caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
1e2c5481502b305d2e38ce94defffb43b82dbe3c
clang-p2996/llvm/test/CodeGen/RISCV/double-convert.ll
Craig Topper a2b5b584a5 [RISCV] Use register allocation hints to improve use of compressed instructions. 
Compressed instructions usually require one of the source registers
to also be the source register. The register allocator doesn't have
that bias on its own.

This patch adds register allocation hints to introduce this bias.
I've started with ADDI, ADDIW, and SLLI. These all have a 5-bit
field for the register. If the source and dest register are the
same they are guaranteed to compress as long as the immediate is
also 6 bits.

This code was inspired by similar code from the SystemZ target.

Reviewed By: reames

Differential Revision: https://reviews.llvm.org/D138242
2022-11-25 08:39:44 -08:00

2076 lines
66 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+d -verify-machineinstrs < %s \
; RUN: -target-abi=ilp32d | FileCheck -check-prefixes=CHECKIFD,RV32IFD %s
; RUN: llc -mtriple=riscv64 -mattr=+d -verify-machineinstrs < %s \
; RUN: -target-abi=lp64d | FileCheck -check-prefixes=CHECKIFD,RV64IFD %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
define float @fcvt_s_d(double %a) nounwind {
; CHECKIFD-LABEL: fcvt_s_d:
; CHECKIFD: # %bb.0:
; CHECKIFD-NEXT: fcvt.s.d fa0, fa0
; CHECKIFD-NEXT: ret
;
; RV32I-LABEL: fcvt_s_d:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __truncdfsf2@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_s_d:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __truncdfsf2@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptrunc double %a to float
ret float %1
}
define double @fcvt_d_s(float %a) nounwind {
; CHECKIFD-LABEL: fcvt_d_s:
; CHECKIFD: # %bb.0:
; CHECKIFD-NEXT: fcvt.d.s fa0, fa0
; CHECKIFD-NEXT: ret
;
; RV32I-LABEL: fcvt_d_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __extendsfdf2@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_d_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __extendsfdf2@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fpext float %a to double
ret double %1
}
define i32 @fcvt_w_d(double %a) nounwind {
; CHECKIFD-LABEL: fcvt_w_d:
; CHECKIFD: # %bb.0:
; CHECKIFD-NEXT: fcvt.w.d a0, fa0, rtz
; CHECKIFD-NEXT: ret
;
; RV32I-LABEL: fcvt_w_d:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __fixdfsi@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_w_d:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __fixdfsi@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptosi double %a to i32
ret i32 %1
}
define i32 @fcvt_w_d_sat(double %a) nounwind {
; CHECKIFD-LABEL: fcvt_w_d_sat:
; CHECKIFD: # %bb.0: # %start
; CHECKIFD-NEXT: fcvt.w.d a0, fa0, rtz
; CHECKIFD-NEXT: feq.d a1, fa0, fa0
; CHECKIFD-NEXT: seqz a1, a1
; CHECKIFD-NEXT: addi a1, a1, -1
; CHECKIFD-NEXT: and a0, a1, a0
; CHECKIFD-NEXT: ret
;
; RV32I-LABEL: fcvt_w_d_sat:
; RV32I: # %bb.0: # %start
; 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 s0, a1
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: lui a3, 269824
; RV32I-NEXT: addi a3, a3, -1
; RV32I-NEXT: lui a2, 1047552
; RV32I-NEXT: call __gtdf2@plt
; RV32I-NEXT: mv s2, a0
; RV32I-NEXT: lui a3, 794112
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: call __gedf2@plt
; RV32I-NEXT: mv s4, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: call __fixdfsi@plt
; RV32I-NEXT: mv s3, a0
; RV32I-NEXT: lui a0, 524288
; RV32I-NEXT: bgez s4, .LBB3_2
; RV32I-NEXT: # %bb.1: # %start
; RV32I-NEXT: lui s3, 524288
; RV32I-NEXT: .LBB3_2: # %start
; RV32I-NEXT: blez s2, .LBB3_4
; RV32I-NEXT: # %bb.3: # %start
; RV32I-NEXT: addi s3, a0, -1
; RV32I-NEXT: .LBB3_4: # %start
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: mv a2, s1
; RV32I-NEXT: mv a3, s0
; RV32I-NEXT: call __unorddf2@plt
; RV32I-NEXT: snez a0, a0
; RV32I-NEXT: addi a0, a0, -1
; RV32I-NEXT: and a0, a0, s3
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_w_d_sat:
; RV64I: # %bb.0: # %start
; 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 s0, a0
; RV64I-NEXT: li a1, -497
; RV64I-NEXT: slli a1, a1, 53
; RV64I-NEXT: call __gedf2@plt
; RV64I-NEXT: mv s2, a0
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: call __fixdfdi@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: lui s3, 524288
; RV64I-NEXT: bgez s2, .LBB3_2
; RV64I-NEXT: # %bb.1: # %start
; RV64I-NEXT: lui s1, 524288
; RV64I-NEXT: .LBB3_2: # %start
; RV64I-NEXT: li a0, 527
; RV64I-NEXT: slli a0, a0, 31
; RV64I-NEXT: addi a0, a0, -1
; RV64I-NEXT: slli a1, a0, 22
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: call __gtdf2@plt
; RV64I-NEXT: blez a0, .LBB3_4
; RV64I-NEXT: # %bb.3: # %start
; RV64I-NEXT: addiw s1, s3, -1
; RV64I-NEXT: .LBB3_4: # %start
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: mv a1, s0
; RV64I-NEXT: call __unorddf2@plt
; RV64I-NEXT: snez a0, a0
; RV64I-NEXT: addi a0, a0, -1
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
start:
%0 = tail call i32 @llvm.fptosi.sat.i32.f64(double %a)
ret i32 %0
}
declare i32 @llvm.fptosi.sat.i32.f64(double)
; For RV64D, fcvt.lu.d is semantically equivalent to fcvt.wu.d in this case
; because fptosi will produce poison if the result doesn't fit into an i32.
define i32 @fcvt_wu_d(double %a) nounwind {
; CHECKIFD-LABEL: fcvt_wu_d:
; CHECKIFD: # %bb.0:
; CHECKIFD-NEXT: fcvt.wu.d a0, fa0, rtz
; CHECKIFD-NEXT: ret
;
; RV32I-LABEL: fcvt_wu_d:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __fixunsdfsi@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_wu_d:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __fixunsdfsi@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptoui double %a to i32
ret i32 %1
}
; Test where the fptoui has multiple uses, one of which causes a sext to be
; inserted on RV64.
define i32 @fcvt_wu_d_multiple_use(double %x, i32* %y) nounwind {
; CHECKIFD-LABEL: fcvt_wu_d_multiple_use:
; CHECKIFD: # %bb.0:
; CHECKIFD-NEXT: fcvt.wu.d a0, fa0, rtz
; CHECKIFD-NEXT: bnez a0, .LBB5_2
; CHECKIFD-NEXT: # %bb.1:
; CHECKIFD-NEXT: li a0, 1
; CHECKIFD-NEXT: .LBB5_2:
; CHECKIFD-NEXT: ret
;
; RV32I-LABEL: fcvt_wu_d_multiple_use:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __fixunsdfsi@plt
; RV32I-NEXT: bnez a0, .LBB5_2
; RV32I-NEXT: # %bb.1:
; RV32I-NEXT: li a0, 1
; RV32I-NEXT: .LBB5_2:
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_wu_d_multiple_use:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __fixunsdfsi@plt
; RV64I-NEXT: bnez a0, .LBB5_2
; RV64I-NEXT: # %bb.1:
; RV64I-NEXT: li a0, 1
; RV64I-NEXT: .LBB5_2:
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%a = fptoui double %x to i32
%b = icmp eq i32 %a, 0
%c = select i1 %b, i32 1, i32 %a
ret i32 %c
}
define i32 @fcvt_wu_d_sat(double %a) nounwind {
; RV32IFD-LABEL: fcvt_wu_d_sat:
; RV32IFD: # %bb.0: # %start
; RV32IFD-NEXT: fcvt.wu.d a0, fa0, rtz
; RV32IFD-NEXT: feq.d a1, fa0, fa0
; RV32IFD-NEXT: seqz a1, a1
; RV32IFD-NEXT: addi a1, a1, -1
; RV32IFD-NEXT: and a0, a1, a0
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_wu_d_sat:
; RV64IFD: # %bb.0: # %start
; RV64IFD-NEXT: fcvt.wu.d a0, fa0, rtz
; RV64IFD-NEXT: feq.d a1, fa0, fa0
; RV64IFD-NEXT: seqz a1, a1
; RV64IFD-NEXT: addi a1, a1, -1
; RV64IFD-NEXT: and a0, a0, a1
; RV64IFD-NEXT: slli a0, a0, 32
; RV64IFD-NEXT: srli a0, a0, 32
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_wu_d_sat:
; RV32I: # %bb.0: # %start
; 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 s0, a1
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: lui a3, 270080
; RV32I-NEXT: addi a3, a3, -1
; RV32I-NEXT: lui a2, 1048064
; RV32I-NEXT: call __gtdf2@plt
; RV32I-NEXT: sgtz a0, a0
; RV32I-NEXT: neg s2, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: li a3, 0
; RV32I-NEXT: call __gedf2@plt
; RV32I-NEXT: slti a0, a0, 0
; RV32I-NEXT: addi s3, a0, -1
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: call __fixunsdfsi@plt
; RV32I-NEXT: and a0, s3, a0
; RV32I-NEXT: or a0, s2, a0
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_wu_d_sat:
; RV64I: # %bb.0: # %start
; 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, a0
; RV64I-NEXT: li a1, 0
; RV64I-NEXT: call __gedf2@plt
; RV64I-NEXT: mv s0, a0
; RV64I-NEXT: mv a0, s2
; RV64I-NEXT: call __fixunsdfdi@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: li a0, 1055
; RV64I-NEXT: slli a0, a0, 31
; RV64I-NEXT: addi a0, a0, -1
; RV64I-NEXT: slli a1, a0, 21
; RV64I-NEXT: mv a0, s2
; RV64I-NEXT: call __gtdf2@plt
; RV64I-NEXT: blez a0, .LBB6_2
; RV64I-NEXT: # %bb.1: # %start
; RV64I-NEXT: li a0, -1
; RV64I-NEXT: srli a0, a0, 32
; RV64I-NEXT: j .LBB6_3
; RV64I-NEXT: .LBB6_2:
; RV64I-NEXT: slti a0, s0, 0
; RV64I-NEXT: addi a0, a0, -1
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: .LBB6_3: # %start
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
start:
%0 = tail call i32 @llvm.fptoui.sat.i32.f64(double %a)
ret i32 %0
}
declare i32 @llvm.fptoui.sat.i32.f64(double)
define double @fcvt_d_w(i32 %a) nounwind {
; CHECKIFD-LABEL: fcvt_d_w:
; CHECKIFD: # %bb.0:
; CHECKIFD-NEXT: fcvt.d.w fa0, a0
; CHECKIFD-NEXT: ret
;
; RV32I-LABEL: fcvt_d_w:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __floatsidf@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_d_w:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sext.w a0, a0
; RV64I-NEXT: call __floatsidf@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = sitofp i32 %a to double
ret double %1
}
define double @fcvt_d_w_load(i32* %p) nounwind {
; CHECKIFD-LABEL: fcvt_d_w_load:
; CHECKIFD: # %bb.0:
; CHECKIFD-NEXT: lw a0, 0(a0)
; CHECKIFD-NEXT: fcvt.d.w fa0, a0
; CHECKIFD-NEXT: ret
;
; RV32I-LABEL: fcvt_d_w_load:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: lw a0, 0(a0)
; RV32I-NEXT: call __floatsidf@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_d_w_load:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: lw a0, 0(a0)
; RV64I-NEXT: call __floatsidf@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%a = load i32, i32* %p
%1 = sitofp i32 %a to double
ret double %1
}
define double @fcvt_d_wu(i32 %a) nounwind {
; CHECKIFD-LABEL: fcvt_d_wu:
; CHECKIFD: # %bb.0:
; CHECKIFD-NEXT: fcvt.d.wu fa0, a0
; CHECKIFD-NEXT: ret
;
; RV32I-LABEL: fcvt_d_wu:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __floatunsidf@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_d_wu:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sext.w a0, a0
; RV64I-NEXT: call __floatunsidf@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = uitofp i32 %a to double
ret double %1
}
define double @fcvt_d_wu_load(i32* %p) nounwind {
; RV32IFD-LABEL: fcvt_d_wu_load:
; RV32IFD: # %bb.0:
; RV32IFD-NEXT: lw a0, 0(a0)
; RV32IFD-NEXT: fcvt.d.wu fa0, a0
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_d_wu_load:
; RV64IFD: # %bb.0:
; RV64IFD-NEXT: lwu a0, 0(a0)
; RV64IFD-NEXT: fcvt.d.wu fa0, a0
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_d_wu_load:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: lw a0, 0(a0)
; RV32I-NEXT: call __floatunsidf@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_d_wu_load:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: lw a0, 0(a0)
; RV64I-NEXT: call __floatunsidf@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%a = load i32, i32* %p
%1 = uitofp i32 %a to double
ret double %1
}
define i64 @fcvt_l_d(double %a) nounwind {
; RV32IFD-LABEL: fcvt_l_d:
; RV32IFD: # %bb.0:
; RV32IFD-NEXT: addi sp, sp, -16
; RV32IFD-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IFD-NEXT: call __fixdfdi@plt
; RV32IFD-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IFD-NEXT: addi sp, sp, 16
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_l_d:
; RV64IFD: # %bb.0:
; RV64IFD-NEXT: fcvt.l.d a0, fa0, rtz
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_l_d:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __fixdfdi@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_l_d:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __fixdfdi@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptosi double %a to i64
ret i64 %1
}
define i64 @fcvt_l_d_sat(double %a) nounwind {
; RV32IFD-LABEL: fcvt_l_d_sat:
; RV32IFD: # %bb.0: # %start
; RV32IFD-NEXT: addi sp, sp, -16
; RV32IFD-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IFD-NEXT: sw s0, 8(sp) # 4-byte Folded Spill
; RV32IFD-NEXT: fsd fs0, 0(sp) # 8-byte Folded Spill
; RV32IFD-NEXT: lui a0, %hi(.LCPI12_0)
; RV32IFD-NEXT: fld ft0, %lo(.LCPI12_0)(a0)
; RV32IFD-NEXT: fmv.d fs0, fa0
; RV32IFD-NEXT: fle.d s0, ft0, fa0
; RV32IFD-NEXT: call __fixdfdi@plt
; RV32IFD-NEXT: lui a3, 524288
; RV32IFD-NEXT: bnez s0, .LBB12_2
; RV32IFD-NEXT: # %bb.1: # %start
; RV32IFD-NEXT: lui a1, 524288
; RV32IFD-NEXT: .LBB12_2: # %start
; RV32IFD-NEXT: lui a2, %hi(.LCPI12_1)
; RV32IFD-NEXT: fld ft0, %lo(.LCPI12_1)(a2)
; RV32IFD-NEXT: flt.d a2, ft0, fs0
; RV32IFD-NEXT: beqz a2, .LBB12_4
; RV32IFD-NEXT: # %bb.3:
; RV32IFD-NEXT: addi a1, a3, -1
; RV32IFD-NEXT: .LBB12_4: # %start
; RV32IFD-NEXT: feq.d a3, fs0, fs0
; RV32IFD-NEXT: seqz a3, a3
; RV32IFD-NEXT: addi a3, a3, -1
; RV32IFD-NEXT: and a1, a3, a1
; RV32IFD-NEXT: neg a2, a2
; RV32IFD-NEXT: neg a4, s0
; RV32IFD-NEXT: and a0, a4, a0
; RV32IFD-NEXT: or a0, a2, a0
; RV32IFD-NEXT: and a0, a3, a0
; RV32IFD-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IFD-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; RV32IFD-NEXT: fld fs0, 0(sp) # 8-byte Folded Reload
; RV32IFD-NEXT: addi sp, sp, 16
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_l_d_sat:
; RV64IFD: # %bb.0: # %start
; RV64IFD-NEXT: fcvt.l.d a0, fa0, rtz
; RV64IFD-NEXT: feq.d a1, fa0, fa0
; RV64IFD-NEXT: seqz a1, a1
; RV64IFD-NEXT: addi a1, a1, -1
; RV64IFD-NEXT: and a0, a1, a0
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_l_d_sat:
; RV32I: # %bb.0: # %start
; 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: sw s5, 4(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s6, 0(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s0, a1
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: lui s2, 278016
; RV32I-NEXT: addi s2, s2, -1
; RV32I-NEXT: li a2, -1
; RV32I-NEXT: mv a3, s2
; RV32I-NEXT: call __gtdf2@plt
; RV32I-NEXT: mv s4, a0
; RV32I-NEXT: lui a3, 802304
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: call __gedf2@plt
; RV32I-NEXT: mv s6, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: call __fixdfdi@plt
; RV32I-NEXT: mv s3, a0
; RV32I-NEXT: mv s5, a1
; RV32I-NEXT: lui a0, 524288
; RV32I-NEXT: bgez s6, .LBB12_2
; RV32I-NEXT: # %bb.1: # %start
; RV32I-NEXT: lui s5, 524288
; RV32I-NEXT: .LBB12_2: # %start
; RV32I-NEXT: blez s4, .LBB12_4
; RV32I-NEXT: # %bb.3: # %start
; RV32I-NEXT: addi s5, a0, -1
; RV32I-NEXT: .LBB12_4: # %start
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: mv a2, s1
; RV32I-NEXT: mv a3, s0
; RV32I-NEXT: call __unorddf2@plt
; RV32I-NEXT: snez a0, a0
; RV32I-NEXT: addi a0, a0, -1
; RV32I-NEXT: and s4, a0, s5
; RV32I-NEXT: lui a3, 802304
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: call __gedf2@plt
; RV32I-NEXT: slti a0, a0, 0
; RV32I-NEXT: addi a0, a0, -1
; RV32I-NEXT: and s3, a0, s3
; RV32I-NEXT: li a2, -1
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: mv a3, s2
; RV32I-NEXT: call __gtdf2@plt
; RV32I-NEXT: sgtz a0, a0
; RV32I-NEXT: neg a0, a0
; RV32I-NEXT: or s2, a0, s3
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: mv a2, s1
; RV32I-NEXT: mv a3, s0
; RV32I-NEXT: call __unorddf2@plt
; RV32I-NEXT: snez a0, a0
; RV32I-NEXT: addi a0, a0, -1
; RV32I-NEXT: and a0, a0, s2
; RV32I-NEXT: mv a1, s4
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s5, 4(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s6, 0(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_l_d_sat:
; RV64I: # %bb.0: # %start
; 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 s0, a0
; RV64I-NEXT: li a1, -481
; RV64I-NEXT: slli a1, a1, 53
; RV64I-NEXT: call __gedf2@plt
; RV64I-NEXT: mv s2, a0
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: call __fixdfdi@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: li s3, -1
; RV64I-NEXT: bgez s2, .LBB12_2
; RV64I-NEXT: # %bb.1: # %start
; RV64I-NEXT: slli s1, s3, 63
; RV64I-NEXT: .LBB12_2: # %start
; RV64I-NEXT: li a0, 543
; RV64I-NEXT: slli a0, a0, 53
; RV64I-NEXT: addi a1, a0, -1
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: call __gtdf2@plt
; RV64I-NEXT: blez a0, .LBB12_4
; RV64I-NEXT: # %bb.3: # %start
; RV64I-NEXT: srli s1, s3, 1
; RV64I-NEXT: .LBB12_4: # %start
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: mv a1, s0
; RV64I-NEXT: call __unorddf2@plt
; RV64I-NEXT: snez a0, a0
; RV64I-NEXT: addi a0, a0, -1
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
start:
%0 = tail call i64 @llvm.fptosi.sat.i64.f64(double %a)
ret i64 %0
}
declare i64 @llvm.fptosi.sat.i64.f64(double)
define i64 @fcvt_lu_d(double %a) nounwind {
; RV32IFD-LABEL: fcvt_lu_d:
; RV32IFD: # %bb.0:
; RV32IFD-NEXT: addi sp, sp, -16
; RV32IFD-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IFD-NEXT: call __fixunsdfdi@plt
; RV32IFD-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IFD-NEXT: addi sp, sp, 16
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_lu_d:
; RV64IFD: # %bb.0:
; RV64IFD-NEXT: fcvt.lu.d a0, fa0, rtz
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_lu_d:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __fixunsdfdi@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_lu_d:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __fixunsdfdi@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptoui double %a to i64
ret i64 %1
}
define i64 @fcvt_lu_d_sat(double %a) nounwind {
; RV32IFD-LABEL: fcvt_lu_d_sat:
; RV32IFD: # %bb.0: # %start
; RV32IFD-NEXT: addi sp, sp, -16
; RV32IFD-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IFD-NEXT: sw s0, 8(sp) # 4-byte Folded Spill
; RV32IFD-NEXT: fsd fs0, 0(sp) # 8-byte Folded Spill
; RV32IFD-NEXT: fmv.d fs0, fa0
; RV32IFD-NEXT: fcvt.d.w ft0, zero
; RV32IFD-NEXT: fle.d a0, ft0, fa0
; RV32IFD-NEXT: neg s0, a0
; RV32IFD-NEXT: call __fixunsdfdi@plt
; RV32IFD-NEXT: lui a2, %hi(.LCPI14_0)
; RV32IFD-NEXT: fld ft0, %lo(.LCPI14_0)(a2)
; RV32IFD-NEXT: and a0, s0, a0
; RV32IFD-NEXT: flt.d a2, ft0, fs0
; RV32IFD-NEXT: neg a2, a2
; RV32IFD-NEXT: or a0, a2, a0
; RV32IFD-NEXT: and a1, s0, a1
; RV32IFD-NEXT: or a1, a2, a1
; RV32IFD-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IFD-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; RV32IFD-NEXT: fld fs0, 0(sp) # 8-byte Folded Reload
; RV32IFD-NEXT: addi sp, sp, 16
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_lu_d_sat:
; RV64IFD: # %bb.0: # %start
; RV64IFD-NEXT: fcvt.lu.d a0, fa0, rtz
; RV64IFD-NEXT: feq.d a1, fa0, fa0
; RV64IFD-NEXT: seqz a1, a1
; RV64IFD-NEXT: addi a1, a1, -1
; RV64IFD-NEXT: and a0, a1, a0
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_lu_d_sat:
; RV32I: # %bb.0: # %start
; 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: sw s5, 4(sp) # 4-byte Folded Spill
; RV32I-NEXT: mv s0, a1
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: lui s2, 278272
; RV32I-NEXT: addi s2, s2, -1
; RV32I-NEXT: li a2, -1
; RV32I-NEXT: mv a3, s2
; RV32I-NEXT: call __gtdf2@plt
; RV32I-NEXT: sgtz a0, a0
; RV32I-NEXT: neg s4, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: li a3, 0
; RV32I-NEXT: call __gedf2@plt
; RV32I-NEXT: slti a0, a0, 0
; RV32I-NEXT: addi s5, a0, -1
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: call __fixunsdfdi@plt
; RV32I-NEXT: mv s3, a1
; RV32I-NEXT: and a0, s5, a0
; RV32I-NEXT: or s4, s4, a0
; RV32I-NEXT: li a2, -1
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: mv a3, s2
; RV32I-NEXT: call __gtdf2@plt
; RV32I-NEXT: sgtz a0, a0
; RV32I-NEXT: neg s2, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: li a3, 0
; RV32I-NEXT: call __gedf2@plt
; RV32I-NEXT: slti a0, a0, 0
; RV32I-NEXT: addi a0, a0, -1
; RV32I-NEXT: and a0, a0, s3
; RV32I-NEXT: or a1, s2, a0
; RV32I-NEXT: mv a0, s4
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s5, 4(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_lu_d_sat:
; RV64I: # %bb.0: # %start
; 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: mv s0, a0
; RV64I-NEXT: li a1, 0
; RV64I-NEXT: call __gedf2@plt
; RV64I-NEXT: slti a0, a0, 0
; RV64I-NEXT: addi s1, a0, -1
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: call __fixunsdfdi@plt
; RV64I-NEXT: and s1, s1, a0
; RV64I-NEXT: li a0, 1087
; RV64I-NEXT: slli a0, a0, 52
; RV64I-NEXT: addi a1, a0, -1
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: call __gtdf2@plt
; RV64I-NEXT: sgtz a0, a0
; RV64I-NEXT: neg a0, a0
; RV64I-NEXT: or a0, a0, s1
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
start:
%0 = tail call i64 @llvm.fptoui.sat.i64.f64(double %a)
ret i64 %0
}
declare i64 @llvm.fptoui.sat.i64.f64(double)
define i64 @fmv_x_d(double %a, double %b) nounwind {
; RV32IFD-LABEL: fmv_x_d:
; RV32IFD: # %bb.0:
; RV32IFD-NEXT: addi sp, sp, -16
; RV32IFD-NEXT: fadd.d ft0, fa0, fa1
; RV32IFD-NEXT: fsd ft0, 8(sp)
; RV32IFD-NEXT: lw a0, 8(sp)
; RV32IFD-NEXT: lw a1, 12(sp)
; RV32IFD-NEXT: addi sp, sp, 16
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fmv_x_d:
; RV64IFD: # %bb.0:
; RV64IFD-NEXT: fadd.d ft0, fa0, fa1
; RV64IFD-NEXT: fmv.x.d a0, ft0
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fmv_x_d:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __adddf3@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fmv_x_d:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __adddf3@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fadd double %a, %b
%2 = bitcast double %1 to i64
ret i64 %2
}
define double @fcvt_d_l(i64 %a) nounwind {
; RV32IFD-LABEL: fcvt_d_l:
; RV32IFD: # %bb.0:
; RV32IFD-NEXT: addi sp, sp, -16
; RV32IFD-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IFD-NEXT: call __floatdidf@plt
; RV32IFD-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IFD-NEXT: addi sp, sp, 16
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_d_l:
; RV64IFD: # %bb.0:
; RV64IFD-NEXT: fcvt.d.l fa0, a0
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_d_l:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __floatdidf@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_d_l:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __floatdidf@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = sitofp i64 %a to double
ret double %1
}
define double @fcvt_d_lu(i64 %a) nounwind {
; RV32IFD-LABEL: fcvt_d_lu:
; RV32IFD: # %bb.0:
; RV32IFD-NEXT: addi sp, sp, -16
; RV32IFD-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IFD-NEXT: call __floatundidf@plt
; RV32IFD-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IFD-NEXT: addi sp, sp, 16
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_d_lu:
; RV64IFD: # %bb.0:
; RV64IFD-NEXT: fcvt.d.lu fa0, a0
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_d_lu:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __floatundidf@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_d_lu:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __floatundidf@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = uitofp i64 %a to double
ret double %1
}
define double @fmv_d_x(i64 %a, i64 %b) nounwind {
; Ensure fmv.w.x is generated even for a soft double calling convention
; RV32IFD-LABEL: fmv_d_x:
; RV32IFD: # %bb.0:
; RV32IFD-NEXT: addi sp, sp, -16
; RV32IFD-NEXT: sw a3, 4(sp)
; RV32IFD-NEXT: sw a2, 0(sp)
; RV32IFD-NEXT: sw a1, 12(sp)
; RV32IFD-NEXT: sw a0, 8(sp)
; RV32IFD-NEXT: fld ft0, 0(sp)
; RV32IFD-NEXT: fld ft1, 8(sp)
; RV32IFD-NEXT: fadd.d fa0, ft1, ft0
; RV32IFD-NEXT: addi sp, sp, 16
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fmv_d_x:
; RV64IFD: # %bb.0:
; RV64IFD-NEXT: fmv.d.x ft0, a0
; RV64IFD-NEXT: fmv.d.x ft1, a1
; RV64IFD-NEXT: fadd.d fa0, ft0, ft1
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fmv_d_x:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __adddf3@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fmv_d_x:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __adddf3@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = bitcast i64 %a to double
%2 = bitcast i64 %b to double
%3 = fadd double %1, %2
ret double %3
}
define double @fcvt_d_w_i8(i8 signext %a) nounwind {
; CHECKIFD-LABEL: fcvt_d_w_i8:
; CHECKIFD: # %bb.0:
; CHECKIFD-NEXT: fcvt.d.w fa0, a0
; CHECKIFD-NEXT: ret
;
; RV32I-LABEL: fcvt_d_w_i8:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __floatsidf@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_d_w_i8:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __floatsidf@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = sitofp i8 %a to double
ret double %1
}
define double @fcvt_d_wu_i8(i8 zeroext %a) nounwind {
; CHECKIFD-LABEL: fcvt_d_wu_i8:
; CHECKIFD: # %bb.0:
; CHECKIFD-NEXT: fcvt.d.wu fa0, a0
; CHECKIFD-NEXT: ret
;
; RV32I-LABEL: fcvt_d_wu_i8:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __floatunsidf@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_d_wu_i8:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __floatunsidf@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = uitofp i8 %a to double
ret double %1
}
define double @fcvt_d_w_i16(i16 signext %a) nounwind {
; CHECKIFD-LABEL: fcvt_d_w_i16:
; CHECKIFD: # %bb.0:
; CHECKIFD-NEXT: fcvt.d.w fa0, a0
; CHECKIFD-NEXT: ret
;
; RV32I-LABEL: fcvt_d_w_i16:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __floatsidf@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_d_w_i16:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __floatsidf@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = sitofp i16 %a to double
ret double %1
}
define double @fcvt_d_wu_i16(i16 zeroext %a) nounwind {
; CHECKIFD-LABEL: fcvt_d_wu_i16:
; CHECKIFD: # %bb.0:
; CHECKIFD-NEXT: fcvt.d.wu fa0, a0
; CHECKIFD-NEXT: ret
;
; RV32I-LABEL: fcvt_d_wu_i16:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __floatunsidf@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_d_wu_i16:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __floatunsidf@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = uitofp i16 %a to double
ret double %1
}
; Make sure we select W version of addi on RV64.
define signext i32 @fcvt_d_w_demanded_bits(i32 signext %0, double* %1) nounwind {
; RV32IFD-LABEL: fcvt_d_w_demanded_bits:
; RV32IFD: # %bb.0:
; RV32IFD-NEXT: addi a0, a0, 1
; RV32IFD-NEXT: fcvt.d.w ft0, a0
; RV32IFD-NEXT: fsd ft0, 0(a1)
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_d_w_demanded_bits:
; RV64IFD: # %bb.0:
; RV64IFD-NEXT: addiw a0, a0, 1
; RV64IFD-NEXT: fcvt.d.w ft0, a0
; RV64IFD-NEXT: fsd ft0, 0(a1)
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_d_w_demanded_bits:
; 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: mv s0, a1
; RV32I-NEXT: addi s1, a0, 1
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: call __floatsidf@plt
; RV32I-NEXT: sw a1, 4(s0)
; RV32I-NEXT: sw a0, 0(s0)
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 4(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_d_w_demanded_bits:
; 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: mv s0, a1
; RV64I-NEXT: addiw s1, a0, 1
; RV64I-NEXT: mv a0, s1
; RV64I-NEXT: call __floatsidf@plt
; RV64I-NEXT: sd a0, 0(s0)
; RV64I-NEXT: mv a0, s1
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
%3 = add i32 %0, 1
%4 = sitofp i32 %3 to double
store double %4, double* %1, align 8
ret i32 %3
}
; Make sure we select W version of addi on RV64.
define signext i32 @fcvt_d_wu_demanded_bits(i32 signext %0, double* %1) nounwind {
; RV32IFD-LABEL: fcvt_d_wu_demanded_bits:
; RV32IFD: # %bb.0:
; RV32IFD-NEXT: addi a0, a0, 1
; RV32IFD-NEXT: fcvt.d.wu ft0, a0
; RV32IFD-NEXT: fsd ft0, 0(a1)
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_d_wu_demanded_bits:
; RV64IFD: # %bb.0:
; RV64IFD-NEXT: addiw a0, a0, 1
; RV64IFD-NEXT: fcvt.d.wu ft0, a0
; RV64IFD-NEXT: fsd ft0, 0(a1)
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_d_wu_demanded_bits:
; 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: mv s0, a1
; RV32I-NEXT: addi s1, a0, 1
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: call __floatunsidf@plt
; RV32I-NEXT: sw a1, 4(s0)
; RV32I-NEXT: sw a0, 0(s0)
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 4(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_d_wu_demanded_bits:
; 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: mv s0, a1
; RV64I-NEXT: addiw s1, a0, 1
; RV64I-NEXT: mv a0, s1
; RV64I-NEXT: call __floatunsidf@plt
; RV64I-NEXT: sd a0, 0(s0)
; RV64I-NEXT: mv a0, s1
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
%3 = add i32 %0, 1
%4 = uitofp i32 %3 to double
store double %4, double* %1, align 8
ret i32 %3
}
define signext i16 @fcvt_w_s_i16(double %a) nounwind {
; RV32IFD-LABEL: fcvt_w_s_i16:
; RV32IFD: # %bb.0:
; RV32IFD-NEXT: fcvt.w.d a0, fa0, rtz
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_w_s_i16:
; RV64IFD: # %bb.0:
; RV64IFD-NEXT: fcvt.l.d a0, fa0, rtz
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_w_s_i16:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __fixdfsi@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_w_s_i16:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __fixdfdi@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptosi double %a to i16
ret i16 %1
}
define signext i16 @fcvt_w_s_sat_i16(double %a) nounwind {
; RV32IFD-LABEL: fcvt_w_s_sat_i16:
; RV32IFD: # %bb.0: # %start
; RV32IFD-NEXT: lui a0, %hi(.LCPI26_0)
; RV32IFD-NEXT: fld ft0, %lo(.LCPI26_0)(a0)
; RV32IFD-NEXT: lui a0, %hi(.LCPI26_1)
; RV32IFD-NEXT: fld ft1, %lo(.LCPI26_1)(a0)
; RV32IFD-NEXT: fmax.d ft0, fa0, ft0
; RV32IFD-NEXT: fmin.d ft0, ft0, ft1
; RV32IFD-NEXT: fcvt.w.d a0, ft0, rtz
; RV32IFD-NEXT: feq.d a1, fa0, fa0
; RV32IFD-NEXT: seqz a1, a1
; RV32IFD-NEXT: addi a1, a1, -1
; RV32IFD-NEXT: and a0, a1, a0
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_w_s_sat_i16:
; RV64IFD: # %bb.0: # %start
; RV64IFD-NEXT: lui a0, %hi(.LCPI26_0)
; RV64IFD-NEXT: fld ft0, %lo(.LCPI26_0)(a0)
; RV64IFD-NEXT: lui a0, %hi(.LCPI26_1)
; RV64IFD-NEXT: fld ft1, %lo(.LCPI26_1)(a0)
; RV64IFD-NEXT: fmax.d ft0, fa0, ft0
; RV64IFD-NEXT: fmin.d ft0, ft0, ft1
; RV64IFD-NEXT: fcvt.l.d a0, ft0, rtz
; RV64IFD-NEXT: feq.d a1, fa0, fa0
; RV64IFD-NEXT: seqz a1, a1
; RV64IFD-NEXT: addi a1, a1, -1
; RV64IFD-NEXT: and a0, a1, a0
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_w_s_sat_i16:
; RV32I: # %bb.0: # %start
; 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 s0, a1
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: lui a0, 265728
; RV32I-NEXT: addi a3, a0, -64
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: call __gtdf2@plt
; RV32I-NEXT: mv s2, a0
; RV32I-NEXT: lui a3, 790016
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: call __gedf2@plt
; RV32I-NEXT: mv s4, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: call __fixdfsi@plt
; RV32I-NEXT: mv s3, a0
; RV32I-NEXT: bgez s4, .LBB26_2
; RV32I-NEXT: # %bb.1: # %start
; RV32I-NEXT: lui s3, 1048568
; RV32I-NEXT: .LBB26_2: # %start
; RV32I-NEXT: blez s2, .LBB26_4
; RV32I-NEXT: # %bb.3: # %start
; RV32I-NEXT: lui s3, 8
; RV32I-NEXT: addi s3, s3, -1
; RV32I-NEXT: .LBB26_4: # %start
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: mv a2, s1
; RV32I-NEXT: mv a3, s0
; RV32I-NEXT: call __unorddf2@plt
; RV32I-NEXT: snez a0, a0
; RV32I-NEXT: addi a0, a0, -1
; RV32I-NEXT: and a0, a0, s3
; RV32I-NEXT: slli a0, a0, 16
; RV32I-NEXT: srai a0, a0, 16
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_w_s_sat_i16:
; RV64I: # %bb.0: # %start
; 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 s0, a0
; RV64I-NEXT: li a1, -505
; RV64I-NEXT: slli a1, a1, 53
; RV64I-NEXT: call __gedf2@plt
; RV64I-NEXT: mv s2, a0
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: call __fixdfdi@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: bgez s2, .LBB26_2
; RV64I-NEXT: # %bb.1: # %start
; RV64I-NEXT: lui s1, 1048568
; RV64I-NEXT: .LBB26_2: # %start
; RV64I-NEXT: lui a0, 4152
; RV64I-NEXT: addiw a0, a0, -1
; RV64I-NEXT: slli a1, a0, 38
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: call __gtdf2@plt
; RV64I-NEXT: blez a0, .LBB26_4
; RV64I-NEXT: # %bb.3: # %start
; RV64I-NEXT: lui s1, 8
; RV64I-NEXT: addiw s1, s1, -1
; RV64I-NEXT: .LBB26_4: # %start
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: mv a1, s0
; RV64I-NEXT: call __unorddf2@plt
; RV64I-NEXT: snez a0, a0
; RV64I-NEXT: addi a0, a0, -1
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: slli a0, a0, 48
; RV64I-NEXT: srai a0, a0, 48
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
start:
%0 = tail call i16 @llvm.fptosi.sat.i16.f64(double %a)
ret i16 %0
}
declare i16 @llvm.fptosi.sat.i16.f64(double)
define zeroext i16 @fcvt_wu_s_i16(double %a) nounwind {
; RV32IFD-LABEL: fcvt_wu_s_i16:
; RV32IFD: # %bb.0:
; RV32IFD-NEXT: fcvt.wu.d a0, fa0, rtz
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_wu_s_i16:
; RV64IFD: # %bb.0:
; RV64IFD-NEXT: fcvt.lu.d a0, fa0, rtz
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_wu_s_i16:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __fixunsdfsi@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_wu_s_i16:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __fixunsdfdi@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptoui double %a to i16
ret i16 %1
}
define zeroext i16 @fcvt_wu_s_sat_i16(double %a) nounwind {
; RV32IFD-LABEL: fcvt_wu_s_sat_i16:
; RV32IFD: # %bb.0: # %start
; RV32IFD-NEXT: lui a0, %hi(.LCPI28_0)
; RV32IFD-NEXT: fld ft0, %lo(.LCPI28_0)(a0)
; RV32IFD-NEXT: fcvt.d.w ft1, zero
; RV32IFD-NEXT: fmax.d ft1, fa0, ft1
; RV32IFD-NEXT: fmin.d ft0, ft1, ft0
; RV32IFD-NEXT: fcvt.wu.d a0, ft0, rtz
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_wu_s_sat_i16:
; RV64IFD: # %bb.0: # %start
; RV64IFD-NEXT: lui a0, %hi(.LCPI28_0)
; RV64IFD-NEXT: fld ft0, %lo(.LCPI28_0)(a0)
; RV64IFD-NEXT: fmv.d.x ft1, zero
; RV64IFD-NEXT: fmax.d ft1, fa0, ft1
; RV64IFD-NEXT: fmin.d ft0, ft1, ft0
; RV64IFD-NEXT: fcvt.lu.d a0, ft0, rtz
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_wu_s_sat_i16:
; RV32I: # %bb.0: # %start
; 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 s1, a1
; RV32I-NEXT: mv s2, a0
; RV32I-NEXT: lui a3, 265984
; RV32I-NEXT: addi a3, a3, -32
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: call __gtdf2@plt
; RV32I-NEXT: mv s3, a0
; RV32I-NEXT: mv a0, s2
; RV32I-NEXT: mv a1, s1
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: li a3, 0
; RV32I-NEXT: call __gedf2@plt
; RV32I-NEXT: mv s0, a0
; RV32I-NEXT: mv a0, s2
; RV32I-NEXT: mv a1, s1
; RV32I-NEXT: call __fixunsdfsi@plt
; RV32I-NEXT: lui a1, 16
; RV32I-NEXT: addi a1, a1, -1
; RV32I-NEXT: blez s3, .LBB28_2
; RV32I-NEXT: # %bb.1: # %start
; RV32I-NEXT: mv a0, a1
; RV32I-NEXT: j .LBB28_3
; RV32I-NEXT: .LBB28_2:
; RV32I-NEXT: slti a2, s0, 0
; RV32I-NEXT: addi a2, a2, -1
; RV32I-NEXT: and a0, a2, a0
; RV32I-NEXT: .LBB28_3: # %start
; RV32I-NEXT: and a0, a0, a1
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_wu_s_sat_i16:
; RV64I: # %bb.0: # %start
; 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, a0
; RV64I-NEXT: li a1, 0
; RV64I-NEXT: call __gedf2@plt
; RV64I-NEXT: mv s0, a0
; RV64I-NEXT: mv a0, s2
; RV64I-NEXT: call __fixunsdfdi@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: lui a0, 8312
; RV64I-NEXT: addiw a0, a0, -1
; RV64I-NEXT: slli a1, a0, 37
; RV64I-NEXT: mv a0, s2
; RV64I-NEXT: call __gtdf2@plt
; RV64I-NEXT: lui a1, 16
; RV64I-NEXT: addiw a1, a1, -1
; RV64I-NEXT: blez a0, .LBB28_2
; RV64I-NEXT: # %bb.1: # %start
; RV64I-NEXT: mv a0, a1
; RV64I-NEXT: j .LBB28_3
; RV64I-NEXT: .LBB28_2:
; RV64I-NEXT: slti a0, s0, 0
; RV64I-NEXT: addi a0, a0, -1
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: .LBB28_3: # %start
; RV64I-NEXT: and a0, a0, a1
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
start:
%0 = tail call i16 @llvm.fptoui.sat.i16.f64(double %a)
ret i16 %0
}
declare i16 @llvm.fptoui.sat.i16.f64(double)
define signext i8 @fcvt_w_s_i8(double %a) nounwind {
; RV32IFD-LABEL: fcvt_w_s_i8:
; RV32IFD: # %bb.0:
; RV32IFD-NEXT: fcvt.w.d a0, fa0, rtz
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_w_s_i8:
; RV64IFD: # %bb.0:
; RV64IFD-NEXT: fcvt.l.d a0, fa0, rtz
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_w_s_i8:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __fixdfsi@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_w_s_i8:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __fixdfdi@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptosi double %a to i8
ret i8 %1
}
define signext i8 @fcvt_w_s_sat_i8(double %a) nounwind {
; RV32IFD-LABEL: fcvt_w_s_sat_i8:
; RV32IFD: # %bb.0: # %start
; RV32IFD-NEXT: lui a0, %hi(.LCPI30_0)
; RV32IFD-NEXT: fld ft0, %lo(.LCPI30_0)(a0)
; RV32IFD-NEXT: lui a0, %hi(.LCPI30_1)
; RV32IFD-NEXT: fld ft1, %lo(.LCPI30_1)(a0)
; RV32IFD-NEXT: fmax.d ft0, fa0, ft0
; RV32IFD-NEXT: fmin.d ft0, ft0, ft1
; RV32IFD-NEXT: fcvt.w.d a0, ft0, rtz
; RV32IFD-NEXT: feq.d a1, fa0, fa0
; RV32IFD-NEXT: seqz a1, a1
; RV32IFD-NEXT: addi a1, a1, -1
; RV32IFD-NEXT: and a0, a1, a0
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_w_s_sat_i8:
; RV64IFD: # %bb.0: # %start
; RV64IFD-NEXT: lui a0, %hi(.LCPI30_0)
; RV64IFD-NEXT: fld ft0, %lo(.LCPI30_0)(a0)
; RV64IFD-NEXT: lui a0, %hi(.LCPI30_1)
; RV64IFD-NEXT: fld ft1, %lo(.LCPI30_1)(a0)
; RV64IFD-NEXT: fmax.d ft0, fa0, ft0
; RV64IFD-NEXT: fmin.d ft0, ft0, ft1
; RV64IFD-NEXT: fcvt.l.d a0, ft0, rtz
; RV64IFD-NEXT: feq.d a1, fa0, fa0
; RV64IFD-NEXT: seqz a1, a1
; RV64IFD-NEXT: addi a1, a1, -1
; RV64IFD-NEXT: and a0, a1, a0
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_w_s_sat_i8:
; RV32I: # %bb.0: # %start
; 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 s0, a1
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: lui a3, 263676
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: call __gtdf2@plt
; RV32I-NEXT: mv s2, a0
; RV32I-NEXT: lui a3, 787968
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: call __gedf2@plt
; RV32I-NEXT: mv s4, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: call __fixdfsi@plt
; RV32I-NEXT: mv s3, a0
; RV32I-NEXT: bgez s4, .LBB30_2
; RV32I-NEXT: # %bb.1: # %start
; RV32I-NEXT: li s3, -128
; RV32I-NEXT: .LBB30_2: # %start
; RV32I-NEXT: blez s2, .LBB30_4
; RV32I-NEXT: # %bb.3: # %start
; RV32I-NEXT: li s3, 127
; RV32I-NEXT: .LBB30_4: # %start
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: mv a2, s1
; RV32I-NEXT: mv a3, s0
; RV32I-NEXT: call __unorddf2@plt
; RV32I-NEXT: snez a0, a0
; RV32I-NEXT: addi a0, a0, -1
; RV32I-NEXT: and a0, a0, s3
; RV32I-NEXT: slli a0, a0, 24
; RV32I-NEXT: srai a0, a0, 24
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_w_s_sat_i8:
; RV64I: # %bb.0: # %start
; 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 s0, a0
; RV64I-NEXT: li a1, -509
; RV64I-NEXT: slli a1, a1, 53
; RV64I-NEXT: call __gedf2@plt
; RV64I-NEXT: mv s2, a0
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: call __fixdfdi@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: bgez s2, .LBB30_2
; RV64I-NEXT: # %bb.1: # %start
; RV64I-NEXT: li s1, -128
; RV64I-NEXT: .LBB30_2: # %start
; RV64I-NEXT: lui a1, 65919
; RV64I-NEXT: slli a1, a1, 34
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: call __gtdf2@plt
; RV64I-NEXT: blez a0, .LBB30_4
; RV64I-NEXT: # %bb.3: # %start
; RV64I-NEXT: li s1, 127
; RV64I-NEXT: .LBB30_4: # %start
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: mv a1, s0
; RV64I-NEXT: call __unorddf2@plt
; RV64I-NEXT: snez a0, a0
; RV64I-NEXT: addi a0, a0, -1
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: slli a0, a0, 56
; RV64I-NEXT: srai a0, a0, 56
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
start:
%0 = tail call i8 @llvm.fptosi.sat.i8.f64(double %a)
ret i8 %0
}
declare i8 @llvm.fptosi.sat.i8.f64(double)
define zeroext i8 @fcvt_wu_s_i8(double %a) nounwind {
;
;
; RV32IFD-LABEL: fcvt_wu_s_i8:
; RV32IFD: # %bb.0:
; RV32IFD-NEXT: fcvt.wu.d a0, fa0, rtz
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_wu_s_i8:
; RV64IFD: # %bb.0:
; RV64IFD-NEXT: fcvt.lu.d a0, fa0, rtz
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_wu_s_i8:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __fixunsdfsi@plt
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_wu_s_i8:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __fixunsdfdi@plt
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptoui double %a to i8
ret i8 %1
}
define zeroext i8 @fcvt_wu_s_sat_i8(double %a) nounwind {
;
;
; RV32IFD-LABEL: fcvt_wu_s_sat_i8:
; RV32IFD: # %bb.0: # %start
; RV32IFD-NEXT: lui a0, %hi(.LCPI32_0)
; RV32IFD-NEXT: fld ft0, %lo(.LCPI32_0)(a0)
; RV32IFD-NEXT: fcvt.d.w ft1, zero
; RV32IFD-NEXT: fmax.d ft1, fa0, ft1
; RV32IFD-NEXT: fmin.d ft0, ft1, ft0
; RV32IFD-NEXT: fcvt.wu.d a0, ft0, rtz
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_wu_s_sat_i8:
; RV64IFD: # %bb.0: # %start
; RV64IFD-NEXT: lui a0, %hi(.LCPI32_0)
; RV64IFD-NEXT: fld ft0, %lo(.LCPI32_0)(a0)
; RV64IFD-NEXT: fmv.d.x ft1, zero
; RV64IFD-NEXT: fmax.d ft1, fa0, ft1
; RV64IFD-NEXT: fmin.d ft0, ft1, ft0
; RV64IFD-NEXT: fcvt.lu.d a0, ft0, rtz
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_wu_s_sat_i8:
; RV32I: # %bb.0: # %start
; 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 s1, a1
; RV32I-NEXT: mv s2, a0
; RV32I-NEXT: lui a3, 263934
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: call __gtdf2@plt
; RV32I-NEXT: mv s3, a0
; RV32I-NEXT: mv a0, s2
; RV32I-NEXT: mv a1, s1
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: li a3, 0
; RV32I-NEXT: call __gedf2@plt
; RV32I-NEXT: mv s0, a0
; RV32I-NEXT: mv a0, s2
; RV32I-NEXT: mv a1, s1
; RV32I-NEXT: call __fixunsdfsi@plt
; RV32I-NEXT: blez s3, .LBB32_2
; RV32I-NEXT: # %bb.1: # %start
; RV32I-NEXT: li a0, 255
; RV32I-NEXT: j .LBB32_3
; RV32I-NEXT: .LBB32_2:
; RV32I-NEXT: slti a1, s0, 0
; RV32I-NEXT: addi a1, a1, -1
; RV32I-NEXT: and a0, a1, a0
; RV32I-NEXT: .LBB32_3: # %start
; RV32I-NEXT: andi a0, a0, 255
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_wu_s_sat_i8:
; RV64I: # %bb.0: # %start
; 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, a0
; RV64I-NEXT: li a1, 0
; RV64I-NEXT: call __gedf2@plt
; RV64I-NEXT: mv s0, a0
; RV64I-NEXT: mv a0, s2
; RV64I-NEXT: call __fixunsdfdi@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: lui a1, 131967
; RV64I-NEXT: slli a1, a1, 33
; RV64I-NEXT: mv a0, s2
; RV64I-NEXT: call __gtdf2@plt
; RV64I-NEXT: blez a0, .LBB32_2
; RV64I-NEXT: # %bb.1: # %start
; RV64I-NEXT: li a0, 255
; RV64I-NEXT: j .LBB32_3
; RV64I-NEXT: .LBB32_2:
; RV64I-NEXT: slti a0, s0, 0
; RV64I-NEXT: addi a0, a0, -1
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: .LBB32_3: # %start
; RV64I-NEXT: andi a0, a0, 255
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
start:
%0 = tail call i8 @llvm.fptoui.sat.i8.f64(double %a)
ret i8 %0
}
declare i8 @llvm.fptoui.sat.i8.f64(double)
define zeroext i32 @fcvt_wu_d_sat_zext(double %a) nounwind {
; RV32IFD-LABEL: fcvt_wu_d_sat_zext:
; RV32IFD: # %bb.0: # %start
; RV32IFD-NEXT: fcvt.wu.d a0, fa0, rtz
; RV32IFD-NEXT: feq.d a1, fa0, fa0
; RV32IFD-NEXT: seqz a1, a1
; RV32IFD-NEXT: addi a1, a1, -1
; RV32IFD-NEXT: and a0, a1, a0
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: fcvt_wu_d_sat_zext:
; RV64IFD: # %bb.0: # %start
; RV64IFD-NEXT: fcvt.wu.d a0, fa0, rtz
; RV64IFD-NEXT: feq.d a1, fa0, fa0
; RV64IFD-NEXT: seqz a1, a1
; RV64IFD-NEXT: addi a1, a1, -1
; RV64IFD-NEXT: and a0, a0, a1
; RV64IFD-NEXT: slli a0, a0, 32
; RV64IFD-NEXT: srli a0, a0, 32
; RV64IFD-NEXT: ret
;
; RV32I-LABEL: fcvt_wu_d_sat_zext:
; RV32I: # %bb.0: # %start
; 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 s0, a1
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: lui a3, 270080
; RV32I-NEXT: addi a3, a3, -1
; RV32I-NEXT: lui a2, 1048064
; RV32I-NEXT: call __gtdf2@plt
; RV32I-NEXT: sgtz a0, a0
; RV32I-NEXT: neg s2, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: li a3, 0
; RV32I-NEXT: call __gedf2@plt
; RV32I-NEXT: slti a0, a0, 0
; RV32I-NEXT: addi s3, a0, -1
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: call __fixunsdfsi@plt
; RV32I-NEXT: and a0, s3, a0
; RV32I-NEXT: or a0, s2, a0
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_wu_d_sat_zext:
; RV64I: # %bb.0: # %start
; 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, a0
; RV64I-NEXT: li a1, 0
; RV64I-NEXT: call __gedf2@plt
; RV64I-NEXT: mv s0, a0
; RV64I-NEXT: mv a0, s2
; RV64I-NEXT: call __fixunsdfdi@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: li a0, 1055
; RV64I-NEXT: slli a0, a0, 31
; RV64I-NEXT: addi a0, a0, -1
; RV64I-NEXT: slli a1, a0, 21
; RV64I-NEXT: mv a0, s2
; RV64I-NEXT: call __gtdf2@plt
; RV64I-NEXT: blez a0, .LBB33_2
; RV64I-NEXT: # %bb.1: # %start
; RV64I-NEXT: li a0, -1
; RV64I-NEXT: srli a0, a0, 32
; RV64I-NEXT: j .LBB33_3
; RV64I-NEXT: .LBB33_2:
; RV64I-NEXT: slti a0, s0, 0
; RV64I-NEXT: addi a0, a0, -1
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: .LBB33_3: # %start
; RV64I-NEXT: slli a0, a0, 32
; RV64I-NEXT: srli a0, a0, 32
; RV64I-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 0(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 32
; RV64I-NEXT: ret
start:
%0 = tail call i32 @llvm.fptoui.sat.i32.f64(double %a)
ret i32 %0
}
define signext i32 @fcvt_w_d_sat_sext(double %a) nounwind {
; CHECKIFD-LABEL: fcvt_w_d_sat_sext:
; CHECKIFD: # %bb.0: # %start
; CHECKIFD-NEXT: fcvt.w.d a0, fa0, rtz
; CHECKIFD-NEXT: feq.d a1, fa0, fa0
; CHECKIFD-NEXT: seqz a1, a1
; CHECKIFD-NEXT: addi a1, a1, -1
; CHECKIFD-NEXT: and a0, a1, a0
; CHECKIFD-NEXT: ret
;
; RV32I-LABEL: fcvt_w_d_sat_sext:
; RV32I: # %bb.0: # %start
; 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 s0, a1
; RV32I-NEXT: mv s1, a0
; RV32I-NEXT: lui a3, 269824
; RV32I-NEXT: addi a3, a3, -1
; RV32I-NEXT: lui a2, 1047552
; RV32I-NEXT: call __gtdf2@plt
; RV32I-NEXT: mv s2, a0
; RV32I-NEXT: lui a3, 794112
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: li a2, 0
; RV32I-NEXT: call __gedf2@plt
; RV32I-NEXT: mv s4, a0
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: call __fixdfsi@plt
; RV32I-NEXT: mv s3, a0
; RV32I-NEXT: lui a0, 524288
; RV32I-NEXT: bgez s4, .LBB34_2
; RV32I-NEXT: # %bb.1: # %start
; RV32I-NEXT: lui s3, 524288
; RV32I-NEXT: .LBB34_2: # %start
; RV32I-NEXT: blez s2, .LBB34_4
; RV32I-NEXT: # %bb.3: # %start
; RV32I-NEXT: addi s3, a0, -1
; RV32I-NEXT: .LBB34_4: # %start
; RV32I-NEXT: mv a0, s1
; RV32I-NEXT: mv a1, s0
; RV32I-NEXT: mv a2, s1
; RV32I-NEXT: mv a3, s0
; RV32I-NEXT: call __unorddf2@plt
; RV32I-NEXT: snez a0, a0
; RV32I-NEXT: addi a0, a0, -1
; RV32I-NEXT: and a0, a0, s3
; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 32
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_w_d_sat_sext:
; RV64I: # %bb.0: # %start
; 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 s0, a0
; RV64I-NEXT: li a1, -497
; RV64I-NEXT: slli a1, a1, 53
; RV64I-NEXT: call __gedf2@plt
; RV64I-NEXT: mv s2, a0
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: call __fixdfdi@plt
; RV64I-NEXT: mv s1, a0
; RV64I-NEXT: lui s3, 524288
; RV64I-NEXT: bgez s2, .LBB34_2
; RV64I-NEXT: # %bb.1: # %start
; RV64I-NEXT: lui s1, 524288
; RV64I-NEXT: .LBB34_2: # %start
; RV64I-NEXT: li a0, 527
; RV64I-NEXT: slli a0, a0, 31
; RV64I-NEXT: addi a0, a0, -1
; RV64I-NEXT: slli a1, a0, 22
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: call __gtdf2@plt
; RV64I-NEXT: blez a0, .LBB34_4
; RV64I-NEXT: # %bb.3: # %start
; RV64I-NEXT: addiw s1, s3, -1
; RV64I-NEXT: .LBB34_4: # %start
; RV64I-NEXT: mv a0, s0
; RV64I-NEXT: mv a1, s0
; RV64I-NEXT: call __unorddf2@plt
; RV64I-NEXT: snez a0, a0
; RV64I-NEXT: addi a0, a0, -1
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: sext.w a0, a0
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
start:
%0 = tail call i32 @llvm.fptosi.sat.i32.f64(double %a)
ret i32 %0
}
Reference in New Issue View Git Blame Copy Permalink