[clang] [llvm] [AArch64] Implement NEON vamin/vamax intrinsics (PR #99041)
Momchil Velikov via llvm-commits
llvm-commits at lists.llvm.org
Wed Aug 28 06:53:47 PDT 2024
https://github.com/momchil-velikov updated https://github.com/llvm/llvm-project/pull/99041
>From 87f1a5aa2215a9fbc1bde7905b2fd5e8d5ff859a 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 1/2] [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 | 5 +
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, 257 insertions(+), 2 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 3098fa67e6a512..6ea597dfb00c16 100644
--- a/clang/include/clang/Basic/arm_neon.td
+++ b/clang/include/clang/Basic/arm_neon.td
@@ -2096,3 +2096,8 @@ let ArchGuard = "defined(__aarch64__) || defined(__arm64ec__)", TargetGuard = "r
def VLDAP1_LANE : WInst<"vldap1_lane", ".(c*!).I", "QUlQlUlldQdPlQPl">;
def VSTL1_LANE : WInst<"vstl1_lane", "v*(.!)I", "QUlQlUlldQdPlQPl">;
}
+
+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 2a733e4d834cfa..aa9b742d476a3c 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -13481,6 +13481,23 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
Int = Intrinsic::aarch64_neon_suqadd;
return EmitNeonCall(CGM.getIntrinsic(Int, Ty), Ops, "vuqadd");
}
+
+ 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 3735bf5222fce3..f778973880703d 100644
--- a/llvm/include/llvm/IR/IntrinsicsAArch64.td
+++ b/llvm/include/llvm/IR/IntrinsicsAArch64.td
@@ -3730,3 +3730,6 @@ def int_aarch64_sve_pmov_to_vector_lane_zeroing : SVE2_Pred_1VectorArg_Intrinsic
def int_aarch64_sme_mopa_nonwide : SME_OuterProduct_Intrinsic;
def int_aarch64_sme_mops_nonwide : SME_OuterProduct_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 ab8251dc830147..59aa88364b1dce 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 2fff6fffcd7c6d..aa900a69006d9e 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -10091,13 +10091,15 @@ 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 f9ae5f35c75dc72b247a8269751070e7953f9aba 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 2/2] [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 59aa88364b1dce..ab8251dc830147 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,
More information about the llvm-commits
mailing list