559a9db5f5
This change passes 'half' in the lower 16 bits of an f32 value with F/D ABI. LoongArch currently lacks a hardware extension for the fp16 data type, and the ABI manual now documents the half-precision floating-point type following FP calling conventions. Previously, we maintained the 'half' type in its 16-bit format between operations. Regardless of whether the F extension is enabled, the value would be passed in the lower 16 bits of a GPR in its 'half' format. With this patch, depending on the ABI in use, the value will be passed either in an FPR or a GPR in 'half' format. This ensures consistency with the bits location when the fp16 hardware extension is enabled. Co-authored-by: WANG Rui <wangrui@loongson.cn>
546 lines
19 KiB
LLVM
546 lines
19 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc --mtriple=loongarch32 --mattr=+d < %s | FileCheck %s --check-prefix=LA32
|
|
; RUN: llc --mtriple=loongarch64 --mattr=+d < %s | FileCheck %s --check-prefix=LA64
|
|
|
|
define void @test_load_store(ptr %p, ptr %q) nounwind {
|
|
; LA32-LABEL: test_load_store:
|
|
; LA32: # %bb.0:
|
|
; LA32-NEXT: ld.h $a0, $a0, 0
|
|
; LA32-NEXT: st.h $a0, $a1, 0
|
|
; LA32-NEXT: ret
|
|
;
|
|
; LA64-LABEL: test_load_store:
|
|
; LA64: # %bb.0:
|
|
; LA64-NEXT: ld.h $a0, $a0, 0
|
|
; LA64-NEXT: st.h $a0, $a1, 0
|
|
; LA64-NEXT: ret
|
|
%a = load half, ptr %p
|
|
store half %a, ptr %q
|
|
ret void
|
|
}
|
|
|
|
define float @test_fpextend_float(ptr %p) nounwind {
|
|
; LA32-LABEL: test_fpextend_float:
|
|
; LA32: # %bb.0:
|
|
; LA32-NEXT: addi.w $sp, $sp, -16
|
|
; LA32-NEXT: st.w $ra, $sp, 12 # 4-byte Folded Spill
|
|
; LA32-NEXT: ld.hu $a0, $a0, 0
|
|
; LA32-NEXT: movgr2fr.w $fa0, $a0
|
|
; LA32-NEXT: bl __extendhfsf2
|
|
; LA32-NEXT: ld.w $ra, $sp, 12 # 4-byte Folded Reload
|
|
; LA32-NEXT: addi.w $sp, $sp, 16
|
|
; LA32-NEXT: ret
|
|
;
|
|
; LA64-LABEL: test_fpextend_float:
|
|
; LA64: # %bb.0:
|
|
; LA64-NEXT: addi.d $sp, $sp, -16
|
|
; LA64-NEXT: st.d $ra, $sp, 8 # 8-byte Folded Spill
|
|
; LA64-NEXT: ld.hu $a0, $a0, 0
|
|
; LA64-NEXT: movgr2fr.w $fa0, $a0
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__extendhfsf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: ld.d $ra, $sp, 8 # 8-byte Folded Reload
|
|
; LA64-NEXT: addi.d $sp, $sp, 16
|
|
; LA64-NEXT: ret
|
|
%a = load half, ptr %p
|
|
%r = fpext half %a to float
|
|
ret float %r
|
|
}
|
|
|
|
define double @test_fpextend_double(ptr %p) nounwind {
|
|
; LA32-LABEL: test_fpextend_double:
|
|
; LA32: # %bb.0:
|
|
; LA32-NEXT: addi.w $sp, $sp, -16
|
|
; LA32-NEXT: st.w $ra, $sp, 12 # 4-byte Folded Spill
|
|
; LA32-NEXT: ld.hu $a0, $a0, 0
|
|
; LA32-NEXT: movgr2fr.w $fa0, $a0
|
|
; LA32-NEXT: bl __extendhfsf2
|
|
; LA32-NEXT: fcvt.d.s $fa0, $fa0
|
|
; LA32-NEXT: ld.w $ra, $sp, 12 # 4-byte Folded Reload
|
|
; LA32-NEXT: addi.w $sp, $sp, 16
|
|
; LA32-NEXT: ret
|
|
;
|
|
; LA64-LABEL: test_fpextend_double:
|
|
; LA64: # %bb.0:
|
|
; LA64-NEXT: addi.d $sp, $sp, -16
|
|
; LA64-NEXT: st.d $ra, $sp, 8 # 8-byte Folded Spill
|
|
; LA64-NEXT: ld.hu $a0, $a0, 0
|
|
; LA64-NEXT: movgr2fr.w $fa0, $a0
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__extendhfsf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: fcvt.d.s $fa0, $fa0
|
|
; LA64-NEXT: ld.d $ra, $sp, 8 # 8-byte Folded Reload
|
|
; LA64-NEXT: addi.d $sp, $sp, 16
|
|
; LA64-NEXT: ret
|
|
%a = load half, ptr %p
|
|
%r = fpext half %a to double
|
|
ret double %r
|
|
}
|
|
|
|
define void @test_fptrunc_float(float %f, ptr %p) nounwind {
|
|
; LA32-LABEL: test_fptrunc_float:
|
|
; LA32: # %bb.0:
|
|
; LA32-NEXT: addi.w $sp, $sp, -16
|
|
; LA32-NEXT: st.w $ra, $sp, 12 # 4-byte Folded Spill
|
|
; LA32-NEXT: st.w $fp, $sp, 8 # 4-byte Folded Spill
|
|
; LA32-NEXT: move $fp, $a0
|
|
; LA32-NEXT: bl __truncsfhf2
|
|
; LA32-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA32-NEXT: st.h $a0, $fp, 0
|
|
; LA32-NEXT: ld.w $fp, $sp, 8 # 4-byte Folded Reload
|
|
; LA32-NEXT: ld.w $ra, $sp, 12 # 4-byte Folded Reload
|
|
; LA32-NEXT: addi.w $sp, $sp, 16
|
|
; LA32-NEXT: ret
|
|
;
|
|
; LA64-LABEL: test_fptrunc_float:
|
|
; LA64: # %bb.0:
|
|
; LA64-NEXT: addi.d $sp, $sp, -16
|
|
; LA64-NEXT: st.d $ra, $sp, 8 # 8-byte Folded Spill
|
|
; LA64-NEXT: st.d $fp, $sp, 0 # 8-byte Folded Spill
|
|
; LA64-NEXT: move $fp, $a0
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__truncsfhf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA64-NEXT: st.h $a0, $fp, 0
|
|
; LA64-NEXT: ld.d $fp, $sp, 0 # 8-byte Folded Reload
|
|
; LA64-NEXT: ld.d $ra, $sp, 8 # 8-byte Folded Reload
|
|
; LA64-NEXT: addi.d $sp, $sp, 16
|
|
; LA64-NEXT: ret
|
|
%a = fptrunc float %f to half
|
|
store half %a, ptr %p
|
|
ret void
|
|
}
|
|
|
|
define void @test_fptrunc_double(double %d, ptr %p) nounwind {
|
|
; LA32-LABEL: test_fptrunc_double:
|
|
; LA32: # %bb.0:
|
|
; LA32-NEXT: addi.w $sp, $sp, -16
|
|
; LA32-NEXT: st.w $ra, $sp, 12 # 4-byte Folded Spill
|
|
; LA32-NEXT: st.w $fp, $sp, 8 # 4-byte Folded Spill
|
|
; LA32-NEXT: move $fp, $a0
|
|
; LA32-NEXT: bl __truncdfhf2
|
|
; LA32-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA32-NEXT: st.h $a0, $fp, 0
|
|
; LA32-NEXT: ld.w $fp, $sp, 8 # 4-byte Folded Reload
|
|
; LA32-NEXT: ld.w $ra, $sp, 12 # 4-byte Folded Reload
|
|
; LA32-NEXT: addi.w $sp, $sp, 16
|
|
; LA32-NEXT: ret
|
|
;
|
|
; LA64-LABEL: test_fptrunc_double:
|
|
; LA64: # %bb.0:
|
|
; LA64-NEXT: addi.d $sp, $sp, -16
|
|
; LA64-NEXT: st.d $ra, $sp, 8 # 8-byte Folded Spill
|
|
; LA64-NEXT: st.d $fp, $sp, 0 # 8-byte Folded Spill
|
|
; LA64-NEXT: move $fp, $a0
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__truncdfhf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA64-NEXT: st.h $a0, $fp, 0
|
|
; LA64-NEXT: ld.d $fp, $sp, 0 # 8-byte Folded Reload
|
|
; LA64-NEXT: ld.d $ra, $sp, 8 # 8-byte Folded Reload
|
|
; LA64-NEXT: addi.d $sp, $sp, 16
|
|
; LA64-NEXT: ret
|
|
%a = fptrunc double %d to half
|
|
store half %a, ptr %p
|
|
ret void
|
|
}
|
|
|
|
define half @test_fadd_reg(half %a, half %b) nounwind {
|
|
; LA32-LABEL: test_fadd_reg:
|
|
; LA32: # %bb.0:
|
|
; LA32-NEXT: addi.w $sp, $sp, -32
|
|
; LA32-NEXT: st.w $ra, $sp, 28 # 4-byte Folded Spill
|
|
; LA32-NEXT: fst.d $fs0, $sp, 16 # 8-byte Folded Spill
|
|
; LA32-NEXT: fst.d $fs1, $sp, 8 # 8-byte Folded Spill
|
|
; LA32-NEXT: fmov.s $fs0, $fa0
|
|
; LA32-NEXT: fmov.s $fa0, $fa1
|
|
; LA32-NEXT: bl __extendhfsf2
|
|
; LA32-NEXT: fmov.s $fs1, $fa0
|
|
; LA32-NEXT: fmov.s $fa0, $fs0
|
|
; LA32-NEXT: bl __extendhfsf2
|
|
; LA32-NEXT: fadd.s $fa0, $fa0, $fs1
|
|
; LA32-NEXT: bl __truncsfhf2
|
|
; LA32-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA32-NEXT: lu12i.w $a1, -16
|
|
; LA32-NEXT: or $a0, $a0, $a1
|
|
; LA32-NEXT: movgr2fr.w $fa0, $a0
|
|
; LA32-NEXT: fld.d $fs1, $sp, 8 # 8-byte Folded Reload
|
|
; LA32-NEXT: fld.d $fs0, $sp, 16 # 8-byte Folded Reload
|
|
; LA32-NEXT: ld.w $ra, $sp, 28 # 4-byte Folded Reload
|
|
; LA32-NEXT: addi.w $sp, $sp, 32
|
|
; LA32-NEXT: ret
|
|
;
|
|
; LA64-LABEL: test_fadd_reg:
|
|
; LA64: # %bb.0:
|
|
; LA64-NEXT: addi.d $sp, $sp, -32
|
|
; LA64-NEXT: st.d $ra, $sp, 24 # 8-byte Folded Spill
|
|
; LA64-NEXT: fst.d $fs0, $sp, 16 # 8-byte Folded Spill
|
|
; LA64-NEXT: fst.d $fs1, $sp, 8 # 8-byte Folded Spill
|
|
; LA64-NEXT: fmov.s $fs0, $fa0
|
|
; LA64-NEXT: fmov.s $fa0, $fa1
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__extendhfsf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: fmov.s $fs1, $fa0
|
|
; LA64-NEXT: fmov.s $fa0, $fs0
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__extendhfsf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: fadd.s $fa0, $fa0, $fs1
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__truncsfhf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA64-NEXT: lu12i.w $a1, -16
|
|
; LA64-NEXT: or $a0, $a0, $a1
|
|
; LA64-NEXT: movgr2fr.w $fa0, $a0
|
|
; LA64-NEXT: fld.d $fs1, $sp, 8 # 8-byte Folded Reload
|
|
; LA64-NEXT: fld.d $fs0, $sp, 16 # 8-byte Folded Reload
|
|
; LA64-NEXT: ld.d $ra, $sp, 24 # 8-byte Folded Reload
|
|
; LA64-NEXT: addi.d $sp, $sp, 32
|
|
; LA64-NEXT: ret
|
|
%r = fadd half %a, %b
|
|
ret half %r
|
|
}
|
|
|
|
define void @test_fadd_mem(ptr %p, ptr %q) nounwind {
|
|
; LA32-LABEL: test_fadd_mem:
|
|
; LA32: # %bb.0:
|
|
; LA32-NEXT: addi.w $sp, $sp, -32
|
|
; LA32-NEXT: st.w $ra, $sp, 28 # 4-byte Folded Spill
|
|
; LA32-NEXT: st.w $fp, $sp, 24 # 4-byte Folded Spill
|
|
; LA32-NEXT: fst.d $fs0, $sp, 16 # 8-byte Folded Spill
|
|
; LA32-NEXT: fst.d $fs1, $sp, 8 # 8-byte Folded Spill
|
|
; LA32-NEXT: move $fp, $a0
|
|
; LA32-NEXT: ld.hu $a0, $a0, 0
|
|
; LA32-NEXT: ld.hu $a1, $a1, 0
|
|
; LA32-NEXT: movgr2fr.w $fs0, $a0
|
|
; LA32-NEXT: movgr2fr.w $fa0, $a1
|
|
; LA32-NEXT: bl __extendhfsf2
|
|
; LA32-NEXT: fmov.s $fs1, $fa0
|
|
; LA32-NEXT: fmov.s $fa0, $fs0
|
|
; LA32-NEXT: bl __extendhfsf2
|
|
; LA32-NEXT: fadd.s $fa0, $fa0, $fs1
|
|
; LA32-NEXT: bl __truncsfhf2
|
|
; LA32-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA32-NEXT: st.h $a0, $fp, 0
|
|
; LA32-NEXT: fld.d $fs1, $sp, 8 # 8-byte Folded Reload
|
|
; LA32-NEXT: fld.d $fs0, $sp, 16 # 8-byte Folded Reload
|
|
; LA32-NEXT: ld.w $fp, $sp, 24 # 4-byte Folded Reload
|
|
; LA32-NEXT: ld.w $ra, $sp, 28 # 4-byte Folded Reload
|
|
; LA32-NEXT: addi.w $sp, $sp, 32
|
|
; LA32-NEXT: ret
|
|
;
|
|
; LA64-LABEL: test_fadd_mem:
|
|
; LA64: # %bb.0:
|
|
; LA64-NEXT: addi.d $sp, $sp, -32
|
|
; LA64-NEXT: st.d $ra, $sp, 24 # 8-byte Folded Spill
|
|
; LA64-NEXT: st.d $fp, $sp, 16 # 8-byte Folded Spill
|
|
; LA64-NEXT: st.d $s0, $sp, 8 # 8-byte Folded Spill
|
|
; LA64-NEXT: fst.d $fs0, $sp, 0 # 8-byte Folded Spill
|
|
; LA64-NEXT: move $fp, $a0
|
|
; LA64-NEXT: ld.hu $s0, $a0, 0
|
|
; LA64-NEXT: ld.hu $a0, $a1, 0
|
|
; LA64-NEXT: movgr2fr.w $fa0, $a0
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__extendhfsf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: fmov.s $fs0, $fa0
|
|
; LA64-NEXT: movgr2fr.w $fa0, $s0
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__extendhfsf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: fadd.s $fa0, $fa0, $fs0
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__truncsfhf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA64-NEXT: st.h $a0, $fp, 0
|
|
; LA64-NEXT: fld.d $fs0, $sp, 0 # 8-byte Folded Reload
|
|
; LA64-NEXT: ld.d $s0, $sp, 8 # 8-byte Folded Reload
|
|
; LA64-NEXT: ld.d $fp, $sp, 16 # 8-byte Folded Reload
|
|
; LA64-NEXT: ld.d $ra, $sp, 24 # 8-byte Folded Reload
|
|
; LA64-NEXT: addi.d $sp, $sp, 32
|
|
; LA64-NEXT: ret
|
|
%a = load half, ptr %p
|
|
%b = load half, ptr %q
|
|
%r = fadd half %a, %b
|
|
store half %r, ptr %p
|
|
ret void
|
|
}
|
|
|
|
define half @test_fmul_reg(half %a, half %b) nounwind {
|
|
; LA32-LABEL: test_fmul_reg:
|
|
; LA32: # %bb.0:
|
|
; LA32-NEXT: addi.w $sp, $sp, -32
|
|
; LA32-NEXT: st.w $ra, $sp, 28 # 4-byte Folded Spill
|
|
; LA32-NEXT: fst.d $fs0, $sp, 16 # 8-byte Folded Spill
|
|
; LA32-NEXT: fst.d $fs1, $sp, 8 # 8-byte Folded Spill
|
|
; LA32-NEXT: fmov.s $fs0, $fa0
|
|
; LA32-NEXT: fmov.s $fa0, $fa1
|
|
; LA32-NEXT: bl __extendhfsf2
|
|
; LA32-NEXT: fmov.s $fs1, $fa0
|
|
; LA32-NEXT: fmov.s $fa0, $fs0
|
|
; LA32-NEXT: bl __extendhfsf2
|
|
; LA32-NEXT: fmul.s $fa0, $fa0, $fs1
|
|
; LA32-NEXT: bl __truncsfhf2
|
|
; LA32-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA32-NEXT: lu12i.w $a1, -16
|
|
; LA32-NEXT: or $a0, $a0, $a1
|
|
; LA32-NEXT: movgr2fr.w $fa0, $a0
|
|
; LA32-NEXT: fld.d $fs1, $sp, 8 # 8-byte Folded Reload
|
|
; LA32-NEXT: fld.d $fs0, $sp, 16 # 8-byte Folded Reload
|
|
; LA32-NEXT: ld.w $ra, $sp, 28 # 4-byte Folded Reload
|
|
; LA32-NEXT: addi.w $sp, $sp, 32
|
|
; LA32-NEXT: ret
|
|
;
|
|
; LA64-LABEL: test_fmul_reg:
|
|
; LA64: # %bb.0:
|
|
; LA64-NEXT: addi.d $sp, $sp, -32
|
|
; LA64-NEXT: st.d $ra, $sp, 24 # 8-byte Folded Spill
|
|
; LA64-NEXT: fst.d $fs0, $sp, 16 # 8-byte Folded Spill
|
|
; LA64-NEXT: fst.d $fs1, $sp, 8 # 8-byte Folded Spill
|
|
; LA64-NEXT: fmov.s $fs0, $fa0
|
|
; LA64-NEXT: fmov.s $fa0, $fa1
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__extendhfsf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: fmov.s $fs1, $fa0
|
|
; LA64-NEXT: fmov.s $fa0, $fs0
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__extendhfsf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: fmul.s $fa0, $fa0, $fs1
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__truncsfhf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA64-NEXT: lu12i.w $a1, -16
|
|
; LA64-NEXT: or $a0, $a0, $a1
|
|
; LA64-NEXT: movgr2fr.w $fa0, $a0
|
|
; LA64-NEXT: fld.d $fs1, $sp, 8 # 8-byte Folded Reload
|
|
; LA64-NEXT: fld.d $fs0, $sp, 16 # 8-byte Folded Reload
|
|
; LA64-NEXT: ld.d $ra, $sp, 24 # 8-byte Folded Reload
|
|
; LA64-NEXT: addi.d $sp, $sp, 32
|
|
; LA64-NEXT: ret
|
|
%r = fmul half %a, %b
|
|
ret half %r
|
|
}
|
|
|
|
define void @test_fmul_mem(ptr %p, ptr %q) nounwind {
|
|
; LA32-LABEL: test_fmul_mem:
|
|
; LA32: # %bb.0:
|
|
; LA32-NEXT: addi.w $sp, $sp, -32
|
|
; LA32-NEXT: st.w $ra, $sp, 28 # 4-byte Folded Spill
|
|
; LA32-NEXT: st.w $fp, $sp, 24 # 4-byte Folded Spill
|
|
; LA32-NEXT: fst.d $fs0, $sp, 16 # 8-byte Folded Spill
|
|
; LA32-NEXT: fst.d $fs1, $sp, 8 # 8-byte Folded Spill
|
|
; LA32-NEXT: move $fp, $a0
|
|
; LA32-NEXT: ld.hu $a0, $a0, 0
|
|
; LA32-NEXT: ld.hu $a1, $a1, 0
|
|
; LA32-NEXT: movgr2fr.w $fs0, $a0
|
|
; LA32-NEXT: movgr2fr.w $fa0, $a1
|
|
; LA32-NEXT: bl __extendhfsf2
|
|
; LA32-NEXT: fmov.s $fs1, $fa0
|
|
; LA32-NEXT: fmov.s $fa0, $fs0
|
|
; LA32-NEXT: bl __extendhfsf2
|
|
; LA32-NEXT: fmul.s $fa0, $fa0, $fs1
|
|
; LA32-NEXT: bl __truncsfhf2
|
|
; LA32-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA32-NEXT: st.h $a0, $fp, 0
|
|
; LA32-NEXT: fld.d $fs1, $sp, 8 # 8-byte Folded Reload
|
|
; LA32-NEXT: fld.d $fs0, $sp, 16 # 8-byte Folded Reload
|
|
; LA32-NEXT: ld.w $fp, $sp, 24 # 4-byte Folded Reload
|
|
; LA32-NEXT: ld.w $ra, $sp, 28 # 4-byte Folded Reload
|
|
; LA32-NEXT: addi.w $sp, $sp, 32
|
|
; LA32-NEXT: ret
|
|
;
|
|
; LA64-LABEL: test_fmul_mem:
|
|
; LA64: # %bb.0:
|
|
; LA64-NEXT: addi.d $sp, $sp, -32
|
|
; LA64-NEXT: st.d $ra, $sp, 24 # 8-byte Folded Spill
|
|
; LA64-NEXT: st.d $fp, $sp, 16 # 8-byte Folded Spill
|
|
; LA64-NEXT: st.d $s0, $sp, 8 # 8-byte Folded Spill
|
|
; LA64-NEXT: fst.d $fs0, $sp, 0 # 8-byte Folded Spill
|
|
; LA64-NEXT: move $fp, $a0
|
|
; LA64-NEXT: ld.hu $s0, $a0, 0
|
|
; LA64-NEXT: ld.hu $a0, $a1, 0
|
|
; LA64-NEXT: movgr2fr.w $fa0, $a0
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__extendhfsf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: fmov.s $fs0, $fa0
|
|
; LA64-NEXT: movgr2fr.w $fa0, $s0
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__extendhfsf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: fmul.s $fa0, $fa0, $fs0
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__truncsfhf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA64-NEXT: st.h $a0, $fp, 0
|
|
; LA64-NEXT: fld.d $fs0, $sp, 0 # 8-byte Folded Reload
|
|
; LA64-NEXT: ld.d $s0, $sp, 8 # 8-byte Folded Reload
|
|
; LA64-NEXT: ld.d $fp, $sp, 16 # 8-byte Folded Reload
|
|
; LA64-NEXT: ld.d $ra, $sp, 24 # 8-byte Folded Reload
|
|
; LA64-NEXT: addi.d $sp, $sp, 32
|
|
; LA64-NEXT: ret
|
|
%a = load half, ptr %p
|
|
%b = load half, ptr %q
|
|
%r = fmul half %a, %b
|
|
store half %r, ptr %p
|
|
ret void
|
|
}
|
|
|
|
define half @freeze_half_undef() nounwind {
|
|
; LA32-LABEL: freeze_half_undef:
|
|
; LA32: # %bb.0:
|
|
; LA32-NEXT: addi.w $sp, $sp, -16
|
|
; LA32-NEXT: st.w $ra, $sp, 12 # 4-byte Folded Spill
|
|
; LA32-NEXT: movgr2fr.w $fa0, $zero
|
|
; LA32-NEXT: bl __truncsfhf2
|
|
; LA32-NEXT: bl __extendhfsf2
|
|
; LA32-NEXT: fadd.s $fa0, $fa0, $fa0
|
|
; LA32-NEXT: bl __truncsfhf2
|
|
; LA32-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA32-NEXT: lu12i.w $a1, -16
|
|
; LA32-NEXT: or $a0, $a0, $a1
|
|
; LA32-NEXT: movgr2fr.w $fa0, $a0
|
|
; LA32-NEXT: ld.w $ra, $sp, 12 # 4-byte Folded Reload
|
|
; LA32-NEXT: addi.w $sp, $sp, 16
|
|
; LA32-NEXT: ret
|
|
;
|
|
; LA64-LABEL: freeze_half_undef:
|
|
; LA64: # %bb.0:
|
|
; LA64-NEXT: addi.d $sp, $sp, -16
|
|
; LA64-NEXT: st.d $ra, $sp, 8 # 8-byte Folded Spill
|
|
; LA64-NEXT: movgr2fr.w $fa0, $zero
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__truncsfhf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__extendhfsf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: fadd.s $fa0, $fa0, $fa0
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__truncsfhf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA64-NEXT: lu12i.w $a1, -16
|
|
; LA64-NEXT: or $a0, $a0, $a1
|
|
; LA64-NEXT: movgr2fr.w $fa0, $a0
|
|
; LA64-NEXT: ld.d $ra, $sp, 8 # 8-byte Folded Reload
|
|
; LA64-NEXT: addi.d $sp, $sp, 16
|
|
; LA64-NEXT: ret
|
|
%y1 = freeze half undef
|
|
%t1 = fadd half %y1, %y1
|
|
ret half %t1
|
|
}
|
|
|
|
define half @freeze_half_poison(half %maybe.poison) nounwind {
|
|
; LA32-LABEL: freeze_half_poison:
|
|
; LA32: # %bb.0:
|
|
; LA32-NEXT: addi.w $sp, $sp, -16
|
|
; LA32-NEXT: st.w $ra, $sp, 12 # 4-byte Folded Spill
|
|
; LA32-NEXT: bl __extendhfsf2
|
|
; LA32-NEXT: fadd.s $fa0, $fa0, $fa0
|
|
; LA32-NEXT: bl __truncsfhf2
|
|
; LA32-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA32-NEXT: lu12i.w $a1, -16
|
|
; LA32-NEXT: or $a0, $a0, $a1
|
|
; LA32-NEXT: movgr2fr.w $fa0, $a0
|
|
; LA32-NEXT: ld.w $ra, $sp, 12 # 4-byte Folded Reload
|
|
; LA32-NEXT: addi.w $sp, $sp, 16
|
|
; LA32-NEXT: ret
|
|
;
|
|
; LA64-LABEL: freeze_half_poison:
|
|
; LA64: # %bb.0:
|
|
; LA64-NEXT: addi.d $sp, $sp, -16
|
|
; LA64-NEXT: st.d $ra, $sp, 8 # 8-byte Folded Spill
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__extendhfsf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: fadd.s $fa0, $fa0, $fa0
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__truncsfhf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA64-NEXT: lu12i.w $a1, -16
|
|
; LA64-NEXT: or $a0, $a0, $a1
|
|
; LA64-NEXT: movgr2fr.w $fa0, $a0
|
|
; LA64-NEXT: ld.d $ra, $sp, 8 # 8-byte Folded Reload
|
|
; LA64-NEXT: addi.d $sp, $sp, 16
|
|
; LA64-NEXT: ret
|
|
%y1 = freeze half %maybe.poison
|
|
%t1 = fadd half %y1, %y1
|
|
ret half %t1
|
|
}
|
|
|
|
define signext i32 @test_half_to_s32(half %a) nounwind {
|
|
; LA32-LABEL: test_half_to_s32:
|
|
; LA32: # %bb.0: # %entry
|
|
; LA32-NEXT: addi.w $sp, $sp, -16
|
|
; LA32-NEXT: st.w $ra, $sp, 12 # 4-byte Folded Spill
|
|
; LA32-NEXT: bl __extendhfsf2
|
|
; LA32-NEXT: ftintrz.w.s $fa0, $fa0
|
|
; LA32-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA32-NEXT: ld.w $ra, $sp, 12 # 4-byte Folded Reload
|
|
; LA32-NEXT: addi.w $sp, $sp, 16
|
|
; LA32-NEXT: ret
|
|
;
|
|
; LA64-LABEL: test_half_to_s32:
|
|
; LA64: # %bb.0: # %entry
|
|
; LA64-NEXT: addi.d $sp, $sp, -16
|
|
; LA64-NEXT: st.d $ra, $sp, 8 # 8-byte Folded Spill
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__extendhfsf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: ftintrz.l.s $fa0, $fa0
|
|
; LA64-NEXT: movfr2gr.d $a0, $fa0
|
|
; LA64-NEXT: ld.d $ra, $sp, 8 # 8-byte Folded Reload
|
|
; LA64-NEXT: addi.d $sp, $sp, 16
|
|
; LA64-NEXT: ret
|
|
entry:
|
|
%conv = fptosi half %a to i32
|
|
ret i32 %conv
|
|
}
|
|
|
|
define zeroext i32 @test_half_to_s32_u32(half %a) nounwind {
|
|
; LA32-LABEL: test_half_to_s32_u32:
|
|
; LA32: # %bb.0: # %entry
|
|
; LA32-NEXT: addi.w $sp, $sp, -16
|
|
; LA32-NEXT: st.w $ra, $sp, 12 # 4-byte Folded Spill
|
|
; LA32-NEXT: bl __extendhfsf2
|
|
; LA32-NEXT: ftintrz.w.s $fa0, $fa0
|
|
; LA32-NEXT: movfr2gr.s $a0, $fa0
|
|
; LA32-NEXT: ld.w $ra, $sp, 12 # 4-byte Folded Reload
|
|
; LA32-NEXT: addi.w $sp, $sp, 16
|
|
; LA32-NEXT: ret
|
|
;
|
|
; LA64-LABEL: test_half_to_s32_u32:
|
|
; LA64: # %bb.0: # %entry
|
|
; LA64-NEXT: addi.d $sp, $sp, -16
|
|
; LA64-NEXT: st.d $ra, $sp, 8 # 8-byte Folded Spill
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__extendhfsf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: ftintrz.l.s $fa0, $fa0
|
|
; LA64-NEXT: movfr2gr.d $a0, $fa0
|
|
; LA64-NEXT: bstrpick.d $a0, $a0, 31, 0
|
|
; LA64-NEXT: ld.d $ra, $sp, 8 # 8-byte Folded Reload
|
|
; LA64-NEXT: addi.d $sp, $sp, 16
|
|
; LA64-NEXT: ret
|
|
entry:
|
|
%conv = fptosi half %a to i32
|
|
ret i32 %conv
|
|
}
|
|
|
|
define i64 @test_half_to_i64(half %a) nounwind {
|
|
; LA32-LABEL: test_half_to_i64:
|
|
; LA32: # %bb.0: # %entry
|
|
; LA32-NEXT: addi.w $sp, $sp, -16
|
|
; LA32-NEXT: st.w $ra, $sp, 12 # 4-byte Folded Spill
|
|
; LA32-NEXT: bl __extendhfsf2
|
|
; LA32-NEXT: bl __fixsfdi
|
|
; LA32-NEXT: ld.w $ra, $sp, 12 # 4-byte Folded Reload
|
|
; LA32-NEXT: addi.w $sp, $sp, 16
|
|
; LA32-NEXT: ret
|
|
;
|
|
; LA64-LABEL: test_half_to_i64:
|
|
; LA64: # %bb.0: # %entry
|
|
; LA64-NEXT: addi.d $sp, $sp, -16
|
|
; LA64-NEXT: st.d $ra, $sp, 8 # 8-byte Folded Spill
|
|
; LA64-NEXT: pcaddu18i $ra, %call36(__extendhfsf2)
|
|
; LA64-NEXT: jirl $ra, $ra, 0
|
|
; LA64-NEXT: ftintrz.l.s $fa0, $fa0
|
|
; LA64-NEXT: movfr2gr.d $a0, $fa0
|
|
; LA64-NEXT: ld.d $ra, $sp, 8 # 8-byte Folded Reload
|
|
; LA64-NEXT: addi.d $sp, $sp, 16
|
|
; LA64-NEXT: ret
|
|
entry:
|
|
%conv = fptosi half %a to i64
|
|
ret i64 %conv
|
|
}
|