maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[LoongArch] Add codegen support for fsqrt 

Reviewed By: xen0n, SixWeining

Differential Revision: https://reviews.llvm.org/D132198
This commit is contained in:
gonglingqin 2022-08-20 10:20:30 +08:00
parent e0f64b319e
commit 1e0fe6a947
3 changed files with 136 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
llvm/lib/Target/LoongArch/LoongArchFloat32InstrInfo.td
View File

@ -144,6 +144,9 @@ def : PatFprFpr<fmul, FMUL_S, FPR32>;
def : PatFprFpr<fdiv, FDIV_S, FPR32>;
def : PatFpr<fneg, FNEG_S, FPR32>;
def : PatFpr<fabs, FABS_S, FPR32>;
def : PatFpr<fsqrt, FSQRT_S, FPR32>;
def : Pat<(fdiv fpimm1, (fsqrt FPR32:$fj)), (FRSQRT_S FPR32:$fj)>;
/// Setcc

3
llvm/lib/Target/LoongArch/LoongArchFloat64InstrInfo.td
View File

@ -150,6 +150,9 @@ def : PatFprFpr<fmul, FMUL_D, FPR64>;
def : PatFprFpr<fdiv, FDIV_D, FPR64>;
def : PatFpr<fneg, FNEG_D, FPR64>;
def : PatFpr<fabs, FABS_D, FPR64>;
def : PatFpr<fsqrt, FSQRT_D, FPR64>;
def : Pat<(fdiv fpimm1, (fsqrt FPR64:$fj)), (FRSQRT_D FPR64:$fj)>;
/// Setcc

130
llvm/test/CodeGen/LoongArch/fsqrt.ll Normal file
View File

@ -0,0 +1,130 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc --mtriple=loongarch32 --mattr=+f,-d < %s | FileCheck %s --check-prefix=LA32F
; RUN: llc --mtriple=loongarch32 --mattr=+d < %s | FileCheck %s --check-prefix=LA32D
; RUN: llc --mtriple=loongarch64 --mattr=+f,-d < %s | FileCheck %s --check-prefix=LA64F
; RUN: llc --mtriple=loongarch64 --mattr=+d < %s | FileCheck %s --check-prefix=LA64D
declare float @llvm.sqrt.f32(float)
declare double @llvm.sqrt.f64(double)
define float @fsqrt_f32(float %a) nounwind {
; LA32F-LABEL: fsqrt_f32:
; LA32F: # %bb.0:
; LA32F-NEXT: fsqrt.s $fa0, $fa0
; LA32F-NEXT: ret
;
; LA32D-LABEL: fsqrt_f32:
; LA32D: # %bb.0:
; LA32D-NEXT: fsqrt.s $fa0, $fa0
; LA32D-NEXT: ret
;
; LA64F-LABEL: fsqrt_f32:
; LA64F: # %bb.0:
; LA64F-NEXT: fsqrt.s $fa0, $fa0
; LA64F-NEXT: ret
;
; LA64D-LABEL: fsqrt_f32:
; LA64D: # %bb.0:
; LA64D-NEXT: fsqrt.s $fa0, $fa0
; LA64D-NEXT: ret
%1 = call float @llvm.sqrt.f32(float %a)
ret float %1
}
define double @fsqrt_f64(double %a) nounwind {
; LA32F-LABEL: fsqrt_f64:
; LA32F: # %bb.0:
; LA32F-NEXT: addi.w $sp, $sp, -16
; LA32F-NEXT: st.w $ra, $sp, 12 # 4-byte Folded Spill
; LA32F-NEXT: bl sqrt
; LA32F-NEXT: ld.w $ra, $sp, 12 # 4-byte Folded Reload
; LA32F-NEXT: addi.w $sp, $sp, 16
; LA32F-NEXT: ret
;
; LA32D-LABEL: fsqrt_f64:
; LA32D: # %bb.0:
; LA32D-NEXT: fsqrt.d $fa0, $fa0
; LA32D-NEXT: ret
;
; LA64F-LABEL: fsqrt_f64:
; LA64F: # %bb.0:
; LA64F-NEXT: addi.d $sp, $sp, -16
; LA64F-NEXT: st.d $ra, $sp, 8 # 8-byte Folded Spill
; LA64F-NEXT: bl sqrt
; LA64F-NEXT: ld.d $ra, $sp, 8 # 8-byte Folded Reload
; LA64F-NEXT: addi.d $sp, $sp, 16
; LA64F-NEXT: ret
;
; LA64D-LABEL: fsqrt_f64:
; LA64D: # %bb.0:
; LA64D-NEXT: fsqrt.d $fa0, $fa0
; LA64D-NEXT: ret
%1 = call double @llvm.sqrt.f64(double %a)
ret double %1
}
define float @frsqrt_f32(float %a) nounwind {
; LA32F-LABEL: frsqrt_f32:
; LA32F: # %bb.0:
; LA32F-NEXT: frsqrt.s $fa0, $fa0
; LA32F-NEXT: ret
;
; LA32D-LABEL: frsqrt_f32:
; LA32D: # %bb.0:
; LA32D-NEXT: frsqrt.s $fa0, $fa0
; LA32D-NEXT: ret
;
; LA64F-LABEL: frsqrt_f32:
; LA64F: # %bb.0:
; LA64F-NEXT: frsqrt.s $fa0, $fa0
; LA64F-NEXT: ret
;
; LA64D-LABEL: frsqrt_f32:
; LA64D: # %bb.0:
; LA64D-NEXT: frsqrt.s $fa0, $fa0
; LA64D-NEXT: ret
%1 = call float @llvm.sqrt.f32(float %a)
%2 = fdiv float 1.0, %1
ret float %2
}
define double @frsqrt_f64(double %a) nounwind {
; LA32F-LABEL: frsqrt_f64:
; LA32F: # %bb.0:
; LA32F-NEXT: addi.w $sp, $sp, -16
; LA32F-NEXT: st.w $ra, $sp, 12 # 4-byte Folded Spill
; LA32F-NEXT: bl sqrt
; LA32F-NEXT: move $a2, $a0
; LA32F-NEXT: move $a3, $a1
; LA32F-NEXT: lu12i.w $a1, 261888
; LA32F-NEXT: move $a0, $zero
; LA32F-NEXT: bl __divdf3
; LA32F-NEXT: ld.w $ra, $sp, 12 # 4-byte Folded Reload
; LA32F-NEXT: addi.w $sp, $sp, 16
; LA32F-NEXT: ret
;
; LA32D-LABEL: frsqrt_f64:
; LA32D: # %bb.0:
; LA32D-NEXT: frsqrt.d $fa0, $fa0
; LA32D-NEXT: ret
;
; LA64F-LABEL: frsqrt_f64:
; LA64F: # %bb.0:
; LA64F-NEXT: addi.d $sp, $sp, -16
; LA64F-NEXT: st.d $ra, $sp, 8 # 8-byte Folded Spill
; LA64F-NEXT: bl sqrt
; LA64F-NEXT: move $a1, $a0
; LA64F-NEXT: lu52i.d $a0, $zero, 1023
; LA64F-NEXT: bl __divdf3
; LA64F-NEXT: ld.d $ra, $sp, 8 # 8-byte Folded Reload
; LA64F-NEXT: addi.d $sp, $sp, 16
; LA64F-NEXT: ret
;
; LA64D-LABEL: frsqrt_f64:
; LA64D: # %bb.0:
; LA64D-NEXT: frsqrt.d $fa0, $fa0
; LA64D-NEXT: ret
%1 = call double @llvm.sqrt.f64(double %a)
%2 = fdiv double 1.0, %1
ret double %2
}