[llvm] [RISCV] Split fp rounding ops with zvfhmin nxv32f16 (PR #108765)
via llvm-commits
llvm-commits at lists.llvm.org
Sun Sep 15 09:01:22 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-risc-v
Author: Luke Lau (lukel97)
<details>
<summary>Changes</summary>
This adds zvfhmin test coverage for fceil, ffloor, fnearbyint, frint, fround and froundeven and splits them at nxv32f16 to avoid crashing, similarly to what we do for other nodes that we promote.
This also sets ftrunc to promote which was previously missing. We already promote the VP version of it, vp_froundtozero.
---
Patch is 95.90 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/108765.diff
8 Files Affected:
- (modified) llvm/lib/Target/RISCV/RISCVISelLowering.cpp (+11-6)
- (modified) llvm/test/CodeGen/RISCV/rvv/fceil-sdnode.ll (+218-86)
- (modified) llvm/test/CodeGen/RISCV/rvv/ffloor-sdnode.ll (+218-86)
- (modified) llvm/test/CodeGen/RISCV/rvv/fnearbyint-sdnode.ll (+233-86)
- (modified) llvm/test/CodeGen/RISCV/rvv/frint-sdnode.ll (+194-74)
- (modified) llvm/test/CodeGen/RISCV/rvv/fround-sdnode.ll (+218-86)
- (modified) llvm/test/CodeGen/RISCV/rvv/froundeven-sdnode.ll (+218-86)
- (modified) llvm/test/CodeGen/RISCV/rvv/ftrunc-sdnode.ll (+194-74)
``````````diff
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
index 6f2dc710cb3d4d..7b1b35160cf460 100644
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -938,12 +938,13 @@ RISCVTargetLowering::RISCVTargetLowering(const TargetMachine &TM,
// TODO: support more ops.
static const unsigned ZvfhminPromoteOps[] = {
- ISD::FMINNUM, ISD::FMAXNUM, ISD::FADD, ISD::FSUB,
- ISD::FMUL, ISD::FMA, ISD::FDIV, ISD::FSQRT,
- ISD::FCEIL, ISD::FFLOOR, ISD::FROUND, ISD::FROUNDEVEN,
- ISD::FRINT, ISD::FNEARBYINT, ISD::IS_FPCLASS, ISD::SETCC,
- ISD::FMAXIMUM, ISD::FMINIMUM, ISD::STRICT_FADD, ISD::STRICT_FSUB,
- ISD::STRICT_FMUL, ISD::STRICT_FDIV, ISD::STRICT_FSQRT, ISD::STRICT_FMA};
+ ISD::FMINNUM, ISD::FMAXNUM, ISD::FADD, ISD::FSUB,
+ ISD::FMUL, ISD::FMA, ISD::FDIV, ISD::FSQRT,
+ ISD::FCEIL, ISD::FTRUNC, ISD::FFLOOR, ISD::FROUND,
+ ISD::FROUNDEVEN, ISD::FRINT, ISD::FNEARBYINT, ISD::IS_FPCLASS,
+ ISD::SETCC, ISD::FMAXIMUM, ISD::FMINIMUM, ISD::STRICT_FADD,
+ ISD::STRICT_FSUB, ISD::STRICT_FMUL, ISD::STRICT_FDIV, ISD::STRICT_FSQRT,
+ ISD::STRICT_FMA};
// TODO: support more vp ops.
static const unsigned ZvfhminPromoteVPOps[] = {ISD::VP_FADD,
@@ -6926,6 +6927,10 @@ SDValue RISCVTargetLowering::LowerOperation(SDValue Op,
case ISD::FRINT:
case ISD::FROUND:
case ISD::FROUNDEVEN:
+ if (Op.getValueType() == MVT::nxv32f16 &&
+ (Subtarget.hasVInstructionsF16Minimal() &&
+ !Subtarget.hasVInstructionsF16()))
+ return SplitVectorOp(Op, DAG);
return lowerFTRUNC_FCEIL_FFLOOR_FROUND(Op, DAG, Subtarget);
case ISD::LRINT:
case ISD::LLRINT:
diff --git a/llvm/test/CodeGen/RISCV/rvv/fceil-sdnode.ll b/llvm/test/CodeGen/RISCV/rvv/fceil-sdnode.ll
index 9efc3183f15a52..111d1d8e07d3bf 100644
--- a/llvm/test/CodeGen/RISCV/rvv/fceil-sdnode.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fceil-sdnode.ll
@@ -1,124 +1,256 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+zvfh,+v -target-abi=ilp32d \
-; RUN: -verify-machineinstrs < %s | FileCheck %s
+; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFH
; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+zvfh,+v -target-abi=lp64d \
-; RUN: -verify-machineinstrs < %s | FileCheck %s
+; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFH
+; RUN: llc -mtriple=riscv32 -mattr=+d,+zfhmin,+zvfhmin,+v -target-abi=ilp32d \
+; RUN: -verify-machineinstrs < %s | FileCheck %s \
+; RUN: --check-prefixes=CHECK,ZVFHMIN
+; RUN: llc -mtriple=riscv64 -mattr=+d,+zfhmin,+zvfhmin,+v -target-abi=lp64d \
+; RUN: -verify-machineinstrs < %s | FileCheck %s \
+; RUN: --check-prefixes=CHECK,ZVFHMIN
define <vscale x 1 x half> @ceil_nxv1f16(<vscale x 1 x half> %x) {
-; CHECK-LABEL: ceil_nxv1f16:
-; CHECK: # %bb.0:
-; CHECK-NEXT: lui a0, %hi(.LCPI0_0)
-; CHECK-NEXT: flh fa5, %lo(.LCPI0_0)(a0)
-; CHECK-NEXT: vsetvli a0, zero, e16, mf4, ta, ma
-; CHECK-NEXT: vfabs.v v9, v8
-; CHECK-NEXT: vmflt.vf v0, v9, fa5
-; CHECK-NEXT: fsrmi a0, 3
-; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
-; CHECK-NEXT: fsrm a0
-; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, mu
-; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
-; CHECK-NEXT: ret
+; ZVFH-LABEL: ceil_nxv1f16:
+; ZVFH: # %bb.0:
+; ZVFH-NEXT: lui a0, %hi(.LCPI0_0)
+; ZVFH-NEXT: flh fa5, %lo(.LCPI0_0)(a0)
+; ZVFH-NEXT: vsetvli a0, zero, e16, mf4, ta, ma
+; ZVFH-NEXT: vfabs.v v9, v8
+; ZVFH-NEXT: vmflt.vf v0, v9, fa5
+; ZVFH-NEXT: fsrmi a0, 3
+; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t
+; ZVFH-NEXT: fsrm a0
+; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t
+; ZVFH-NEXT: vsetvli zero, zero, e16, mf4, ta, mu
+; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; ZVFH-NEXT: ret
+;
+; ZVFHMIN-LABEL: ceil_nxv1f16:
+; ZVFHMIN: # %bb.0:
+; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf4, ta, ma
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v8
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
+; ZVFHMIN-NEXT: vfabs.v v8, v9
+; ZVFHMIN-NEXT: lui a0, 307200
+; ZVFHMIN-NEXT: fmv.w.x fa5, a0
+; ZVFHMIN-NEXT: vmflt.vf v0, v8, fa5
+; ZVFHMIN-NEXT: fsrmi a0, 3
+; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v9, v0.t
+; ZVFHMIN-NEXT: fsrm a0
+; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, mf2, ta, mu
+; ZVFHMIN-NEXT: vfsgnj.vv v9, v8, v9, v0.t
+; ZVFHMIN-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
+; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9
+; ZVFHMIN-NEXT: ret
%a = call <vscale x 1 x half> @llvm.ceil.nxv1f16(<vscale x 1 x half> %x)
ret <vscale x 1 x half> %a
}
declare <vscale x 1 x half> @llvm.ceil.nxv1f16(<vscale x 1 x half>)
define <vscale x 2 x half> @ceil_nxv2f16(<vscale x 2 x half> %x) {
-; CHECK-LABEL: ceil_nxv2f16:
-; CHECK: # %bb.0:
-; CHECK-NEXT: lui a0, %hi(.LCPI1_0)
-; CHECK-NEXT: flh fa5, %lo(.LCPI1_0)(a0)
-; CHECK-NEXT: vsetvli a0, zero, e16, mf2, ta, ma
-; CHECK-NEXT: vfabs.v v9, v8
-; CHECK-NEXT: vmflt.vf v0, v9, fa5
-; CHECK-NEXT: fsrmi a0, 3
-; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
-; CHECK-NEXT: fsrm a0
-; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: vsetvli zero, zero, e16, mf2, ta, mu
-; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
-; CHECK-NEXT: ret
+; ZVFH-LABEL: ceil_nxv2f16:
+; ZVFH: # %bb.0:
+; ZVFH-NEXT: lui a0, %hi(.LCPI1_0)
+; ZVFH-NEXT: flh fa5, %lo(.LCPI1_0)(a0)
+; ZVFH-NEXT: vsetvli a0, zero, e16, mf2, ta, ma
+; ZVFH-NEXT: vfabs.v v9, v8
+; ZVFH-NEXT: vmflt.vf v0, v9, fa5
+; ZVFH-NEXT: fsrmi a0, 3
+; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t
+; ZVFH-NEXT: fsrm a0
+; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t
+; ZVFH-NEXT: vsetvli zero, zero, e16, mf2, ta, mu
+; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; ZVFH-NEXT: ret
+;
+; ZVFHMIN-LABEL: ceil_nxv2f16:
+; ZVFHMIN: # %bb.0:
+; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf2, ta, ma
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v8
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m1, ta, ma
+; ZVFHMIN-NEXT: vfabs.v v8, v9
+; ZVFHMIN-NEXT: lui a0, 307200
+; ZVFHMIN-NEXT: fmv.w.x fa5, a0
+; ZVFHMIN-NEXT: vmflt.vf v0, v8, fa5
+; ZVFHMIN-NEXT: fsrmi a0, 3
+; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v9, v0.t
+; ZVFHMIN-NEXT: fsrm a0
+; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m1, ta, mu
+; ZVFHMIN-NEXT: vfsgnj.vv v9, v8, v9, v0.t
+; ZVFHMIN-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
+; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9
+; ZVFHMIN-NEXT: ret
%a = call <vscale x 2 x half> @llvm.ceil.nxv2f16(<vscale x 2 x half> %x)
ret <vscale x 2 x half> %a
}
declare <vscale x 2 x half> @llvm.ceil.nxv2f16(<vscale x 2 x half>)
define <vscale x 4 x half> @ceil_nxv4f16(<vscale x 4 x half> %x) {
-; CHECK-LABEL: ceil_nxv4f16:
-; CHECK: # %bb.0:
-; CHECK-NEXT: lui a0, %hi(.LCPI2_0)
-; CHECK-NEXT: flh fa5, %lo(.LCPI2_0)(a0)
-; CHECK-NEXT: vsetvli a0, zero, e16, m1, ta, ma
-; CHECK-NEXT: vfabs.v v9, v8
-; CHECK-NEXT: vmflt.vf v0, v9, fa5
-; CHECK-NEXT: fsrmi a0, 3
-; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
-; CHECK-NEXT: fsrm a0
-; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: vsetvli zero, zero, e16, m1, ta, mu
-; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
-; CHECK-NEXT: ret
+; ZVFH-LABEL: ceil_nxv4f16:
+; ZVFH: # %bb.0:
+; ZVFH-NEXT: lui a0, %hi(.LCPI2_0)
+; ZVFH-NEXT: flh fa5, %lo(.LCPI2_0)(a0)
+; ZVFH-NEXT: vsetvli a0, zero, e16, m1, ta, ma
+; ZVFH-NEXT: vfabs.v v9, v8
+; ZVFH-NEXT: vmflt.vf v0, v9, fa5
+; ZVFH-NEXT: fsrmi a0, 3
+; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t
+; ZVFH-NEXT: fsrm a0
+; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t
+; ZVFH-NEXT: vsetvli zero, zero, e16, m1, ta, mu
+; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; ZVFH-NEXT: ret
+;
+; ZVFHMIN-LABEL: ceil_nxv4f16:
+; ZVFHMIN: # %bb.0:
+; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m1, ta, ma
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v10, v8
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m2, ta, ma
+; ZVFHMIN-NEXT: vfabs.v v8, v10
+; ZVFHMIN-NEXT: lui a0, 307200
+; ZVFHMIN-NEXT: fmv.w.x fa5, a0
+; ZVFHMIN-NEXT: vmflt.vf v0, v8, fa5
+; ZVFHMIN-NEXT: fsrmi a0, 3
+; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v10, v0.t
+; ZVFHMIN-NEXT: fsrm a0
+; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m2, ta, mu
+; ZVFHMIN-NEXT: vfsgnj.vv v10, v8, v10, v0.t
+; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m1, ta, ma
+; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v10
+; ZVFHMIN-NEXT: ret
%a = call <vscale x 4 x half> @llvm.ceil.nxv4f16(<vscale x 4 x half> %x)
ret <vscale x 4 x half> %a
}
declare <vscale x 4 x half> @llvm.ceil.nxv4f16(<vscale x 4 x half>)
define <vscale x 8 x half> @ceil_nxv8f16(<vscale x 8 x half> %x) {
-; CHECK-LABEL: ceil_nxv8f16:
-; CHECK: # %bb.0:
-; CHECK-NEXT: lui a0, %hi(.LCPI3_0)
-; CHECK-NEXT: flh fa5, %lo(.LCPI3_0)(a0)
-; CHECK-NEXT: vsetvli a0, zero, e16, m2, ta, ma
-; CHECK-NEXT: vfabs.v v10, v8
-; CHECK-NEXT: vmflt.vf v0, v10, fa5
-; CHECK-NEXT: fsrmi a0, 3
-; CHECK-NEXT: vfcvt.x.f.v v10, v8, v0.t
-; CHECK-NEXT: fsrm a0
-; CHECK-NEXT: vfcvt.f.x.v v10, v10, v0.t
-; CHECK-NEXT: vsetvli zero, zero, e16, m2, ta, mu
-; CHECK-NEXT: vfsgnj.vv v8, v10, v8, v0.t
-; CHECK-NEXT: ret
+; ZVFH-LABEL: ceil_nxv8f16:
+; ZVFH: # %bb.0:
+; ZVFH-NEXT: lui a0, %hi(.LCPI3_0)
+; ZVFH-NEXT: flh fa5, %lo(.LCPI3_0)(a0)
+; ZVFH-NEXT: vsetvli a0, zero, e16, m2, ta, ma
+; ZVFH-NEXT: vfabs.v v10, v8
+; ZVFH-NEXT: vmflt.vf v0, v10, fa5
+; ZVFH-NEXT: fsrmi a0, 3
+; ZVFH-NEXT: vfcvt.x.f.v v10, v8, v0.t
+; ZVFH-NEXT: fsrm a0
+; ZVFH-NEXT: vfcvt.f.x.v v10, v10, v0.t
+; ZVFH-NEXT: vsetvli zero, zero, e16, m2, ta, mu
+; ZVFH-NEXT: vfsgnj.vv v8, v10, v8, v0.t
+; ZVFH-NEXT: ret
+;
+; ZVFHMIN-LABEL: ceil_nxv8f16:
+; ZVFHMIN: # %bb.0:
+; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m2, ta, ma
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v12, v8
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m4, ta, ma
+; ZVFHMIN-NEXT: vfabs.v v8, v12
+; ZVFHMIN-NEXT: lui a0, 307200
+; ZVFHMIN-NEXT: fmv.w.x fa5, a0
+; ZVFHMIN-NEXT: vmflt.vf v0, v8, fa5
+; ZVFHMIN-NEXT: fsrmi a0, 3
+; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v12, v0.t
+; ZVFHMIN-NEXT: fsrm a0
+; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m4, ta, mu
+; ZVFHMIN-NEXT: vfsgnj.vv v12, v8, v12, v0.t
+; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m2, ta, ma
+; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v12
+; ZVFHMIN-NEXT: ret
%a = call <vscale x 8 x half> @llvm.ceil.nxv8f16(<vscale x 8 x half> %x)
ret <vscale x 8 x half> %a
}
declare <vscale x 8 x half> @llvm.ceil.nxv8f16(<vscale x 8 x half>)
define <vscale x 16 x half> @ceil_nxv16f16(<vscale x 16 x half> %x) {
-; CHECK-LABEL: ceil_nxv16f16:
-; CHECK: # %bb.0:
-; CHECK-NEXT: lui a0, %hi(.LCPI4_0)
-; CHECK-NEXT: flh fa5, %lo(.LCPI4_0)(a0)
-; CHECK-NEXT: vsetvli a0, zero, e16, m4, ta, ma
-; CHECK-NEXT: vfabs.v v12, v8
-; CHECK-NEXT: vmflt.vf v0, v12, fa5
-; CHECK-NEXT: fsrmi a0, 3
-; CHECK-NEXT: vfcvt.x.f.v v12, v8, v0.t
-; CHECK-NEXT: fsrm a0
-; CHECK-NEXT: vfcvt.f.x.v v12, v12, v0.t
-; CHECK-NEXT: vsetvli zero, zero, e16, m4, ta, mu
-; CHECK-NEXT: vfsgnj.vv v8, v12, v8, v0.t
-; CHECK-NEXT: ret
+; ZVFH-LABEL: ceil_nxv16f16:
+; ZVFH: # %bb.0:
+; ZVFH-NEXT: lui a0, %hi(.LCPI4_0)
+; ZVFH-NEXT: flh fa5, %lo(.LCPI4_0)(a0)
+; ZVFH-NEXT: vsetvli a0, zero, e16, m4, ta, ma
+; ZVFH-NEXT: vfabs.v v12, v8
+; ZVFH-NEXT: vmflt.vf v0, v12, fa5
+; ZVFH-NEXT: fsrmi a0, 3
+; ZVFH-NEXT: vfcvt.x.f.v v12, v8, v0.t
+; ZVFH-NEXT: fsrm a0
+; ZVFH-NEXT: vfcvt.f.x.v v12, v12, v0.t
+; ZVFH-NEXT: vsetvli zero, zero, e16, m4, ta, mu
+; ZVFH-NEXT: vfsgnj.vv v8, v12, v8, v0.t
+; ZVFH-NEXT: ret
+;
+; ZVFHMIN-LABEL: ceil_nxv16f16:
+; ZVFHMIN: # %bb.0:
+; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v8
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma
+; ZVFHMIN-NEXT: vfabs.v v8, v16
+; ZVFHMIN-NEXT: lui a0, 307200
+; ZVFHMIN-NEXT: fmv.w.x fa5, a0
+; ZVFHMIN-NEXT: vmflt.vf v0, v8, fa5
+; ZVFHMIN-NEXT: fsrmi a0, 3
+; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v16, v0.t
+; ZVFHMIN-NEXT: fsrm a0
+; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu
+; ZVFHMIN-NEXT: vfsgnj.vv v16, v8, v16, v0.t
+; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m4, ta, ma
+; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v16
+; ZVFHMIN-NEXT: ret
%a = call <vscale x 16 x half> @llvm.ceil.nxv16f16(<vscale x 16 x half> %x)
ret <vscale x 16 x half> %a
}
declare <vscale x 16 x half> @llvm.ceil.nxv16f16(<vscale x 16 x half>)
define <vscale x 32 x half> @ceil_nxv32f16(<vscale x 32 x half> %x) {
-; CHECK-LABEL: ceil_nxv32f16:
-; CHECK: # %bb.0:
-; CHECK-NEXT: lui a0, %hi(.LCPI5_0)
-; CHECK-NEXT: flh fa5, %lo(.LCPI5_0)(a0)
-; CHECK-NEXT: vsetvli a0, zero, e16, m8, ta, ma
-; CHECK-NEXT: vfabs.v v16, v8
-; CHECK-NEXT: vmflt.vf v0, v16, fa5
-; CHECK-NEXT: fsrmi a0, 3
-; CHECK-NEXT: vfcvt.x.f.v v16, v8, v0.t
-; CHECK-NEXT: fsrm a0
-; CHECK-NEXT: vfcvt.f.x.v v16, v16, v0.t
-; CHECK-NEXT: vsetvli zero, zero, e16, m8, ta, mu
-; CHECK-NEXT: vfsgnj.vv v8, v16, v8, v0.t
-; CHECK-NEXT: ret
+; ZVFH-LABEL: ceil_nxv32f16:
+; ZVFH: # %bb.0:
+; ZVFH-NEXT: lui a0, %hi(.LCPI5_0)
+; ZVFH-NEXT: flh fa5, %lo(.LCPI5_0)(a0)
+; ZVFH-NEXT: vsetvli a0, zero, e16, m8, ta, ma
+; ZVFH-NEXT: vfabs.v v16, v8
+; ZVFH-NEXT: vmflt.vf v0, v16, fa5
+; ZVFH-NEXT: fsrmi a0, 3
+; ZVFH-NEXT: vfcvt.x.f.v v16, v8, v0.t
+; ZVFH-NEXT: fsrm a0
+; ZVFH-NEXT: vfcvt.f.x.v v16, v16, v0.t
+; ZVFH-NEXT: vsetvli zero, zero, e16, m8, ta, mu
+; ZVFH-NEXT: vfsgnj.vv v8, v16, v8, v0.t
+; ZVFH-NEXT: ret
+;
+; ZVFHMIN-LABEL: ceil_nxv32f16:
+; ZVFHMIN: # %bb.0:
+; ZVFHMIN-NEXT: vsetvli a0, zero, e16, m4, ta, ma
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v8
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma
+; ZVFHMIN-NEXT: vfabs.v v24, v16
+; ZVFHMIN-NEXT: lui a0, 307200
+; ZVFHMIN-NEXT: fmv.w.x fa5, a0
+; ZVFHMIN-NEXT: vmflt.vf v0, v24, fa5
+; ZVFHMIN-NEXT: fsrmi a0, 3
+; ZVFHMIN-NEXT: vfcvt.x.f.v v24, v16, v0.t
+; ZVFHMIN-NEXT: fsrm a0
+; ZVFHMIN-NEXT: vfcvt.f.x.v v24, v24, v0.t
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu
+; ZVFHMIN-NEXT: vfsgnj.vv v16, v24, v16, v0.t
+; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m4, ta, ma
+; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v16
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v16, v12
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, ma
+; ZVFHMIN-NEXT: vfabs.v v24, v16
+; ZVFHMIN-NEXT: vmflt.vf v0, v24, fa5
+; ZVFHMIN-NEXT: fsrmi a0, 3
+; ZVFHMIN-NEXT: vfcvt.x.f.v v24, v16, v0.t
+; ZVFHMIN-NEXT: fsrm a0
+; ZVFHMIN-NEXT: vfcvt.f.x.v v24, v24, v0.t
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m8, ta, mu
+; ZVFHMIN-NEXT: vfsgnj.vv v16, v24, v16, v0.t
+; ZVFHMIN-NEXT: vsetvli zero, zero, e16, m4, ta, ma
+; ZVFHMIN-NEXT: vfncvt.f.f.w v12, v16
+; ZVFHMIN-NEXT: ret
%a = call <vscale x 32 x half> @llvm.ceil.nxv32f16(<vscale x 32 x half> %x)
ret <vscale x 32 x half> %a
}
diff --git a/llvm/test/CodeGen/RISCV/rvv/ffloor-sdnode.ll b/llvm/test/CodeGen/RISCV/rvv/ffloor-sdnode.ll
index ec60b3ed3e0c88..97d84e91744038 100644
--- a/llvm/test/CodeGen/RISCV/rvv/ffloor-sdnode.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/ffloor-sdnode.ll
@@ -1,124 +1,256 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+zvfh,+v -target-abi=ilp32d \
-; RUN: -verify-machineinstrs < %s | FileCheck %s
+; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFH
; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+zvfh,+v -target-abi=lp64d \
-; RUN: -verify-machineinstrs < %s | FileCheck %s
+; RUN: -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,ZVFH
+; RUN: llc -mtriple=riscv32 -mattr=+d,+zfhmin,+zvfhmin,+v -target-abi=ilp32d \
+; RUN: -verify-machineinstrs < %s | FileCheck %s \
+; RUN: --check-prefixes=CHECK,ZVFHMIN
+; RUN: llc -mtriple=riscv64 -mattr=+d,+zfhmin,+zvfhmin,+v -target-abi=lp64d \
+; RUN: -verify-machineinstrs < %s | FileCheck %s \
+; RUN: --check-prefixes=CHECK,ZVFHMIN
define <vscale x 1 x half> @floor_nxv1f16(<vscale x 1 x half> %x) {
-; CHECK-LABEL: floor_nxv1f16:
-; CHECK: # %bb.0:
-; CHECK-NEXT: lui a0, %hi(.LCPI0_0)
-; CHECK-NEXT: flh fa5, %lo(.LCPI0_0)(a0)
-; CHECK-NEXT: vsetvli a0, zero, e16, mf4, ta, ma
-; CHECK-NEXT: vfabs.v v9, v8
-; CHECK-NEXT: vmflt.vf v0, v9, fa5
-; CHECK-NEXT: fsrmi a0, 2
-; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
-; CHECK-NEXT: fsrm a0
-; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, mu
-; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
-; CHECK-NEXT: ret
+; ZVFH-LABEL: floor_nxv1f16:
+; ZVFH: # %bb.0:
+; ZVFH-NEXT: lui a0, %hi(.LCPI0_0)
+; ZVFH-NEXT: flh fa5, %lo(.LCPI0_0)(a0)
+; ZVFH-NEXT: vsetvli a0, zero, e16, mf4, ta, ma
+; ZVFH-NEXT: vfabs.v v9, v8
+; ZVFH-NEXT: vmflt.vf v0, v9, fa5
+; ZVFH-NEXT: fsrmi a0, 2
+; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t
+; ZVFH-NEXT: fsrm a0
+; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t
+; ZVFH-NEXT: vsetvli zero, zero, e16, mf4, ta, mu
+; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; ZVFH-NEXT: ret
+;
+; ZVFHMIN-LABEL: floor_nxv1f16:
+; ZVFHMIN: # %bb.0:
+; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf4, ta, ma
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v8
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, mf2, ta, ma
+; ZVFHMIN-NEXT: vfabs.v v8, v9
+; ZVFHMIN-NEXT: lui a0, 307200
+; ZVFHMIN-NEXT: fmv.w.x fa5, a0
+; ZVFHMIN-NEXT: vmflt.vf v0, v8, fa5
+; ZVFHMIN-NEXT: fsrmi a0, 2
+; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v9, v0.t
+; ZVFHMIN-NEXT: fsrm a0
+; ZVFHMIN-NEXT: vfcvt.f.x.v v8, v8, v0.t
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, mf2, ta, mu
+; ZVFHMIN-NEXT: vfsgnj.vv v9, v8, v9, v0.t
+; ZVFHMIN-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
+; ZVFHMIN-NEXT: vfncvt.f.f.w v8, v9
+; ZVFHMIN-NEXT: ret
%a = call <vscale x 1 x half> @llvm.floor.nxv1f16(<vscale x 1 x half> %x)
ret <vscale x 1 x half> %a
}
declare <vscale x 1 x half> @llvm.floor.nxv1f16(<vscale x 1 x half>)
define <vscale x 2 x half> @floor_nxv2f16(<vscale x 2 x half> %x) {
-; CHECK-LABEL: floor_nxv2f16:
-; CHECK: # %bb.0:
-; CHECK-NEXT: lui a0, %hi(.LCPI1_0)
-; CHECK-NEXT: flh fa5, %lo(.LCPI1_0)(a0)
-; CHECK-NEXT: vsetvli a0, zero, e16, mf2, ta, ma
-; CHECK-NEXT: vfabs.v v9, v8
-; CHECK-NEXT: vmflt.vf v0, v9, fa5
-; CHECK-NEXT: fsrmi a0, 2
-; CHECK-NEXT: vfcvt.x.f.v v9, v8, v0.t
-; CHECK-NEXT: fsrm a0
-; CHECK-NEXT: vfcvt.f.x.v v9, v9, v0.t
-; CHECK-NEXT: vsetvli zero, zero, e16, mf2, ta, mu
-; CHECK-NEXT: vfsgnj.vv v8, v9, v8, v0.t
-; CHECK-NEXT: ret
+; ZVFH-LABEL: floor_nxv2f16:
+; ZVFH: # %bb.0:
+; ZVFH-NEXT: lui a0, %hi(.LCPI1_0)
+; ZVFH-NEXT: flh fa5, %lo(.LCPI1_0)(a0)
+; ZVFH-NEXT: vsetvli a0, zero, e16, mf2, ta, ma
+; ZVFH-NEXT: vfabs.v v9, v8
+; ZVFH-NEXT: vmflt.vf v0, v9, fa5
+; ZVFH-NEXT: fsrmi a0, 2
+; ZVFH-NEXT: vfcvt.x.f.v v9, v8, v0.t
+; ZVFH-NEXT: fsrm a0
+; ZVFH-NEXT: vfcvt.f.x.v v9, v9, v0.t
+; ZVFH-NEXT: vsetvli zero, zero, e16, mf2, ta, mu
+; ZVFH-NEXT: vfsgnj.vv v8, v9, v8, v0.t
+; ZVFH-NEXT: ret
+;
+; ZVFHMIN-LABEL: floor_nxv2f16:
+; ZVFHMIN: # %bb.0:
+; ZVFHMIN-NEXT: vsetvli a0, zero, e16, mf2, ta, ma
+; ZVFHMIN-NEXT: vfwcvt.f.f.v v9, v8
+; ZVFHMIN-NEXT: vsetvli zero, zero, e32, m1, ta, ma
+; ZVFHMIN-NEXT: vfabs.v v8, v9
+; ZVFHMIN-NEXT: lui a0, 307200
+; ZVFHMIN-NEXT: fmv.w.x fa5, a0
+; ZVFHMIN-NEXT: vmflt.vf v0, v8, fa5
+; ZVFHMIN-NEXT: fsrmi a0, 2
+; ZVFHMIN-NEXT: vfcvt.x.f.v v8, v9, v0.t
+; ZVFHMIN-NEXT: fsrm a0
+; ...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/108765
More information about the llvm-commits
mailing list