ret <4 x float> %res
+}
+
+define <2 x double> @test_famax_f64(<2 x double> %vn, <2 x double> %vm) #0 {
+; CHECK-LABEL: test_famax_f64:
+; CHECK: // %bb.0:
+; CHECK-NEXT: famax v0.2d, v0.2d, v1.2d
+; CHECK-NEXT: ret
+ %res = call <2 x double> @llvm.aarch64.neon.famax.v2f64(<2 x double> %vn, <2 x double> %vm)
+ ret <2 x double> %res
+}
+
+attributes #0 = { "target-features"="+neon,+faminmax" }
>From 67fe9899be62394d46390a5b25c29c5029d72116 Mon Sep 17 00:00:00 2001
From: Momchil Velikov <momchil.velikov at arm.com>
Date: Fri, 26 Jul 2024 16:03:14 +0100
Subject: [PATCH 2/4] [fixup] Remove unused tablegen class
---
.../lib/Target/AArch64/AArch64InstrFormats.td | 20 -------------------
1 file changed, 20 deletions(-)
diff --git a/llvm/lib/Target/AArch64/AArch64InstrFormats.td b/llvm/lib/Target/AArch64/AArch64InstrFormats.td
index 1777f65e378603..16002011aedfbe 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrFormats.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrFormats.td
@@ -5992,26 +5992,6 @@ multiclass SIMDThreeSameVectorFP<bit U, bit S, bits<3> opc,
[(set (v2f64 V128:$Rd), (OpNode (v2f64 V128:$Rn), (v2f64 V128:$Rm)))]>;
}
-let mayRaiseFPException = 1, Uses = [FPCR] in
-multiclass SIMDThreeVectorFP<bit U, bit S, bits<3> opc,
- string asm, SDPatternOperator OpNode> {
- def v4f16 : BaseSIMDThreeSameVector<0, U, {S,0b10}, {0b00,opc}, V64,
- asm, ".4h",
- [(set (v4f16 V64:$Rd), (OpNode (v4f16 V64:$Rn), (v4i16 V64:$Rm)))]>;
- def v8f16 : BaseSIMDThreeSameVector<1, U, {S,0b10}, {0b00,opc}, V128,
- asm, ".8h",
- [(set (v8f16 V128:$Rd), (OpNode (v8f16 V128:$Rn), (v8i16 V128:$Rm)))]>;
- def v2f32 : BaseSIMDThreeSameVector<0, U, {S,0b01}, {0b11,opc}, V64,
- asm, ".2s",
- [(set (v2f32 V64:$Rd), (OpNode (v2f32 V64:$Rn), (v2i32 V64:$Rm)))]>;
- def v4f32 : BaseSIMDThreeSameVector<1, U, {S,0b01}, {0b11,opc}, V128,
- asm, ".4s",
- [(set (v4f32 V128:$Rd), (OpNode (v4f32 V128:$Rn), (v4i32 V128:$Rm)))]>;
- def v2f64 : BaseSIMDThreeSameVector<1, U, {S,0b11}, {0b11,opc}, V128,
- asm, ".2d",
- [(set (v2f64 V128:$Rd), (OpNode (v2f64 V128:$Rn), (v2i64 V128:$Rm)))]>;
-}
-
let mayRaiseFPException = 1, Uses = [FPCR] in
multiclass SIMDThreeSameVectorFPCmp<bit U, bit S, bits<3> opc,
string asm,
>From 634302b8de24917675e5476ad5e9669899c00e15 Mon Sep 17 00:00:00 2001
From: Momchil Velikov <momchil.velikov at arm.com>
Date: Wed, 4 Sep 2024 18:20:36 +0100
Subject: [PATCH 3/4] [fixup] Add a REQUIRES clause to a test and rebase
---
clang/test/CodeGen/aarch64-neon-faminmax-intrinsics.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/clang/test/CodeGen/aarch64-neon-faminmax-intrinsics.c b/clang/test/CodeGen/aarch64-neon-faminmax-intrinsics.c
index 631e9738b85c5f..3dc5afe68e7f46 100644
--- a/clang/test/CodeGen/aarch64-neon-faminmax-intrinsics.c
+++ b/clang/test/CodeGen/aarch64-neon-faminmax-intrinsics.c
@@ -1,9 +1,11 @@
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5
-#include <arm_neon.h>
-
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +faminmax -O3 -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple aarch64-none-linux-gnu -target-feature +neon -target-feature +faminmax -S -O3 -Werror -Wall -o /dev/null %s
+// REQUIRES: aarch64-registered-target
+
+#include <arm_neon.h>
+
// CHECK-LABEL: define dso_local <4 x half> @test_vamin_f16(
// CHECK-SAME: <4 x half> noundef [[VN:%.*]], <4 x half> noundef [[VM:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: [[ENTRY:.*:]]
>From 65101a0f3d879c24e71952f3342f42f82fa48732 Mon Sep 17 00:00:00 2001
From: Momchil Velikov <momchil.velikov at arm.com>
Date: Thu, 5 Sep 2024 12:16:43 +0100
Subject: [PATCH 4/4] [fixup] Add neon feature requirement
---
clang/include/clang/Basic/arm_neon.td | 2 +-
.../aarch64-neon-faminmax-intrinsics.c | 7 ----
.../Sema/aarch64-neon-faminmax-no-faminmax.c | 35 +++++++++++++++++++
.../test/Sema/aarch64-neon-faminmax-no-neon.c | 34 ++++++++++++++++++
4 files changed, 70 insertions(+), 8 deletions(-)
create mode 100644 clang/test/Sema/aarch64-neon-faminmax-no-faminmax.c
create mode 100644 clang/test/Sema/aarch64-neon-faminmax-no-neon.c
diff --git a/clang/include/clang/Basic/arm_neon.td b/clang/include/clang/Basic/arm_neon.td
index 4f6dc314941200..92f39744f3d084 100644
--- a/clang/include/clang/Basic/arm_neon.td
+++ b/clang/include/clang/Basic/arm_neon.td
@@ -2122,7 +2122,7 @@ let ArchGuard = "defined(__aarch64__)", TargetGuard = "lut" in {
}
}
-let ArchGuard = "defined(__aarch64__)", TargetGuard = "faminmax" in {
+let ArchGuard = "defined(__aarch64__)", TargetGuard = "neon,faminmax" in {
def FAMIN : WInst<"vamin", "...", "fhQdQfQh">;
def FAMAX : WInst<"vamax", "...", "fhQdQfQh">;
}
diff --git a/clang/test/CodeGen/aarch64-neon-faminmax-intrinsics.c b/clang/test/CodeGen/aarch64-neon-faminmax-intrinsics.c
index 3dc5afe68e7f46..3ae98b5723d7c8 100644
--- a/clang/test/CodeGen/aarch64-neon-faminmax-intrinsics.c
+++ b/clang/test/CodeGen/aarch64-neon-faminmax-intrinsics.c
@@ -24,7 +24,6 @@ float16x4_t test_vamin_f16(float16x4_t vn, float16x4_t vm) {
//
float16x8_t test_vaminq_f16(float16x8_t vn, float16x8_t vm) {
return vaminq_f16(vn, vm);
-
}
// CHECK-LABEL: define dso_local <2 x float> @test_vamin_f32(
@@ -35,7 +34,6 @@ float16x8_t test_vaminq_f16(float16x8_t vn, float16x8_t vm) {
//
float32x2_t test_vamin_f32(float32x2_t vn, float32x2_t vm) {
return vamin_f32(vn, vm);
-
}
// CHECK-LABEL: define dso_local <4 x float> @test_vaminq_f32(
@@ -46,7 +44,6 @@ float32x2_t test_vamin_f32(float32x2_t vn, float32x2_t vm) {
//
float32x4_t test_vaminq_f32(float32x4_t vn, float32x4_t vm) {
return vaminq_f32(vn, vm);
-
}
// CHECK-LABEL: define dso_local <2 x double> @test_vaminq_f64(
@@ -59,7 +56,6 @@ float64x2_t test_vaminq_f64(float64x2_t vn, float64x2_t vm) {
return vaminq_f64(vn, vm);
}
-
// CHECK-LABEL: define dso_local <4 x half> @test_vamax_f16(
// CHECK-SAME: <4 x half> noundef [[VN:%.*]], <4 x half> noundef [[VM:%.*]]) local_unnamed_addr #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
@@ -78,7 +74,6 @@ float16x4_t test_vamax_f16(float16x4_t vn, float16x4_t vm) {
//
float16x8_t test_vamaxq_f16(float16x8_t vn, float16x8_t vm) {
return vamaxq_f16(vn, vm);
-
}
// CHECK-LABEL: define dso_local <2 x float> @test_vamax_f32(
@@ -89,7 +84,6 @@ float16x8_t test_vamaxq_f16(float16x8_t vn, float16x8_t vm) {
//
float32x2_t test_vamax_f32(float32x2_t vn, float32x2_t vm) {
return vamax_f32(vn, vm);
-
}
// CHECK-LABEL: define dso_local <4 x float> @test_vamaxq_f32(
@@ -100,7 +94,6 @@ float32x2_t test_vamax_f32(float32x2_t vn, float32x2_t vm) {
//
float32x4_t test_vamaxq_f32(float32x4_t vn, float32x4_t vm) {
return vamaxq_f32(vn, vm);
-
}
// CHECK-LABEL: define dso_local <2 x double> @test_vamaxq_f64(
diff --git a/clang/test/Sema/aarch64-neon-faminmax-no-faminmax.c b/clang/test/Sema/aarch64-neon-faminmax-no-faminmax.c
new file mode 100644
index 00000000000000..588f69cc7750b3
--- /dev/null
+++ b/clang/test/Sema/aarch64-neon-faminmax-no-faminmax.c
@@ -0,0 +1,35 @@
+// RUN: %clang_cc1 -triple aarch64-linux-gnu -target-feature +neon -emit-llvm -verify %s -o /dev/null
+
+// REQUIRES: aarch64-registered-target
+
+#include <arm_neon.h>
+
+float16x4_t a16x4, b16x4;
+float16x8_t a16x8, b16x8;
+float32x2_t a32x2, b32x2;
+float32x4_t a32x4, b32x4;
+float64x2_t a64x2, b64x2;
+
+
+void test() {
+ (void) vamin_f16 (a16x4, b16x4);
+// expected-error at -1 {{always_inline function 'vamin_f16' requires target feature 'faminmax'}}
+ (void) vaminq_f16(a16x8, b16x8);
+// expected-error at -1 {{always_inline function 'vaminq_f16' requires target feature 'faminmax'}}
+ (void) vamin_f32 (a32x2, b32x2);
+// expected-error at -1 {{always_inline function 'vamin_f32' requires target feature 'faminmax'}}
+ (void) vaminq_f32(a32x4, b32x4);
+// expected-error at -1 {{always_inline function 'vaminq_f32' requires target feature 'faminmax'}}
+ (void) vaminq_f64(a64x2, b64x2);
+// expected-error at -1 {{always_inline function 'vaminq_f64' requires target feature 'faminmax'}}
+ (void) vamax_f16 (a16x4, b16x4);
+// expected-error at -1 {{always_inline function 'vamax_f16' requires target feature 'faminmax'}}
+ (void) vamaxq_f16(a16x8, b16x8);
+// expected-error at -1 {{always_inline function 'vamaxq_f16' requires target feature 'faminmax'}}
+ (void) vamax_f32 (a32x2, b32x2);
+// expected-error at -1 {{always_inline function 'vamax_f32' requires target feature 'faminmax'}}
+ (void) vamaxq_f32(a32x4, b32x4);
+// expected-error at -1 {{always_inline function 'vamaxq_f32' requires target feature 'faminmax'}}
+ (void) vamaxq_f64(a64x2, b64x2);
+// expected-error at -1 {{always_inline function 'vamaxq_f64' requires target feature 'faminmax'}}
+}
diff --git a/clang/test/Sema/aarch64-neon-faminmax-no-neon.c b/clang/test/Sema/aarch64-neon-faminmax-no-neon.c
new file mode 100644
index 00000000000000..a210e8398d9b74
--- /dev/null
+++ b/clang/test/Sema/aarch64-neon-faminmax-no-neon.c
@@ -0,0 +1,34 @@
+// RUN: %clang_cc1 -triple aarch64-linux-gnu -target-feature +faminmax -emit-llvm -verify %s -o /dev/null
+
+// REQUIRES: aarch64-registered-target
+
+#include <arm_neon.h>
+
+float16x4_t a16x4, b16x4;
+float16x8_t a16x8, b16x8;
+float32x2_t a32x2, b32x2;
+float32x4_t a32x4, b32x4;
+float64x2_t a64x2, b64x2;
+
+void test () {
+ (void) vamin_f16 (a16x4, b16x4);
+// expected-error at -1 {{always_inline function 'vamin_f16' requires target feature 'neon'}}
+ (void) vaminq_f16(a16x8, b16x8);
+// expected-error at -1 {{always_inline function 'vaminq_f16' requires target feature 'neon'}}
+ (void) vamin_f32 (a32x2, b32x2);
+// expected-error at -1 {{always_inline function 'vamin_f32' requires target feature 'neon'}}
+ (void) vaminq_f32(a32x4, b32x4);
+// expected-error at -1 {{always_inline function 'vaminq_f32' requires target feature 'neon'}}
+ (void) vaminq_f64(a64x2, b64x2);
+// expected-error at -1 {{always_inline function 'vaminq_f64' requires target feature 'neon'}}
+ (void) vamax_f16 (a16x4, b16x4);
+// expected-error at -1 {{always_inline function 'vamax_f16' requires target feature 'neon'}}
+ (void) vamaxq_f16(a16x8, b16x8);
+// expected-error at -1 {{always_inline function 'vamaxq_f16' requires target feature 'neon'}}
+ (void) vamax_f32 (a32x2, b32x2);
+// expected-error at -1 {{always_inline function 'vamax_f32' requires target feature 'neon'}}
+ (void) vamaxq_f32(a32x4, b32x4);
+// expected-error at -1 {{always_inline function 'vamaxq_f32' requires target feature 'neon'}}
+ (void) vamaxq_f64(a64x2, b64x2);
+// expected-error at -1 {{always_inline function 'vamaxq_f64' requires target feature 'neon'}}
+}
More information about the cfe-commits
mailing list