caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
b20da5117fb66e7f9bcb56cb14af86dcafe2ee9a
clang-p2996/llvm/test/CodeGen/RISCV/half-arith.ll
Craig Topper eb44f3fc58 [RISCV] Add rv32i/rv64i command lines to some floating point tests. NFC 
This improves our coverage of soft float libcalls lowering.

Remove most of the test cases from rv64i-single-softfloat.ll. They
were duplicated in the test files that now test softflow. Only
a couple test cases for constrained FP remain. Those should be
removed when we start supporting constrained FP.

This is follow up from D113528.
2021-11-11 10:56:27 -08:00

2153 lines
73 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+experimental-zfh -verify-machineinstrs \
; RUN: -target-abi ilp32f < %s | FileCheck -check-prefix=RV32IZFH %s
; RUN: llc -mtriple=riscv64 -mattr=+experimental-zfh -verify-machineinstrs \
; RUN: -target-abi lp64f < %s | FileCheck -check-prefix=RV64IZFH %s
; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefix=RV32I %s
; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefix=RV64I %s
; These tests are each targeted at a particular RISC-V FPU instruction. Most
; other files in this folder exercise LLVM IR instructions that don't directly
; match a RISC-V instruction.
define half @fadd_s(half %a, half %b) nounwind {
; RV32IZFH-LABEL: fadd_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fadd.h fa0, fa0, fa1
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fadd_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fadd.h fa0, fa0, fa1
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fadd_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 4(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 0(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a1
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s0, a1, -1
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s2, 0(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 4(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fadd_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -32
; RV64I-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 0(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a1
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s0, a1, -1
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s1
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
%1 = fadd half %a, %b
ret half %1
}
define half @fsub_s(half %a, half %b) nounwind {
; RV32IZFH-LABEL: fsub_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fsub.h fa0, fa0, fa1
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fsub_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fsub.h fa0, fa0, fa1
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fsub_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 4(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 0(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a1
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s0, a1, -1
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: call __subsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s2, 0(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 4(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fsub_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -32
; RV64I-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 0(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a1
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s0, a1, -1
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s1
; RV64I-NEXT: call __subsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
%1 = fsub half %a, %b
ret half %1
}
define half @fmul_s(half %a, half %b) nounwind {
; RV32IZFH-LABEL: fmul_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fmul.h fa0, fa0, fa1
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fmul_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fmul.h fa0, fa0, fa1
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fmul_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 4(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 0(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a1
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s0, a1, -1
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: call __mulsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s2, 0(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 4(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fmul_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -32
; RV64I-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 0(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a1
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s0, a1, -1
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s1
; RV64I-NEXT: call __mulsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
%1 = fmul half %a, %b
ret half %1
}
define half @fdiv_s(half %a, half %b) nounwind {
; RV32IZFH-LABEL: fdiv_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fdiv.h fa0, fa0, fa1
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fdiv_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fdiv.h fa0, fa0, fa1
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fdiv_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 4(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 0(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a1
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s0, a1, -1
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: call __divsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s2, 0(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 4(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fdiv_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -32
; RV64I-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 0(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a1
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s0, a1, -1
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s1
; RV64I-NEXT: call __divsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
%1 = fdiv half %a, %b
ret half %1
}
declare half @llvm.sqrt.f16(half)
define half @fsqrt_s(half %a) nounwind {
; RV32IZFH-LABEL: fsqrt_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fsqrt.h fa0, fa0
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fsqrt_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fsqrt.h fa0, fa0
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fsqrt_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi a1, a1, -1
; RV32I-NEXT: and a0, a0, a1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: call sqrtf@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fsqrt_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw a1, a1, -1
; RV64I-NEXT: and a0, a0, a1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: call sqrtf@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = call half @llvm.sqrt.f16(half %a)
ret half %1
}
declare half @llvm.copysign.f16(half, half)
define half @fsgnj_s(half %a, half %b) nounwind {
; RV32IZFH-LABEL: fsgnj_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fsgnj.h fa0, fa0, fa1
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fsgnj_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fsgnj.h fa0, fa0, fa1
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fsgnj_s:
; RV32I: # %bb.0:
; RV32I-NEXT: lui a2, 1048568
; RV32I-NEXT: and a1, a1, a2
; RV32I-NEXT: lui a2, 8
; RV32I-NEXT: addi a2, a2, -1
; RV32I-NEXT: and a0, a0, a2
; RV32I-NEXT: or a0, a0, a1
; RV32I-NEXT: ret
;
; RV64I-LABEL: fsgnj_s:
; RV64I: # %bb.0:
; RV64I-NEXT: lui a2, 1048568
; RV64I-NEXT: and a1, a1, a2
; RV64I-NEXT: lui a2, 8
; RV64I-NEXT: addiw a2, a2, -1
; RV64I-NEXT: and a0, a0, a2
; RV64I-NEXT: or a0, a0, a1
; RV64I-NEXT: ret
%1 = call half @llvm.copysign.f16(half %a, half %b)
ret half %1
}
; This function performs extra work to ensure that
; DAGCombiner::visitBITCAST doesn't replace the fneg with an xor.
define i32 @fneg_s(half %a, half %b) nounwind {
; RV32IZFH-LABEL: fneg_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fadd.h ft0, fa0, fa0
; RV32IZFH-NEXT: fneg.h ft1, ft0
; RV32IZFH-NEXT: feq.h a0, ft0, ft1
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fneg_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fadd.h ft0, fa0, fa0
; RV64IZFH-NEXT: fneg.h ft1, ft0
; RV64IZFH-NEXT: feq.h a0, ft0, ft1
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fneg_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 4(sp) # 4-byte Folded Spill
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s1, a1, -1
; RV32I-NEXT: and a0, a0, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: and a0, a0, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s0, a0
; RV32I-NEXT: lui a0, 524288
; RV32I-NEXT: xor a0, s0, a0
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: and a0, a0, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s0
; RV32I-NEXT: call __eqsf2@plt
; RV32I-NEXT: seqz a0, a0
; RV32I-NEXT: lw s1, 4(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fneg_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -32
; RV64I-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s1, a1, -1
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s0, a0
; RV64I-NEXT: lui a0, 524288
; RV64I-NEXT: xor a0, s0, a0
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: call __eqsf2@plt
; RV64I-NEXT: seqz a0, a0
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
%1 = fadd half %a, %a
%2 = fneg half %1
%3 = fcmp oeq half %1, %2
%4 = zext i1 %3 to i32
ret i32 %4
}
; This function performs extra work to ensure that
; DAGCombiner::visitBITCAST doesn't replace the fneg with an xor.
define half @fsgnjn_s(half %a, half %b) nounwind {
; RV32IZFH-LABEL: fsgnjn_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fadd.h ft0, fa0, fa1
; RV32IZFH-NEXT: fsgnjn.h fa0, fa0, ft0
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fsgnjn_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fadd.h ft0, fa0, fa1
; RV64IZFH-NEXT: fsgnjn.h fa0, fa0, ft0
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fsgnjn_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -32
; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s3, a1
; RV32I-NEXT: mv s2, a0
; RV32I-NEXT: lui a0, 16
; RV32I-NEXT: addi s0, a0, -1
; RV32I-NEXT: and a0, s2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s3, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: lui a1, 524288
; RV32I-NEXT: xor a0, a0, a1
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lui a1, 1048568
; RV32I-NEXT: and a0, a0, a1
; RV32I-NEXT: lui a1, 8
; RV32I-NEXT: addi a1, a1, -1
; RV32I-NEXT: and a1, s2, a1
; RV32I-NEXT: or a0, a1, a0
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fsgnjn_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -48
; RV64I-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 32(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s3, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s3, a1
; RV64I-NEXT: mv s2, a0
; RV64I-NEXT: lui a0, 16
; RV64I-NEXT: addiw s0, a0, -1
; RV64I-NEXT: and a0, s2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s3, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s1
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: lui a1, 524288
; RV64I-NEXT: xor a0, a0, a1
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: lui a1, 1048568
; RV64I-NEXT: and a0, a0, a1
; RV64I-NEXT: lui a1, 8
; RV64I-NEXT: addiw a1, a1, -1
; RV64I-NEXT: and a1, s2, a1
; RV64I-NEXT: or a0, a1, a0
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
%1 = fadd half %a, %b
%2 = fneg half %1
%3 = call half @llvm.copysign.f16(half %a, half %2)
ret half %3
}
declare half @llvm.fabs.f16(half)
; This function performs extra work to ensure that
; DAGCombiner::visitBITCAST doesn't replace the fabs with an and.
define half @fabs_s(half %a, half %b) nounwind {
; RV32IZFH-LABEL: fabs_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fadd.h ft0, fa0, fa1
; RV32IZFH-NEXT: fabs.h ft1, ft0
; RV32IZFH-NEXT: fadd.h fa0, ft1, ft0
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fabs_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fadd.h ft0, fa0, fa1
; RV64IZFH-NEXT: fabs.h ft1, ft0
; RV64IZFH-NEXT: fadd.h fa0, ft1, ft0
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fabs_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 4(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 0(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a1
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s1, a1, -1
; RV32I-NEXT: and a0, a0, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s0, a0
; RV32I-NEXT: and a0, s2, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s0
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: and a0, a0, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s0, a0
; RV32I-NEXT: lui a0, 524288
; RV32I-NEXT: addi a0, a0, -1
; RV32I-NEXT: and a0, s0, a0
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: and a0, a0, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s2, 0(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 4(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fabs_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -32
; RV64I-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 0(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a1
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s1, a1, -1
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s0, a0
; RV64I-NEXT: and a0, s2, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s0, a0
; RV64I-NEXT: lui a0, 524288
; RV64I-NEXT: addiw a0, a0, -1
; RV64I-NEXT: and a0, s0, a0
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, s0
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
%1 = fadd half %a, %b
%2 = call half @llvm.fabs.f16(half %1)
%3 = fadd half %2, %1
ret half %3
}
declare half @llvm.minnum.f16(half, half)
define half @fmin_s(half %a, half %b) nounwind {
; RV32IZFH-LABEL: fmin_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fmin.h fa0, fa0, fa1
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fmin_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fmin.h fa0, fa0, fa1
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fmin_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 4(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 0(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a1
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s0, a1, -1
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: call fminf@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s2, 0(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 4(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fmin_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -32
; RV64I-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 0(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a1
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s0, a1, -1
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s1
; RV64I-NEXT: call fminf@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
%1 = call half @llvm.minnum.f16(half %a, half %b)
ret half %1
}
declare half @llvm.maxnum.f16(half, half)
define half @fmax_s(half %a, half %b) nounwind {
; RV32IZFH-LABEL: fmax_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fmax.h fa0, fa0, fa1
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fmax_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fmax.h fa0, fa0, fa1
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fmax_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 4(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 0(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a1
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s0, a1, -1
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: call fmaxf@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s2, 0(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 4(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fmax_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -32
; RV64I-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 0(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a1
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s0, a1, -1
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s1
; RV64I-NEXT: call fmaxf@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
%1 = call half @llvm.maxnum.f16(half %a, half %b)
ret half %1
}
define i32 @feq_s(half %a, half %b) nounwind {
; RV32IZFH-LABEL: feq_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: feq.h a0, fa0, fa1
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: feq_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: feq.h a0, fa0, fa1
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: feq_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 4(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 0(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a1
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s0, a1, -1
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: call __eqsf2@plt
; RV32I-NEXT: seqz a0, a0
; RV32I-NEXT: lw s2, 0(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 4(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: feq_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -32
; RV64I-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 0(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a1
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s0, a1, -1
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s1
; RV64I-NEXT: call __eqsf2@plt
; RV64I-NEXT: seqz a0, a0
; RV64I-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
%1 = fcmp oeq half %a, %b
%2 = zext i1 %1 to i32
ret i32 %2
}
define i32 @flt_s(half %a, half %b) nounwind {
; RV32IZFH-LABEL: flt_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: flt.h a0, fa0, fa1
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: flt_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: flt.h a0, fa0, fa1
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: flt_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 4(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 0(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a1
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s0, a1, -1
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: call __ltsf2@plt
; RV32I-NEXT: slti a0, a0, 0
; RV32I-NEXT: lw s2, 0(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 4(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: flt_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -32
; RV64I-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 0(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a1
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s0, a1, -1
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s1
; RV64I-NEXT: call __ltsf2@plt
; RV64I-NEXT: slti a0, a0, 0
; RV64I-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
%1 = fcmp olt half %a, %b
%2 = zext i1 %1 to i32
ret i32 %2
}
define i32 @fle_s(half %a, half %b) nounwind {
; RV32IZFH-LABEL: fle_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fle.h a0, fa0, fa1
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fle_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fle.h a0, fa0, fa1
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fle_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 4(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 0(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a1
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s0, a1, -1
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: call __lesf2@plt
; RV32I-NEXT: slti a0, a0, 1
; RV32I-NEXT: lw s2, 0(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 4(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fle_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -32
; RV64I-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 0(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a1
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s0, a1, -1
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s1
; RV64I-NEXT: call __lesf2@plt
; RV64I-NEXT: slti a0, a0, 1
; RV64I-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
%1 = fcmp ole half %a, %b
%2 = zext i1 %1 to i32
ret i32 %2
}
declare half @llvm.fma.f16(half, half, half)
define half @fmadd_s(half %a, half %b, half %c) nounwind {
; RV32IZFH-LABEL: fmadd_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fmadd.h fa0, fa0, fa1, fa2
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fmadd_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fmadd.h fa0, fa0, fa1, fa2
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fmadd_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -32
; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a2
; RV32I-NEXT: mv s1, a1
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s0, a1, -1
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s3, a0
; RV32I-NEXT: and a0, s1, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a2, a0
; RV32I-NEXT: mv a0, s3
; RV32I-NEXT: mv a1, s1
; RV32I-NEXT: call fmaf@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fmadd_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -48
; RV64I-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 32(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s3, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a2
; RV64I-NEXT: mv s1, a1
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s0, a1, -1
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s3, a0
; RV64I-NEXT: and a0, s1, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a2, a0
; RV64I-NEXT: mv a0, s3
; RV64I-NEXT: mv a1, s1
; RV64I-NEXT: call fmaf@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
%1 = call half @llvm.fma.f16(half %a, half %b, half %c)
ret half %1
}
define half @fmsub_s(half %a, half %b, half %c) nounwind {
; RV32IZFH-LABEL: fmsub_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fmv.h.x ft0, zero
; RV32IZFH-NEXT: fadd.h ft0, fa2, ft0
; RV32IZFH-NEXT: fmsub.h fa0, fa0, fa1, ft0
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fmsub_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fmv.h.x ft0, zero
; RV64IZFH-NEXT: fadd.h ft0, fa2, ft0
; RV64IZFH-NEXT: fmsub.h fa0, fa0, fa1, ft0
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fmsub_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -32
; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s4, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a1
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: lui a0, 16
; RV32I-NEXT: addi s0, a0, -1
; RV32I-NEXT: and a0, a2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, zero
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: lui a1, 524288
; RV32I-NEXT: xor a0, a0, a1
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s4, a0
; RV32I-NEXT: and a0, s1, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s3, a0
; RV32I-NEXT: and a0, s2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s4, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a2, a0
; RV32I-NEXT: mv a0, s3
; RV32I-NEXT: mv a1, s1
; RV32I-NEXT: call fmaf@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fmsub_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -48
; RV64I-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 32(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s3, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s4, 0(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a1
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: lui a0, 16
; RV64I-NEXT: addiw s0, a0, -1
; RV64I-NEXT: and a0, a2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, zero
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: lui a1, 524288
; RV64I-NEXT: xor a0, a0, a1
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s4, a0
; RV64I-NEXT: and a0, s1, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s3, a0
; RV64I-NEXT: and a0, s2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s4, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a2, a0
; RV64I-NEXT: mv a0, s3
; RV64I-NEXT: mv a1, s1
; RV64I-NEXT: call fmaf@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s4, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
%c_ = fadd half 0.0, %c ; avoid negation using xor
%negc = fsub half -0.0, %c_
%1 = call half @llvm.fma.f16(half %a, half %b, half %negc)
ret half %1
}
define half @fnmadd_s(half %a, half %b, half %c) nounwind {
; RV32IZFH-LABEL: fnmadd_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fmv.h.x ft0, zero
; RV32IZFH-NEXT: fadd.h ft1, fa0, ft0
; RV32IZFH-NEXT: fadd.h ft0, fa2, ft0
; RV32IZFH-NEXT: fnmadd.h fa0, ft1, fa1, ft0
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fnmadd_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fmv.h.x ft0, zero
; RV64IZFH-NEXT: fadd.h ft1, fa0, ft0
; RV64IZFH-NEXT: fadd.h ft0, fa2, ft0
; RV64IZFH-NEXT: fnmadd.h fa0, ft1, fa1, ft0
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fnmadd_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -32
; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s4, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s3, a2
; RV32I-NEXT: mv s2, a1
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s1, a1, -1
; RV32I-NEXT: and a0, a0, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, zero
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s4, a0
; RV32I-NEXT: and a0, s3, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, zero
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s0, a0
; RV32I-NEXT: and a0, s4, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: lui s4, 524288
; RV32I-NEXT: xor a0, a0, s4
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s3, a0
; RV32I-NEXT: and a0, s0, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: xor a0, a0, s4
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s4, a0
; RV32I-NEXT: and a0, s2, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s2, a0
; RV32I-NEXT: and a0, s3, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s0, a0
; RV32I-NEXT: and a0, s4, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a2, a0
; RV32I-NEXT: mv a0, s0
; RV32I-NEXT: mv a1, s2
; RV32I-NEXT: call fmaf@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fnmadd_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -48
; RV64I-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 32(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s3, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s4, 0(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s3, a2
; RV64I-NEXT: mv s2, a1
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s1, a1, -1
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, zero
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s4, a0
; RV64I-NEXT: and a0, s3, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, zero
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s0, a0
; RV64I-NEXT: and a0, s4, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: lui s4, 524288
; RV64I-NEXT: xor a0, a0, s4
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s3, a0
; RV64I-NEXT: and a0, s0, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: xor a0, a0, s4
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s4, a0
; RV64I-NEXT: and a0, s2, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s2, a0
; RV64I-NEXT: and a0, s3, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s0, a0
; RV64I-NEXT: and a0, s4, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a2, a0
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: mv a1, s2
; RV64I-NEXT: call fmaf@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s4, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
%a_ = fadd half 0.0, %a
%c_ = fadd half 0.0, %c
%nega = fsub half -0.0, %a_
%negc = fsub half -0.0, %c_
%1 = call half @llvm.fma.f16(half %nega, half %b, half %negc)
ret half %1
}
define half @fnmadd_s_2(half %a, half %b, half %c) nounwind {
; RV32IZFH-LABEL: fnmadd_s_2:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fmv.h.x ft0, zero
; RV32IZFH-NEXT: fadd.h ft1, fa1, ft0
; RV32IZFH-NEXT: fadd.h ft0, fa2, ft0
; RV32IZFH-NEXT: fnmadd.h fa0, ft1, fa0, ft0
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fnmadd_s_2:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fmv.h.x ft0, zero
; RV64IZFH-NEXT: fadd.h ft1, fa1, ft0
; RV64IZFH-NEXT: fadd.h ft0, fa2, ft0
; RV64IZFH-NEXT: fnmadd.h fa0, ft1, fa0, ft0
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fnmadd_s_2:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -32
; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s4, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s3, a2
; RV32I-NEXT: mv s2, a0
; RV32I-NEXT: lui a0, 16
; RV32I-NEXT: addi s1, a0, -1
; RV32I-NEXT: and a0, a1, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, zero
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s4, a0
; RV32I-NEXT: and a0, s3, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, zero
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s0, a0
; RV32I-NEXT: and a0, s4, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: lui s4, 524288
; RV32I-NEXT: xor a0, a0, s4
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s3, a0
; RV32I-NEXT: and a0, s0, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: xor a0, a0, s4
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s4, a0
; RV32I-NEXT: and a0, s2, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s2, a0
; RV32I-NEXT: and a0, s3, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s0, a0
; RV32I-NEXT: and a0, s4, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a2, a0
; RV32I-NEXT: mv a0, s2
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: call fmaf@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fnmadd_s_2:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -48
; RV64I-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 32(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s3, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s4, 0(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s3, a2
; RV64I-NEXT: mv s2, a0
; RV64I-NEXT: lui a0, 16
; RV64I-NEXT: addiw s1, a0, -1
; RV64I-NEXT: and a0, a1, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, zero
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s4, a0
; RV64I-NEXT: and a0, s3, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, zero
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s0, a0
; RV64I-NEXT: and a0, s4, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: lui s4, 524288
; RV64I-NEXT: xor a0, a0, s4
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s3, a0
; RV64I-NEXT: and a0, s0, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: xor a0, a0, s4
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s4, a0
; RV64I-NEXT: and a0, s2, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s2, a0
; RV64I-NEXT: and a0, s3, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s0, a0
; RV64I-NEXT: and a0, s4, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a2, a0
; RV64I-NEXT: mv a0, s2
; RV64I-NEXT: mv a1, s0
; RV64I-NEXT: call fmaf@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s4, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
%b_ = fadd half 0.0, %b
%c_ = fadd half 0.0, %c
%negb = fsub half -0.0, %b_
%negc = fsub half -0.0, %c_
%1 = call half @llvm.fma.f16(half %a, half %negb, half %negc)
ret half %1
}
define half @fnmsub_s(half %a, half %b, half %c) nounwind {
; RV32IZFH-LABEL: fnmsub_s:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fmv.h.x ft0, zero
; RV32IZFH-NEXT: fadd.h ft0, fa0, ft0
; RV32IZFH-NEXT: fnmsub.h fa0, ft0, fa1, fa2
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fnmsub_s:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fmv.h.x ft0, zero
; RV64IZFH-NEXT: fadd.h ft0, fa0, ft0
; RV64IZFH-NEXT: fnmsub.h fa0, ft0, fa1, fa2
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fnmsub_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -32
; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s4, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a2
; RV32I-NEXT: mv s1, a1
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s0, a1, -1
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, zero
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: lui a1, 524288
; RV32I-NEXT: xor a0, a0, a1
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s4, a0
; RV32I-NEXT: and a0, s1, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s3, a0
; RV32I-NEXT: and a0, s2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s4, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, s3
; RV32I-NEXT: mv a2, s1
; RV32I-NEXT: call fmaf@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fnmsub_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -48
; RV64I-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 32(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s3, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s4, 0(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a2
; RV64I-NEXT: mv s1, a1
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s0, a1, -1
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, zero
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: lui a1, 524288
; RV64I-NEXT: xor a0, a0, a1
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s4, a0
; RV64I-NEXT: and a0, s1, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s3, a0
; RV64I-NEXT: and a0, s2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s4, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, s3
; RV64I-NEXT: mv a2, s1
; RV64I-NEXT: call fmaf@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s4, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
%a_ = fadd half 0.0, %a
%nega = fsub half -0.0, %a_
%1 = call half @llvm.fma.f16(half %nega, half %b, half %c)
ret half %1
}
define half @fnmsub_s_2(half %a, half %b, half %c) nounwind {
; RV32IZFH-LABEL: fnmsub_s_2:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fmv.h.x ft0, zero
; RV32IZFH-NEXT: fadd.h ft0, fa1, ft0
; RV32IZFH-NEXT: fnmsub.h fa0, ft0, fa0, fa2
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fnmsub_s_2:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fmv.h.x ft0, zero
; RV64IZFH-NEXT: fadd.h ft0, fa1, ft0
; RV64IZFH-NEXT: fnmsub.h fa0, ft0, fa0, fa2
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fnmsub_s_2:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -32
; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s4, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a2
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: lui a0, 16
; RV32I-NEXT: addi s0, a0, -1
; RV32I-NEXT: and a0, a1, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, zero
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: lui a1, 524288
; RV32I-NEXT: xor a0, a0, a1
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s4, a0
; RV32I-NEXT: and a0, s1, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s3, a0
; RV32I-NEXT: and a0, s2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s4, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s3
; RV32I-NEXT: mv a2, s1
; RV32I-NEXT: call fmaf@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fnmsub_s_2:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -48
; RV64I-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 32(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s3, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s4, 0(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a2
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: lui a0, 16
; RV64I-NEXT: addiw s0, a0, -1
; RV64I-NEXT: and a0, a1, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, zero
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: lui a1, 524288
; RV64I-NEXT: xor a0, a0, a1
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s4, a0
; RV64I-NEXT: and a0, s1, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s3, a0
; RV64I-NEXT: and a0, s2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s4, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s3
; RV64I-NEXT: mv a2, s1
; RV64I-NEXT: call fmaf@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s4, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
%b_ = fadd half 0.0, %b
%negb = fsub half -0.0, %b_
%1 = call half @llvm.fma.f16(half %a, half %negb, half %c)
ret half %1
}
define half @fmadd_s_contract(half %a, half %b, half %c) nounwind {
; RV32IZFH-LABEL: fmadd_s_contract:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fmadd.h fa0, fa0, fa1, fa2
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fmadd_s_contract:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fmadd.h fa0, fa0, fa1, fa2
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fmadd_s_contract:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -32
; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a2
; RV32I-NEXT: mv s3, a1
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s1, a1, -1
; RV32I-NEXT: and a0, a0, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s0, a0
; RV32I-NEXT: and a0, s3, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s0
; RV32I-NEXT: call __mulsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s0, a0
; RV32I-NEXT: and a0, s2, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s2, a0
; RV32I-NEXT: and a0, s0, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, s2
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fmadd_s_contract:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -48
; RV64I-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 32(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s3, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a2
; RV64I-NEXT: mv s3, a1
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s1, a1, -1
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s0, a0
; RV64I-NEXT: and a0, s3, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: call __mulsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s0, a0
; RV64I-NEXT: and a0, s2, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s2, a0
; RV64I-NEXT: and a0, s0, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, s2
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
%1 = fmul contract half %a, %b
%2 = fadd contract half %1, %c
ret half %2
}
define half @fmsub_s_contract(half %a, half %b, half %c) nounwind {
; RV32IZFH-LABEL: fmsub_s_contract:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fmv.h.x ft0, zero
; RV32IZFH-NEXT: fadd.h ft0, fa2, ft0
; RV32IZFH-NEXT: fmsub.h fa0, fa0, fa1, ft0
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fmsub_s_contract:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fmv.h.x ft0, zero
; RV64IZFH-NEXT: fadd.h ft0, fa2, ft0
; RV64IZFH-NEXT: fmsub.h fa0, fa0, fa1, ft0
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fmsub_s_contract:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -32
; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s3, a1
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: lui a0, 16
; RV32I-NEXT: addi s0, a0, -1
; RV32I-NEXT: and a0, a2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, zero
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s2, a0
; RV32I-NEXT: and a0, s1, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s3, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: call __mulsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: call __subsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fmsub_s_contract:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -48
; RV64I-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 32(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s3, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s3, a1
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: lui a0, 16
; RV64I-NEXT: addiw s0, a0, -1
; RV64I-NEXT: and a0, a2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, zero
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s2, a0
; RV64I-NEXT: and a0, s1, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s3, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s1
; RV64I-NEXT: call __mulsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s1
; RV64I-NEXT: call __subsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
%c_ = fadd half 0.0, %c ; avoid negation using xor
%1 = fmul contract half %a, %b
%2 = fsub contract half %1, %c_
ret half %2
}
define half @fnmadd_s_contract(half %a, half %b, half %c) nounwind {
; RV32IZFH-LABEL: fnmadd_s_contract:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fmv.h.x ft0, zero
; RV32IZFH-NEXT: fadd.h ft1, fa0, ft0
; RV32IZFH-NEXT: fadd.h ft2, fa1, ft0
; RV32IZFH-NEXT: fadd.h ft0, fa2, ft0
; RV32IZFH-NEXT: fnmadd.h fa0, ft1, ft2, ft0
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fnmadd_s_contract:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fmv.h.x ft0, zero
; RV64IZFH-NEXT: fadd.h ft1, fa0, ft0
; RV64IZFH-NEXT: fadd.h ft2, fa1, ft0
; RV64IZFH-NEXT: fadd.h ft0, fa2, ft0
; RV64IZFH-NEXT: fnmadd.h fa0, ft1, ft2, ft0
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fnmadd_s_contract:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -32
; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s4, 8(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a2
; RV32I-NEXT: mv s0, a1
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s1, a1, -1
; RV32I-NEXT: and a0, a0, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, zero
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s3, a0
; RV32I-NEXT: and a0, s0, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, zero
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s4, a0
; RV32I-NEXT: and a0, s2, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, zero
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s2, a0
; RV32I-NEXT: and a0, s3, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s0, a0
; RV32I-NEXT: and a0, s4, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s0
; RV32I-NEXT: call __mulsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: and a0, a0, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: lui a1, 524288
; RV32I-NEXT: xor a0, a0, a1
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s0, a0
; RV32I-NEXT: and a0, s2, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s2, a0
; RV32I-NEXT: and a0, s0, s1
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, s2
; RV32I-NEXT: call __subsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fnmadd_s_contract:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -48
; RV64I-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 32(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s3, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s4, 0(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a2
; RV64I-NEXT: mv s0, a1
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s1, a1, -1
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, zero
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s3, a0
; RV64I-NEXT: and a0, s0, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, zero
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s4, a0
; RV64I-NEXT: and a0, s2, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, zero
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s2, a0
; RV64I-NEXT: and a0, s3, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s0, a0
; RV64I-NEXT: and a0, s4, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: call __mulsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: lui a1, 524288
; RV64I-NEXT: xor a0, a0, a1
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s0, a0
; RV64I-NEXT: and a0, s2, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s2, a0
; RV64I-NEXT: and a0, s0, s1
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, s2
; RV64I-NEXT: call __subsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s4, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
%a_ = fadd half 0.0, %a ; avoid negation using xor
%b_ = fadd half 0.0, %b ; avoid negation using xor
%c_ = fadd half 0.0, %c ; avoid negation using xor
%1 = fmul contract half %a_, %b_
%2 = fneg half %1
%3 = fsub contract half %2, %c_
ret half %3
}
define half @fnmsub_s_contract(half %a, half %b, half %c) nounwind {
; RV32IZFH-LABEL: fnmsub_s_contract:
; RV32IZFH: # %bb.0:
; RV32IZFH-NEXT: fmv.h.x ft0, zero
; RV32IZFH-NEXT: fadd.h ft1, fa0, ft0
; RV32IZFH-NEXT: fadd.h ft0, fa1, ft0
; RV32IZFH-NEXT: fnmsub.h fa0, ft1, ft0, fa2
; RV32IZFH-NEXT: ret
;
; RV64IZFH-LABEL: fnmsub_s_contract:
; RV64IZFH: # %bb.0:
; RV64IZFH-NEXT: fmv.h.x ft0, zero
; RV64IZFH-NEXT: fadd.h ft1, fa0, ft0
; RV64IZFH-NEXT: fadd.h ft0, fa1, ft0
; RV64IZFH-NEXT: fnmsub.h fa0, ft1, ft0, fa2
; RV64IZFH-NEXT: ret
;
; RV32I-LABEL: fnmsub_s_contract:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -32
; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s2, a2
; RV32I-NEXT: mv s1, a1
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi s0, a1, -1
; RV32I-NEXT: and a0, a0, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, zero
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s3, a0
; RV32I-NEXT: and a0, s1, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, zero
; RV32I-NEXT: call __addsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s3, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s3, a0
; RV32I-NEXT: and a0, s1, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s3
; RV32I-NEXT: call __mulsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: and a0, s2, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv s2, a0
; RV32I-NEXT: and a0, s1, s0
; RV32I-NEXT: call __gnu_h2f_ieee@plt
; RV32I-NEXT: mv a1, a0
; RV32I-NEXT: mv a0, s2
; RV32I-NEXT: call __subsf3@plt
; RV32I-NEXT: call __gnu_f2h_ieee@plt
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fnmsub_s_contract:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -48
; RV64I-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 32(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s3, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: mv s2, a2
; RV64I-NEXT: mv s1, a1
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw s0, a1, -1
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, zero
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s3, a0
; RV64I-NEXT: and a0, s1, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, zero
; RV64I-NEXT: call __addsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s3, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s3, a0
; RV64I-NEXT: and a0, s1, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s3
; RV64I-NEXT: call __mulsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: and a0, s2, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv s2, a0
; RV64I-NEXT: and a0, s1, s0
; RV64I-NEXT: call __gnu_h2f_ieee@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: mv a0, s2
; RV64I-NEXT: call __subsf3@plt
; RV64I-NEXT: call __gnu_f2h_ieee@plt
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
%a_ = fadd half 0.0, %a ; avoid negation using xor
%b_ = fadd half 0.0, %b ; avoid negation using xor
%1 = fmul contract half %a_, %b_
%2 = fsub contract half %c, %1
ret half %2
}
Reference in New Issue View Git Blame Copy Permalink