[llvm] [AArch64][GlobalISel] SIMD fpcvt codegen for rounding nodes (PR #165546)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Nov 20 02:37:53 PST 2025
https://github.com/Lukacma updated https://github.com/llvm/llvm-project/pull/165546
>From 63779461f28cda3de9161308f89ee1f409a5434d Mon Sep 17 00:00:00 2001
From: Marian Lukac <Marian.Lukac at arm.com>
Date: Wed, 29 Oct 2025 11:48:30 +0000
Subject: [PATCH 1/2] [AArch64][GlobalISel] SIMD fpcvt codegen for rounding
nodes
---
llvm/lib/Target/AArch64/AArch64InstrInfo.td | 73 +++
.../AArch64/GISel/AArch64RegisterBankInfo.cpp | 18 +-
.../AArch64/GlobalISel/regbank-llround.mir | 4 +-
.../AArch64/GlobalISel/regbank-lround.mir | 4 +-
.../AArch64/arm64-cvt-simd-round-rint.ll | 428 ++++++++++++++++++
llvm/test/CodeGen/AArch64/vector-lrint.ll | 18 +-
6 files changed, 522 insertions(+), 23 deletions(-)
create mode 100644 llvm/test/CodeGen/AArch64/arm64-cvt-simd-round-rint.ll
diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.td b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
index b9e299ef37454..f765c6e037176 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -6799,6 +6799,79 @@ defm : FPToIntegerPats<fp_to_uint, fp_to_uint_sat, fp_to_uint_sat_gi, ftrunc, "F
defm : FPToIntegerPats<fp_to_sint, fp_to_sint_sat, fp_to_sint_sat_gi, fround, "FCVTAS">;
defm : FPToIntegerPats<fp_to_uint, fp_to_uint_sat, fp_to_uint_sat_gi, fround, "FCVTAU">;
+// For global-isel we can use register classes to determine
+// which FCVT instruction to use.
+let Predicates = [HasFPRCVT] in {
+def : Pat<(i64 (any_lround f32:$Rn)),
+ (FCVTASDSr f32:$Rn)>;
+def : Pat<(i64 (any_llround f32:$Rn)),
+ (FCVTASDSr f32:$Rn)>;
+}
+def : Pat<(i64 (any_lround f64:$Rn)),
+ (FCVTASv1i64 f64:$Rn)>;
+def : Pat<(i64 (any_llround f64:$Rn)),
+ (FCVTASv1i64 f64:$Rn)>;
+
+let Predicates = [HasFPRCVT] in {
+ def : Pat<(f32 (bitconvert (i32 (any_lround f16:$Rn)))),
+ (FCVTASSHr f16:$Rn)>;
+ def : Pat<(f64 (bitconvert (i64 (any_lround f16:$Rn)))),
+ (FCVTASDHr f16:$Rn)>;
+ def : Pat<(f64 (bitconvert (i64 (any_llround f16:$Rn)))),
+ (FCVTASDHr f16:$Rn)>;
+ def : Pat<(f64 (bitconvert (i64 (any_lround f32:$Rn)))),
+ (FCVTASDSr f32:$Rn)>;
+ def : Pat<(f32 (bitconvert (i32 (any_lround f64:$Rn)))),
+ (FCVTASSDr f64:$Rn)>;
+ def : Pat<(f64 (bitconvert (i64 (any_llround f32:$Rn)))),
+ (FCVTASDSr f32:$Rn)>;
+}
+def : Pat<(f32 (bitconvert (i32 (any_lround f32:$Rn)))),
+ (FCVTASv1i32 f32:$Rn)>;
+def : Pat<(f64 (bitconvert (i64 (any_lround f64:$Rn)))),
+ (FCVTASv1i64 f64:$Rn)>;
+def : Pat<(f64 (bitconvert (i64 (any_llround f64:$Rn)))),
+ (FCVTASv1i64 f64:$Rn)>;
+
+// For global-isel we can use register classes to determine
+// which FCVT instruction to use.
+let Predicates = [HasFPRCVT] in {
+def : Pat<(i64 (any_lrint f16:$Rn)),
+ (FCVTZSDHr (FRINTXHr f16:$Rn))>;
+def : Pat<(i64 (any_llrint f16:$Rn)),
+ (FCVTZSDHr (FRINTXHr f16:$Rn))>;
+def : Pat<(i64 (any_lrint f32:$Rn)),
+ (FCVTZSDSr (FRINTXSr f32:$Rn))>;
+def : Pat<(i64 (any_llrint f32:$Rn)),
+ (FCVTZSDSr (FRINTXSr f32:$Rn))>;
+}
+def : Pat<(i64 (any_lrint f64:$Rn)),
+ (FCVTZSv1i64 (FRINTXDr f64:$Rn))>;
+def : Pat<(i64 (any_llrint f64:$Rn)),
+ (FCVTZSv1i64 (FRINTXDr f64:$Rn))>;
+
+let Predicates = [HasFPRCVT] in {
+ def : Pat<(f32 (bitconvert (i32 (any_lrint f16:$Rn)))),
+ (FCVTZSSHr (FRINTXHr f16:$Rn))>;
+ def : Pat<(f64 (bitconvert (i64 (any_lrint f16:$Rn)))),
+ (FCVTZSDHr (FRINTXHr f16:$Rn))>;
+ def : Pat<(f64 (bitconvert (i64 (any_llrint f16:$Rn)))),
+ (FCVTZSDHr (FRINTXHr f16:$Rn))>;
+ def : Pat<(f64 (bitconvert (i64 (any_lrint f32:$Rn)))),
+ (FCVTZSDSr (FRINTXSr f32:$Rn))>;
+ def : Pat<(f32 (bitconvert (i32 (any_lrint f64:$Rn)))),
+ (FCVTZSSDr (FRINTXDr f64:$Rn))>;
+ def : Pat<(f64 (bitconvert (i64 (any_llrint f32:$Rn)))),
+ (FCVTZSDSr (FRINTXSr f32:$Rn))>;
+}
+def : Pat<(f32 (bitconvert (i32 (any_lrint f32:$Rn)))),
+ (FCVTZSv1i32 (FRINTXSr f32:$Rn))>;
+def : Pat<(f64 (bitconvert (i64 (any_lrint f64:$Rn)))),
+ (FCVTZSv1i64 (FRINTXDr f64:$Rn))>;
+def : Pat<(f64 (bitconvert (i64 (any_llrint f64:$Rn)))),
+ (FCVTZSv1i64 (FRINTXDr f64:$Rn))>;
+
+
// f16 -> s16 conversions
let Predicates = [HasFullFP16] in {
def : Pat<(i16(fp_to_sint_sat_gi f16:$Rn)), (FCVTZSv1f16 f16:$Rn)>;
diff --git a/llvm/lib/Target/AArch64/GISel/AArch64RegisterBankInfo.cpp b/llvm/lib/Target/AArch64/GISel/AArch64RegisterBankInfo.cpp
index 6d2d70511e894..8bd982898b8d6 100644
--- a/llvm/lib/Target/AArch64/GISel/AArch64RegisterBankInfo.cpp
+++ b/llvm/lib/Target/AArch64/GISel/AArch64RegisterBankInfo.cpp
@@ -858,7 +858,11 @@ AArch64RegisterBankInfo::getInstrMapping(const MachineInstr &MI) const {
case TargetOpcode::G_FPTOSI_SAT:
case TargetOpcode::G_FPTOUI_SAT:
case TargetOpcode::G_FPTOSI:
- case TargetOpcode::G_FPTOUI: {
+ case TargetOpcode::G_FPTOUI:
+ case TargetOpcode::G_INTRINSIC_LRINT:
+ case TargetOpcode::G_INTRINSIC_LLRINT:
+ case TargetOpcode::G_LROUND:
+ case TargetOpcode::G_LLROUND: {
LLT DstType = MRI.getType(MI.getOperand(0).getReg());
if (DstType.isVector())
break;
@@ -879,12 +883,6 @@ AArch64RegisterBankInfo::getInstrMapping(const MachineInstr &MI) const {
OpRegBankIdx = {PMI_FirstGPR, PMI_FirstFPR};
break;
}
- case TargetOpcode::G_INTRINSIC_LRINT:
- case TargetOpcode::G_INTRINSIC_LLRINT:
- if (MRI.getType(MI.getOperand(0).getReg()).isVector())
- break;
- OpRegBankIdx = {PMI_FirstGPR, PMI_FirstFPR};
- break;
case TargetOpcode::G_FCMP: {
// If the result is a vector, it must use a FPR.
AArch64GenRegisterBankInfo::PartialMappingIdx Idx0 =
@@ -1224,12 +1222,6 @@ AArch64RegisterBankInfo::getInstrMapping(const MachineInstr &MI) const {
}
break;
}
- case TargetOpcode::G_LROUND:
- case TargetOpcode::G_LLROUND: {
- // Source is always floating point and destination is always integer.
- OpRegBankIdx = {PMI_FirstGPR, PMI_FirstFPR};
- break;
- }
}
// Finally construct the computed mapping.
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/regbank-llround.mir b/llvm/test/CodeGen/AArch64/GlobalISel/regbank-llround.mir
index 420c7cfb07b74..16100f01017a6 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/regbank-llround.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/regbank-llround.mir
@@ -14,7 +14,7 @@ body: |
; CHECK: liveins: $d0
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: %fpr:fpr(s64) = COPY $d0
- ; CHECK-NEXT: %llround:gpr(s64) = G_LLROUND %fpr(s64)
+ ; CHECK-NEXT: %llround:fpr(s64) = G_LLROUND %fpr(s64)
; CHECK-NEXT: $d0 = COPY %llround(s64)
; CHECK-NEXT: RET_ReallyLR implicit $s0
%fpr:_(s64) = COPY $d0
@@ -35,7 +35,7 @@ body: |
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: %gpr:gpr(s64) = COPY $x0
; CHECK-NEXT: [[COPY:%[0-9]+]]:fpr(s64) = COPY %gpr(s64)
- ; CHECK-NEXT: %llround:gpr(s64) = G_LLROUND [[COPY]](s64)
+ ; CHECK-NEXT: %llround:fpr(s64) = G_LLROUND [[COPY]](s64)
; CHECK-NEXT: $d0 = COPY %llround(s64)
; CHECK-NEXT: RET_ReallyLR implicit $s0
%gpr:_(s64) = COPY $x0
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/regbank-lround.mir b/llvm/test/CodeGen/AArch64/GlobalISel/regbank-lround.mir
index 775c6ca773c68..5cb93f7c4646d 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/regbank-lround.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/regbank-lround.mir
@@ -14,7 +14,7 @@ body: |
; CHECK: liveins: $d0
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: %fpr:fpr(s64) = COPY $d0
- ; CHECK-NEXT: %lround:gpr(s64) = G_LROUND %fpr(s64)
+ ; CHECK-NEXT: %lround:fpr(s64) = G_LROUND %fpr(s64)
; CHECK-NEXT: $d0 = COPY %lround(s64)
; CHECK-NEXT: RET_ReallyLR implicit $s0
%fpr:_(s64) = COPY $d0
@@ -35,7 +35,7 @@ body: |
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: %gpr:gpr(s64) = COPY $x0
; CHECK-NEXT: [[COPY:%[0-9]+]]:fpr(s64) = COPY %gpr(s64)
- ; CHECK-NEXT: %lround:gpr(s64) = G_LROUND [[COPY]](s64)
+ ; CHECK-NEXT: %lround:fpr(s64) = G_LROUND [[COPY]](s64)
; CHECK-NEXT: $d0 = COPY %lround(s64)
; CHECK-NEXT: RET_ReallyLR implicit $s0
%gpr:_(s64) = COPY $x0
diff --git a/llvm/test/CodeGen/AArch64/arm64-cvt-simd-round-rint.ll b/llvm/test/CodeGen/AArch64/arm64-cvt-simd-round-rint.ll
new file mode 100644
index 0000000000000..000ff64131ccf
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/arm64-cvt-simd-round-rint.ll
@@ -0,0 +1,428 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc < %s -mtriple aarch64-unknown-unknown -mattr=+fprcvt,+fullfp16 | FileCheck %s --check-prefixes=CHECK,CHECK-SD
+; RUN: llc < %s -mtriple aarch64-unknown-unknown -global-isel -global-isel-abort=2 -mattr=+fprcvt,+fullfp16 2>&1 | FileCheck %s --check-prefixes=CHECK,CHECK-GI
+
+; CHECK-GI: warning: Instruction selection used fallback path for lround_i32_f16_simd
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lround_i64_f16_simd
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lround_i32_f64_simd
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lround_i32_f32_simd
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for llround_i64_f16_simd
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lround_i32_f16_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lround_i64_f16_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lround_i64_f32_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lround_i32_f64_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lround_i32_f32_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lround_i64_f64_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for llround_i64_f16_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for llround_i64_f32_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for llround_i64_f64_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lrint_i32_f16_simd
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lrint_i32_f64_simd
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lrint_i32_f32_simd
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lrint_i32_f16_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lrint_i64_f16_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lrint_i64_f32_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lrint_i32_f64_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lrint_i32_f32_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lrint_i64_f64_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for llrint_i64_f16_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for llrint_i64_f32_simd_exp
+; CHECK-GI-NEXT: warning: Instruction selection used fallback path for llrint_i64_f64_simd_exp
+
+;
+; (L/LL)Round
+;
+
+define float @lround_i32_f16_simd(half %x) {
+; CHECK-LABEL: lround_i32_f16_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas s0, h0
+; CHECK-NEXT: ret
+ %val = call i32 @llvm.lround.i32.f16(half %x)
+ %sum = bitcast i32 %val to float
+ ret float %sum
+}
+
+define double @lround_i64_f16_simd(half %x) {
+; CHECK-LABEL: lround_i64_f16_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas d0, h0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.lround.i64.f16(half %x)
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+define double @lround_i64_f32_simd(float %x) {
+; CHECK-LABEL: lround_i64_f32_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas d0, s0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.lround.i64.f32(float %x)
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+define float @lround_i32_f64_simd(double %x) {
+; CHECK-LABEL: lround_i32_f64_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas s0, d0
+; CHECK-NEXT: ret
+ %val = call i32 @llvm.lround.i32.f64(double %x)
+ %bc = bitcast i32 %val to float
+ ret float %bc
+}
+
+define float @lround_i32_f32_simd(float %x) {
+; CHECK-LABEL: lround_i32_f32_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas s0, s0
+; CHECK-NEXT: ret
+ %val = call i32 @llvm.lround.i32.f32(float %x)
+ %bc = bitcast i32 %val to float
+ ret float %bc
+}
+
+define double @lround_i64_f64_simd(double %x) {
+; CHECK-LABEL: lround_i64_f64_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas d0, d0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.lround.i64.f64(double %x)
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+define double @llround_i64_f16_simd(half %x) {
+; CHECK-LABEL: llround_i64_f16_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas d0, h0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.llround.i64.f16(half %x)
+ %sum = bitcast i64 %val to double
+ ret double %sum
+}
+
+define double @llround_i64_f32_simd(float %x) {
+; CHECK-LABEL: llround_i64_f32_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas d0, s0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.llround.i64.f32(float %x)
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+define double @llround_i64_f64_simd(double %x) {
+; CHECK-LABEL: llround_i64_f64_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas d0, d0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.llround.i64.f64(double %x)
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+
+;
+; (L/LL)Round experimental
+;
+
+define float @lround_i32_f16_simd_exp(half %x) {
+; CHECK-LABEL: lround_i32_f16_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas s0, h0
+; CHECK-NEXT: ret
+ %val = call i32 @llvm.experimental.constrained.lround.i32.f16(half %x, metadata !"fpexcept.strict")
+ %sum = bitcast i32 %val to float
+ ret float %sum
+}
+
+define double @lround_i64_f16_simd_exp(half %x) {
+; CHECK-LABEL: lround_i64_f16_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas d0, h0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.experimental.constrained.lround.i64.f16(half %x, metadata !"fpexcept.strict")
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+define double @lround_i64_f32_simd_exp(float %x) {
+; CHECK-LABEL: lround_i64_f32_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas d0, s0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.experimental.constrained.lround.i64.f32(float %x, metadata !"fpexcept.strict")
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+define float @lround_i32_f64_simd_exp(double %x) {
+; CHECK-LABEL: lround_i32_f64_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas s0, d0
+; CHECK-NEXT: ret
+ %val = call i32 @llvm.experimental.constrained.lround.i32.f64(double %x, metadata !"fpexcept.strict")
+ %bc = bitcast i32 %val to float
+ ret float %bc
+}
+
+define float @lround_i32_f32_simd_exp(float %x) {
+; CHECK-LABEL: lround_i32_f32_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas s0, s0
+; CHECK-NEXT: ret
+ %val = call i32 @llvm.experimental.constrained.lround.i32.f32(float %x, metadata !"fpexcept.strict")
+ %bc = bitcast i32 %val to float
+ ret float %bc
+}
+
+define double @lround_i64_f64_simd_exp(double %x) {
+; CHECK-LABEL: lround_i64_f64_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas d0, d0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.experimental.constrained.lround.i64.f64(double %x, metadata !"fpexcept.strict")
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+define double @llround_i64_f16_simd_exp(half %x) {
+; CHECK-LABEL: llround_i64_f16_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas d0, h0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.experimental.constrained.llround.i64.f16(half %x, metadata !"fpexcept.strict")
+ %sum = bitcast i64 %val to double
+ ret double %sum
+}
+
+define double @llround_i64_f32_simd_exp(float %x) {
+; CHECK-LABEL: llround_i64_f32_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas d0, s0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.experimental.constrained.llround.i64.f32(float %x, metadata !"fpexcept.strict")
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+define double @llround_i64_f64_simd_exp(double %x) {
+; CHECK-LABEL: llround_i64_f64_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: fcvtas d0, d0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.experimental.constrained.llround.i64.f64(double %x, metadata !"fpexcept.strict")
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+;
+; (L/LL)Rint
+;
+
+define float @lrint_i32_f16_simd(half %x) {
+; CHECK-LABEL: lrint_i32_f16_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx h0, h0
+; CHECK-NEXT: fcvtzs s0, h0
+; CHECK-NEXT: ret
+ %val = call i32 @llvm.lrint.i32.f16(half %x)
+ %sum = bitcast i32 %val to float
+ ret float %sum
+}
+
+define double @lrint_i64_f16_simd(half %x) {
+; CHECK-LABEL: lrint_i64_f16_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx h0, h0
+; CHECK-NEXT: fcvtzs d0, h0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.lrint.i53.f16(half %x)
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+define double @lrint_i64_f32_simd(float %x) {
+; CHECK-LABEL: lrint_i64_f32_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx s0, s0
+; CHECK-NEXT: fcvtzs d0, s0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.lrint.i64.f32(float %x)
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+define float @lrint_i32_f64_simd(double %x) {
+; CHECK-LABEL: lrint_i32_f64_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx d0, d0
+; CHECK-NEXT: fcvtzs s0, d0
+; CHECK-NEXT: ret
+ %val = call i32 @llvm.lrint.i32.f64(double %x)
+ %bc = bitcast i32 %val to float
+ ret float %bc
+}
+
+define float @lrint_i32_f32_simd(float %x) {
+; CHECK-LABEL: lrint_i32_f32_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx s0, s0
+; CHECK-NEXT: fcvtzs s0, s0
+; CHECK-NEXT: ret
+ %val = call i32 @llvm.lrint.i32.f32(float %x)
+ %bc = bitcast i32 %val to float
+ ret float %bc
+}
+
+define double @lrint_i64_f64_simd(double %x) {
+; CHECK-LABEL: lrint_i64_f64_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx d0, d0
+; CHECK-NEXT: fcvtzs d0, d0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.lrint.i64.f64(double %x)
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+define double @llrint_i64_f16_simd(half %x) {
+; CHECK-LABEL: llrint_i64_f16_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx h0, h0
+; CHECK-NEXT: fcvtzs d0, h0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.llrint.i64.f16(half %x)
+ %sum = bitcast i64 %val to double
+ ret double %sum
+}
+
+define double @llrint_i64_f32_simd(float %x) {
+; CHECK-LABEL: llrint_i64_f32_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx s0, s0
+; CHECK-NEXT: fcvtzs d0, s0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.llrint.i64.f32(float %x)
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+define double @llrint_i64_f64_simd(double %x) {
+; CHECK-LABEL: llrint_i64_f64_simd:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx d0, d0
+; CHECK-NEXT: fcvtzs d0, d0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.llrint.i64.f64(double %x)
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+;
+; (L/LL)Rint experimental
+;
+
+define float @lrint_i32_f16_simd_exp(half %x) {
+; CHECK-LABEL: lrint_i32_f16_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx h0, h0
+; CHECK-NEXT: fcvtzs s0, h0
+; CHECK-NEXT: ret
+ %val = call i32 @llvm.experimental.constrained.lrint.i32.f16(half %x, metadata !"round.tonearest", metadata !"fpexcept.strict")
+ %sum = bitcast i32 %val to float
+ ret float %sum
+}
+
+define double @lrint_i64_f16_simd_exp(half %x) {
+; CHECK-LABEL: lrint_i64_f16_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx h0, h0
+; CHECK-NEXT: fcvtzs d0, h0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.experimental.constrained.lrint.i53.f16(half %x, metadata !"round.tonearest", metadata !"fpexcept.strict")
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+define double @lrint_i64_f32_simd_exp(float %x) {
+; CHECK-LABEL: lrint_i64_f32_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx s0, s0
+; CHECK-NEXT: fcvtzs d0, s0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.experimental.constrained.lrint.i64.f32(float %x, metadata !"round.tonearest", metadata !"fpexcept.strict")
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+define float @lrint_i32_f64_simd_exp(double %x) {
+; CHECK-LABEL: lrint_i32_f64_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx d0, d0
+; CHECK-NEXT: fcvtzs s0, d0
+; CHECK-NEXT: ret
+ %val = call i32 @llvm.experimental.constrained.lrint.i32.f64(double %x, metadata !"round.tonearest", metadata !"fpexcept.strict")
+ %bc = bitcast i32 %val to float
+ ret float %bc
+}
+
+define float @lrint_i32_f32_simd_exp(float %x) {
+; CHECK-LABEL: lrint_i32_f32_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx s0, s0
+; CHECK-NEXT: fcvtzs s0, s0
+; CHECK-NEXT: ret
+ %val = call i32 @llvm.experimental.constrained.lrint.i32.f32(float %x, metadata !"round.tonearest", metadata !"fpexcept.strict")
+ %bc = bitcast i32 %val to float
+ ret float %bc
+}
+
+define double @lrint_i64_f64_simd_exp(double %x) {
+; CHECK-LABEL: lrint_i64_f64_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx d0, d0
+; CHECK-NEXT: fcvtzs d0, d0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.experimental.constrained.lrint.i64.f64(double %x, metadata !"round.tonearest", metadata !"fpexcept.strict")
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+define double @llrint_i64_f16_simd_exp(half %x) {
+; CHECK-LABEL: llrint_i64_f16_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx h0, h0
+; CHECK-NEXT: fcvtzs d0, h0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.experimental.constrained.llrint.i64.f16(half %x, metadata !"round.tonearest", metadata !"fpexcept.strict")
+ %sum = bitcast i64 %val to double
+ ret double %sum
+}
+
+define double @llrint_i64_f32_simd_exp(float %x) {
+; CHECK-LABEL: llrint_i64_f32_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx s0, s0
+; CHECK-NEXT: fcvtzs d0, s0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.experimental.constrained.llrint.i64.f32(float %x, metadata !"round.tonearest", metadata !"fpexcept.strict")
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+
+define double @llrint_i64_f64_simd_exp(double %x) {
+; CHECK-LABEL: llrint_i64_f64_simd_exp:
+; CHECK: // %bb.0:
+; CHECK-NEXT: frintx d0, d0
+; CHECK-NEXT: fcvtzs d0, d0
+; CHECK-NEXT: ret
+ %val = call i64 @llvm.experimental.constrained.llrint.i64.f64(double %x, metadata !"round.tonearest", metadata !"fpexcept.strict")
+ %bc = bitcast i64 %val to double
+ ret double %bc
+}
+;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
+; CHECK-GI: {{.*}}
+; CHECK-SD: {{.*}}
diff --git a/llvm/test/CodeGen/AArch64/vector-lrint.ll b/llvm/test/CodeGen/AArch64/vector-lrint.ll
index 65839b21b5356..05ff166a3ec90 100644
--- a/llvm/test/CodeGen/AArch64/vector-lrint.ll
+++ b/llvm/test/CodeGen/AArch64/vector-lrint.ll
@@ -1005,12 +1005,18 @@ define <1 x iXLen> @lrint_v1f64(<1 x double> %x) nounwind {
; CHECK-i32-NEXT: fmov s0, w8
; CHECK-i32-NEXT: ret
;
-; CHECK-i64-LABEL: lrint_v1f64:
-; CHECK-i64: // %bb.0:
-; CHECK-i64-NEXT: frintx d0, d0
-; CHECK-i64-NEXT: fcvtzs x8, d0
-; CHECK-i64-NEXT: fmov d0, x8
-; CHECK-i64-NEXT: ret
+; CHECK-i64-SD-LABEL: lrint_v1f64:
+; CHECK-i64-SD: // %bb.0:
+; CHECK-i64-SD-NEXT: frintx d0, d0
+; CHECK-i64-SD-NEXT: fcvtzs x8, d0
+; CHECK-i64-SD-NEXT: fmov d0, x8
+; CHECK-i64-SD-NEXT: ret
+;
+; CHECK-i64-GI-LABEL: lrint_v1f64:
+; CHECK-i64-GI: // %bb.0:
+; CHECK-i64-GI-NEXT: frintx d0, d0
+; CHECK-i64-GI-NEXT: fcvtzs d0, d0
+; CHECK-i64-GI-NEXT: ret
%a = call <1 x iXLen> @llvm.lrint.v1iXLen.v1f64(<1 x double> %x)
ret <1 x iXLen> %a
}
>From 38217973c66464577a09b74da0d524a18deb9f93 Mon Sep 17 00:00:00 2001
From: Marian Lukac <Marian.Lukac at arm.com>
Date: Thu, 20 Nov 2025 10:37:10 +0000
Subject: [PATCH 2/2] Added patterns for legalized rounding nodes
---
llvm/lib/Target/AArch64/AArch64InstrInfo.td | 4 ++
.../AArch64/arm64-cvt-simd-round-rint.ll | 52 +++++++++++--------
2 files changed, 35 insertions(+), 21 deletions(-)
diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.td b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
index 05b0351823b2d..dac796c7bbe09 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -6808,6 +6808,10 @@ defm : FPToIntegerPats<fp_to_uint, fp_to_uint_sat, fp_to_uint_sat_gi, fround, "F
// For global-isel we can use register classes to determine
// which FCVT instruction to use.
let Predicates = [HasFPRCVT] in {
+def : Pat<(i64 (any_lround f16:$Rn)),
+ (FCVTASDHr f16:$Rn)>;
+def : Pat<(i64 (any_llround f16:$Rn)),
+ (FCVTASDHr f16:$Rn)>;
def : Pat<(i64 (any_lround f32:$Rn)),
(FCVTASDSr f32:$Rn)>;
def : Pat<(i64 (any_llround f32:$Rn)),
diff --git a/llvm/test/CodeGen/AArch64/arm64-cvt-simd-round-rint.ll b/llvm/test/CodeGen/AArch64/arm64-cvt-simd-round-rint.ll
index 000ff64131ccf..16fd91c0dd0ab 100644
--- a/llvm/test/CodeGen/AArch64/arm64-cvt-simd-round-rint.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-cvt-simd-round-rint.ll
@@ -2,12 +2,7 @@
; RUN: llc < %s -mtriple aarch64-unknown-unknown -mattr=+fprcvt,+fullfp16 | FileCheck %s --check-prefixes=CHECK,CHECK-SD
; RUN: llc < %s -mtriple aarch64-unknown-unknown -global-isel -global-isel-abort=2 -mattr=+fprcvt,+fullfp16 2>&1 | FileCheck %s --check-prefixes=CHECK,CHECK-GI
-; CHECK-GI: warning: Instruction selection used fallback path for lround_i32_f16_simd
-; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lround_i64_f16_simd
-; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lround_i32_f64_simd
-; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lround_i32_f32_simd
-; CHECK-GI-NEXT: warning: Instruction selection used fallback path for llround_i64_f16_simd
-; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lround_i32_f16_simd_exp
+; CHECK-GI: warning: Instruction selection used fallback path for lround_i32_f16_simd_exp
; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lround_i64_f16_simd_exp
; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lround_i64_f32_simd_exp
; CHECK-GI-NEXT: warning: Instruction selection used fallback path for lround_i32_f64_simd_exp
@@ -34,10 +29,16 @@
;
define float @lround_i32_f16_simd(half %x) {
-; CHECK-LABEL: lround_i32_f16_simd:
-; CHECK: // %bb.0:
-; CHECK-NEXT: fcvtas s0, h0
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: lround_i32_f16_simd:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: fcvtas s0, h0
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: lround_i32_f16_simd:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: fcvtas x8, h0
+; CHECK-GI-NEXT: fmov s0, w8
+; CHECK-GI-NEXT: ret
%val = call i32 @llvm.lround.i32.f16(half %x)
%sum = bitcast i32 %val to float
ret float %sum
@@ -64,20 +65,32 @@ define double @lround_i64_f32_simd(float %x) {
}
define float @lround_i32_f64_simd(double %x) {
-; CHECK-LABEL: lround_i32_f64_simd:
-; CHECK: // %bb.0:
-; CHECK-NEXT: fcvtas s0, d0
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: lround_i32_f64_simd:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: fcvtas s0, d0
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: lround_i32_f64_simd:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: fcvtas x8, d0
+; CHECK-GI-NEXT: fmov s0, w8
+; CHECK-GI-NEXT: ret
%val = call i32 @llvm.lround.i32.f64(double %x)
%bc = bitcast i32 %val to float
ret float %bc
}
define float @lround_i32_f32_simd(float %x) {
-; CHECK-LABEL: lround_i32_f32_simd:
-; CHECK: // %bb.0:
-; CHECK-NEXT: fcvtas s0, s0
-; CHECK-NEXT: ret
+; CHECK-SD-LABEL: lround_i32_f32_simd:
+; CHECK-SD: // %bb.0:
+; CHECK-SD-NEXT: fcvtas s0, s0
+; CHECK-SD-NEXT: ret
+;
+; CHECK-GI-LABEL: lround_i32_f32_simd:
+; CHECK-GI: // %bb.0:
+; CHECK-GI-NEXT: fcvtas x8, s0
+; CHECK-GI-NEXT: fmov s0, w8
+; CHECK-GI-NEXT: ret
%val = call i32 @llvm.lround.i32.f32(float %x)
%bc = bitcast i32 %val to float
ret float %bc
@@ -423,6 +436,3 @@ define double @llrint_i64_f64_simd_exp(double %x) {
%bc = bitcast i64 %val to double
ret double %bc
}
-;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
-; CHECK-GI: {{.*}}
-; CHECK-SD: {{.*}}
More information about the llvm-commits
mailing list