shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
llvm-project/llvm/test/CodeGen/RISCV/GlobalISel/float-convert.ll
Alex Bradbury fc69f25a8f
[RISCV] Convert LWU to LW if possible in RISCVOptWInstrs (#144703) 
After the refactoring in #149710 the logic change is trivial.

Motivation for preferring sign-extended 32-bit loads (LW) vs
zero-extended (LWU):
* LW is compressible while LWU is not.
* Helps to minimise the diff vs RV32 (e.g. LWU vs LW)
* Helps to minimise distracting diffs vs GCC. I see this come up
frequently when comparing GCC code and in these cases it's a red
herring.

Similar normalisation could be done for LHU and LH, but this is less
well motivated as there is a compressed LHU (and if performing the
change in RISCVOptWInstrs it wouldn't be done for RV32). There is a
compressed LBU but not LB, meaning doing a similar normalisation for
byte-sized loads would actually be a regression in terms of code size.
Load narrowing when allowed by hasAllNBitUsers isn't explored in this
patch.

This changes ~20500 instructions in an RVA22 build of the
llvm-test-suite including SPEC 2017. As part of the review, the option
of doing the change at ISel time was explored but was found to be less
effective.
2025-07-21 11:48:33 +01:00

812 lines
24 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -global-isel -mattr=+f -verify-machineinstrs < %s \
; RUN: -target-abi=ilp32f | FileCheck -check-prefixes=CHECKIF,RV32IF %s
; RUN: llc -mtriple=riscv64 -global-isel -mattr=+f -verify-machineinstrs < %s \
; RUN: -target-abi=lp64f | FileCheck -check-prefixes=CHECKIF,RV64IF %s
; RUN: llc -mtriple=riscv32 -global-isel -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefix=RV32I %s
; RUN: llc -mtriple=riscv64 -global-isel -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefix=RV64I %s
define i32 @fcvt_w_s(float %a) nounwind {
; CHECKIF-LABEL: fcvt_w_s:
; CHECKIF: # %bb.0:
; CHECKIF-NEXT: fcvt.w.s a0, fa0, rtz
; CHECKIF-NEXT: ret
;
; RV32I-LABEL: fcvt_w_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __fixsfsi
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_w_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __fixsfsi
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptosi float %a to i32
ret i32 %1
}
define i32 @fcvt_wu_s(float %a) nounwind {
; CHECKIF-LABEL: fcvt_wu_s:
; CHECKIF: # %bb.0:
; CHECKIF-NEXT: fcvt.wu.s a0, fa0, rtz
; CHECKIF-NEXT: ret
;
; RV32I-LABEL: fcvt_wu_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __fixunssfsi
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_wu_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __fixunssfsi
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptoui float %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_s_multiple_use(float %x, ptr %y) nounwind {
; CHECKIF-LABEL: fcvt_wu_s_multiple_use:
; CHECKIF: # %bb.0:
; CHECKIF-NEXT: fcvt.wu.s a0, fa0, rtz
; CHECKIF-NEXT: bnez a0, .LBB2_2
; CHECKIF-NEXT: # %bb.1:
; CHECKIF-NEXT: li a0, 1
; CHECKIF-NEXT: .LBB2_2:
; CHECKIF-NEXT: ret
;
; RV32I-LABEL: fcvt_wu_s_multiple_use:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __fixunssfsi
; RV32I-NEXT: bnez a0, .LBB2_2
; RV32I-NEXT: # %bb.1:
; RV32I-NEXT: li a0, 1
; RV32I-NEXT: .LBB2_2:
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_wu_s_multiple_use:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __fixunssfsi
; RV64I-NEXT: sext.w a1, a0
; RV64I-NEXT: bnez a1, .LBB2_2
; RV64I-NEXT: # %bb.1:
; RV64I-NEXT: li a0, 1
; RV64I-NEXT: .LBB2_2:
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%a = fptoui float %x to i32
%b = icmp eq i32 %a, 0
%c = select i1 %b, i32 1, i32 %a
ret i32 %c
}
define signext i32 @fmv_x_w(float %a, float %b) nounwind {
; RV32IF-LABEL: fmv_x_w:
; RV32IF: # %bb.0:
; RV32IF-NEXT: fadd.s fa5, fa0, fa1
; RV32IF-NEXT: fmv.x.w a0, fa5
; RV32IF-NEXT: ret
;
; RV64IF-LABEL: fmv_x_w:
; RV64IF: # %bb.0:
; RV64IF-NEXT: fadd.s fa5, fa0, fa1
; RV64IF-NEXT: fmv.x.w a0, fa5
; RV64IF-NEXT: sext.w a0, a0
; RV64IF-NEXT: ret
;
; RV32I-LABEL: fmv_x_w:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __addsf3
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fmv_x_w:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __addsf3
; RV64I-NEXT: sext.w a0, a0
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
; Ensure fmv.x.w is generated even for a soft float calling convention
%1 = fadd float %a, %b
%2 = bitcast float %1 to i32
ret i32 %2
}
define float @fcvt_s_w(i32 %a) nounwind {
; CHECKIF-LABEL: fcvt_s_w:
; CHECKIF: # %bb.0:
; CHECKIF-NEXT: fcvt.s.w fa0, a0
; CHECKIF-NEXT: ret
;
; RV32I-LABEL: fcvt_s_w:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __floatsisf
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_s_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 __floatsisf
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = sitofp i32 %a to float
ret float %1
}
define float @fcvt_s_w_load(ptr %p) nounwind {
; CHECKIF-LABEL: fcvt_s_w_load:
; CHECKIF: # %bb.0:
; CHECKIF-NEXT: lw a0, 0(a0)
; CHECKIF-NEXT: fcvt.s.w fa0, a0
; CHECKIF-NEXT: ret
;
; RV32I-LABEL: fcvt_s_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 __floatsisf
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_s_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 __floatsisf
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%a = load i32, ptr %p
%1 = sitofp i32 %a to float
ret float %1
}
define float @fcvt_s_wu(i32 %a) nounwind {
; CHECKIF-LABEL: fcvt_s_wu:
; CHECKIF: # %bb.0:
; CHECKIF-NEXT: fcvt.s.wu fa0, a0
; CHECKIF-NEXT: ret
;
; RV32I-LABEL: fcvt_s_wu:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __floatunsisf
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_s_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 __floatunsisf
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = uitofp i32 %a to float
ret float %1
}
define float @fcvt_s_wu_load(ptr %p) nounwind {
; CHECKIF-LABEL: fcvt_s_wu_load:
; CHECKIF: # %bb.0:
; CHECKIF-NEXT: lw a0, 0(a0)
; CHECKIF-NEXT: fcvt.s.wu fa0, a0
; CHECKIF-NEXT: ret
;
; RV32I-LABEL: fcvt_s_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 __floatunsisf
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_s_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 __floatunsisf
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%a = load i32, ptr %p
%1 = uitofp i32 %a to float
ret float %1
}
define float @fmv_w_x(i32 %a, i32 %b) nounwind {
; CHECKIF-LABEL: fmv_w_x:
; CHECKIF: # %bb.0:
; CHECKIF-NEXT: fmv.w.x fa5, a0
; CHECKIF-NEXT: fmv.w.x fa4, a1
; CHECKIF-NEXT: fadd.s fa0, fa5, fa4
; CHECKIF-NEXT: ret
;
; RV32I-LABEL: fmv_w_x:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __addsf3
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fmv_w_x:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __addsf3
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
; Ensure fmv.w.x is generated even for a soft float calling convention
%1 = bitcast i32 %a to float
%2 = bitcast i32 %b to float
%3 = fadd float %1, %2
ret float %3
}
define i64 @fcvt_l_s(float %a) nounwind {
; RV32IF-LABEL: fcvt_l_s:
; RV32IF: # %bb.0:
; RV32IF-NEXT: addi sp, sp, -16
; RV32IF-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IF-NEXT: call __fixsfdi
; RV32IF-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IF-NEXT: addi sp, sp, 16
; RV32IF-NEXT: ret
;
; RV64IF-LABEL: fcvt_l_s:
; RV64IF: # %bb.0:
; RV64IF-NEXT: fcvt.l.s a0, fa0, rtz
; RV64IF-NEXT: ret
;
; RV32I-LABEL: fcvt_l_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __fixsfdi
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_l_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __fixsfdi
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptosi float %a to i64
ret i64 %1
}
define i64 @fcvt_lu_s(float %a) nounwind {
; RV32IF-LABEL: fcvt_lu_s:
; RV32IF: # %bb.0:
; RV32IF-NEXT: addi sp, sp, -16
; RV32IF-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IF-NEXT: call __fixunssfdi
; RV32IF-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IF-NEXT: addi sp, sp, 16
; RV32IF-NEXT: ret
;
; RV64IF-LABEL: fcvt_lu_s:
; RV64IF: # %bb.0:
; RV64IF-NEXT: fcvt.lu.s a0, fa0, rtz
; RV64IF-NEXT: ret
;
; RV32I-LABEL: fcvt_lu_s:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __fixunssfdi
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_lu_s:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __fixunssfdi
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptoui float %a to i64
ret i64 %1
}
define float @fcvt_s_l(i64 %a) nounwind {
; RV32IF-LABEL: fcvt_s_l:
; RV32IF: # %bb.0:
; RV32IF-NEXT: addi sp, sp, -16
; RV32IF-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IF-NEXT: call __floatdisf
; RV32IF-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IF-NEXT: addi sp, sp, 16
; RV32IF-NEXT: ret
;
; RV64IF-LABEL: fcvt_s_l:
; RV64IF: # %bb.0:
; RV64IF-NEXT: fcvt.s.l fa0, a0
; RV64IF-NEXT: ret
;
; RV32I-LABEL: fcvt_s_l:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __floatdisf
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_s_l:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __floatdisf
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = sitofp i64 %a to float
ret float %1
}
define float @fcvt_s_lu(i64 %a) nounwind {
; RV32IF-LABEL: fcvt_s_lu:
; RV32IF: # %bb.0:
; RV32IF-NEXT: addi sp, sp, -16
; RV32IF-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32IF-NEXT: call __floatundisf
; RV32IF-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32IF-NEXT: addi sp, sp, 16
; RV32IF-NEXT: ret
;
; RV64IF-LABEL: fcvt_s_lu:
; RV64IF: # %bb.0:
; RV64IF-NEXT: fcvt.s.lu fa0, a0
; RV64IF-NEXT: ret
;
; RV32I-LABEL: fcvt_s_lu:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __floatundisf
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_s_lu:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __floatundisf
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = uitofp i64 %a to float
ret float %1
}
define float @fcvt_s_w_i8(i8 signext %a) nounwind {
; CHECKIF-LABEL: fcvt_s_w_i8:
; CHECKIF: # %bb.0:
; CHECKIF-NEXT: fcvt.s.w fa0, a0
; CHECKIF-NEXT: ret
;
; RV32I-LABEL: fcvt_s_w_i8:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __floatsisf
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_s_w_i8:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __floatsisf
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = sitofp i8 %a to float
ret float %1
}
define float @fcvt_s_wu_i8(i8 zeroext %a) nounwind {
; CHECKIF-LABEL: fcvt_s_wu_i8:
; CHECKIF: # %bb.0:
; CHECKIF-NEXT: fcvt.s.wu fa0, a0
; CHECKIF-NEXT: ret
;
; RV32I-LABEL: fcvt_s_wu_i8:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __floatunsisf
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_s_wu_i8:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __floatunsisf
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = uitofp i8 %a to float
ret float %1
}
define float @fcvt_s_w_i16(i16 signext %a) nounwind {
; CHECKIF-LABEL: fcvt_s_w_i16:
; CHECKIF: # %bb.0:
; CHECKIF-NEXT: fcvt.s.w fa0, a0
; CHECKIF-NEXT: ret
;
; RV32I-LABEL: fcvt_s_w_i16:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __floatsisf
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_s_w_i16:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __floatsisf
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = sitofp i16 %a to float
ret float %1
}
define float @fcvt_s_wu_i16(i16 zeroext %a) nounwind {
; CHECKIF-LABEL: fcvt_s_wu_i16:
; CHECKIF: # %bb.0:
; CHECKIF-NEXT: fcvt.s.wu fa0, a0
; CHECKIF-NEXT: ret
;
; RV32I-LABEL: fcvt_s_wu_i16:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32I-NEXT: call __floatunsisf
; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
;
; RV64I-LABEL: fcvt_s_wu_i16:
; RV64I: # %bb.0:
; RV64I-NEXT: addi sp, sp, -16
; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: call __floatunsisf
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = uitofp i16 %a to float
ret float %1
}
; Make sure we select W version of addi on RV64.
define signext i32 @fcvt_s_w_demanded_bits(i32 signext %0, ptr %1) nounwind {
; RV32IF-LABEL: fcvt_s_w_demanded_bits:
; RV32IF: # %bb.0:
; RV32IF-NEXT: addi a0, a0, 1
; RV32IF-NEXT: fcvt.s.w fa5, a0
; RV32IF-NEXT: fsw fa5, 0(a1)
; RV32IF-NEXT: ret
;
; RV64IF-LABEL: fcvt_s_w_demanded_bits:
; RV64IF: # %bb.0:
; RV64IF-NEXT: addiw a0, a0, 1
; RV64IF-NEXT: fcvt.s.w fa5, a0
; RV64IF-NEXT: fsw fa5, 0(a1)
; RV64IF-NEXT: ret
;
; RV32I-LABEL: fcvt_s_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 __floatsisf
; 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_s_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 __floatsisf
; RV64I-NEXT: sw 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 float
store float %4, ptr %1, align 4
ret i32 %3
}
; Make sure we select W version of addi on RV64.
define signext i32 @fcvt_s_wu_demanded_bits(i32 signext %0, ptr %1) nounwind {
; RV32IF-LABEL: fcvt_s_wu_demanded_bits:
; RV32IF: # %bb.0:
; RV32IF-NEXT: addi a0, a0, 1
; RV32IF-NEXT: fcvt.s.wu fa5, a0
; RV32IF-NEXT: fsw fa5, 0(a1)
; RV32IF-NEXT: ret
;
; RV64IF-LABEL: fcvt_s_wu_demanded_bits:
; RV64IF: # %bb.0:
; RV64IF-NEXT: addiw a0, a0, 1
; RV64IF-NEXT: fcvt.s.wu fa5, a0
; RV64IF-NEXT: fsw fa5, 0(a1)
; RV64IF-NEXT: ret
;
; RV32I-LABEL: fcvt_s_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 __floatunsisf
; 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_s_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 __floatunsisf
; RV64I-NEXT: sw 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 float
store float %4, ptr %1, align 4
ret i32 %3
}
define signext i16 @fcvt_w_s_i16(float %a) nounwind {
; RV32IF-LABEL: fcvt_w_s_i16:
; RV32IF: # %bb.0:
; RV32IF-NEXT: fcvt.w.s a0, fa0, rtz
; RV32IF-NEXT: slli a0, a0, 16
; RV32IF-NEXT: srai a0, a0, 16
; RV32IF-NEXT: ret
;
; RV64IF-LABEL: fcvt_w_s_i16:
; RV64IF: # %bb.0:
; RV64IF-NEXT: fcvt.w.s a0, fa0, rtz
; RV64IF-NEXT: slli a0, a0, 48
; RV64IF-NEXT: srai a0, a0, 48
; RV64IF-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 __fixsfsi
; RV32I-NEXT: slli a0, a0, 16
; RV32I-NEXT: srai a0, a0, 16
; 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 __fixsfsi
; RV64I-NEXT: slli a0, a0, 48
; RV64I-NEXT: srai a0, a0, 48
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptosi float %a to i16
ret i16 %1
}
define zeroext i16 @fcvt_wu_s_i16(float %a) nounwind {
; RV32IF-LABEL: fcvt_wu_s_i16:
; RV32IF: # %bb.0:
; RV32IF-NEXT: fcvt.wu.s a0, fa0, rtz
; RV32IF-NEXT: slli a0, a0, 16
; RV32IF-NEXT: srli a0, a0, 16
; RV32IF-NEXT: ret
;
; RV64IF-LABEL: fcvt_wu_s_i16:
; RV64IF: # %bb.0:
; RV64IF-NEXT: fcvt.wu.s a0, fa0, rtz
; RV64IF-NEXT: slli a0, a0, 48
; RV64IF-NEXT: srli a0, a0, 48
; RV64IF-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 __fixunssfsi
; RV32I-NEXT: slli a0, a0, 16
; RV32I-NEXT: srli a0, a0, 16
; 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 __fixunssfsi
; RV64I-NEXT: slli a0, a0, 48
; RV64I-NEXT: srli a0, a0, 48
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptoui float %a to i16
ret i16 %1
}
define signext i8 @fcvt_w_s_i8(float %a) nounwind {
; RV32IF-LABEL: fcvt_w_s_i8:
; RV32IF: # %bb.0:
; RV32IF-NEXT: fcvt.w.s a0, fa0, rtz
; RV32IF-NEXT: slli a0, a0, 24
; RV32IF-NEXT: srai a0, a0, 24
; RV32IF-NEXT: ret
;
; RV64IF-LABEL: fcvt_w_s_i8:
; RV64IF: # %bb.0:
; RV64IF-NEXT: fcvt.w.s a0, fa0, rtz
; RV64IF-NEXT: slli a0, a0, 56
; RV64IF-NEXT: srai a0, a0, 56
; RV64IF-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 __fixsfsi
; RV32I-NEXT: slli a0, a0, 24
; RV32I-NEXT: srai a0, a0, 24
; 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 __fixsfsi
; RV64I-NEXT: slli a0, a0, 56
; RV64I-NEXT: srai a0, a0, 56
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptosi float %a to i8
ret i8 %1
}
define zeroext i8 @fcvt_wu_s_i8(float %a) nounwind {
; CHECKIF-LABEL: fcvt_wu_s_i8:
; CHECKIF: # %bb.0:
; CHECKIF-NEXT: fcvt.wu.s a0, fa0, rtz
; CHECKIF-NEXT: zext.b a0, a0
; CHECKIF-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 __fixunssfsi
; RV32I-NEXT: zext.b a0, a0
; 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 __fixunssfsi
; RV64I-NEXT: zext.b a0, a0
; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 16
; RV64I-NEXT: ret
%1 = fptoui float %a to i8
ret i8 %1
}
Reference in New Issue View Git Blame Copy Permalink