1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 20:23:11 +01:00
llvm-mirror/test/CodeGen/RISCV/fp16-promote.ll
Craig Topper 18b312e6d9 [RISCV] Use softPromoteHalf legalization for fp16 without Zfh rather than PromoteFloat.
The default legalization strategy is PromoteFloat which keeps
half in single precision format through multiple floating point
operations. Conversion to/from float is done at loads, stores,
bitcasts, and other places that care about the exact size being 16
bits.

This patches switches to the alternative method softPromoteHalf.
This aims to keep the type in 16-bit format between every operation.
So we promote to float and immediately round for any arithmetic
operation. This should be closer to the IR semantics since we
are rounding after each operation and not accumulating extra
precision across multiple operations. X86 is the only other
target that enables this today. See https://reviews.llvm.org/D73749

I had to update getRegisterTypeForCallingConv to force f16 to
use f32 when the F extension is enabled. This way we can still
pass it in the lower bits of an FPR for ilp32f and lp64f ABIs.
The softPromoteHalf would otherwise always give i16 as the
argument type.

Reviewed By: asb, frasercrmck

Differential Revision: https://reviews.llvm.org/D99148
2021-04-01 12:41:57 -07:00

143 lines
4.6 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr +d -target-abi ilp32d < %s | FileCheck %s
define void @test_load_store(half* %p, half* %q) nounwind {
; CHECK-LABEL: test_load_store:
; CHECK: # %bb.0:
; CHECK-NEXT: lh a0, 0(a0)
; CHECK-NEXT: sh a0, 0(a1)
; CHECK-NEXT: ret
%a = load half, half* %p
store half %a, half* %q
ret void
}
define float @test_fpextend_float(half* %p) nounwind {
; CHECK-LABEL: test_fpextend_float:
; CHECK: # %bb.0:
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; CHECK-NEXT: lhu a0, 0(a0)
; CHECK-NEXT: call __gnu_h2f_ieee@plt
; CHECK-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
%a = load half, half* %p
%r = fpext half %a to float
ret float %r
}
define double @test_fpextend_double(half* %p) nounwind {
; CHECK-LABEL: test_fpextend_double:
; CHECK: # %bb.0:
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; CHECK-NEXT: lhu a0, 0(a0)
; CHECK-NEXT: call __gnu_h2f_ieee@plt
; CHECK-NEXT: fcvt.d.s fa0, fa0
; CHECK-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
%a = load half, half* %p
%r = fpext half %a to double
ret double %r
}
define void @test_fptrunc_float(float %f, half* %p) nounwind {
; CHECK-LABEL: test_fptrunc_float:
; CHECK: # %bb.0:
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; CHECK-NEXT: sw s0, 8(sp) # 4-byte Folded Spill
; CHECK-NEXT: mv s0, a0
; CHECK-NEXT: call __gnu_f2h_ieee@plt
; CHECK-NEXT: sh a0, 0(s0)
; CHECK-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; CHECK-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
%a = fptrunc float %f to half
store half %a, half* %p
ret void
}
define void @test_fptrunc_double(double %d, half* %p) nounwind {
; CHECK-LABEL: test_fptrunc_double:
; CHECK: # %bb.0:
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; CHECK-NEXT: sw s0, 8(sp) # 4-byte Folded Spill
; CHECK-NEXT: mv s0, a0
; CHECK-NEXT: call __truncdfhf2@plt
; CHECK-NEXT: sh a0, 0(s0)
; CHECK-NEXT: lw s0, 8(sp) # 4-byte Folded Reload
; CHECK-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
%a = fptrunc double %d to half
store half %a, half* %p
ret void
}
define void @test_fadd(half* %p, half* %q) nounwind {
; CHECK-LABEL: test_fadd:
; CHECK: # %bb.0:
; CHECK-NEXT: addi sp, sp, -32
; CHECK-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; CHECK-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; CHECK-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
; CHECK-NEXT: fsd fs0, 8(sp) # 8-byte Folded Spill
; CHECK-NEXT: mv s0, a0
; CHECK-NEXT: lhu s1, 0(a0)
; CHECK-NEXT: lhu a0, 0(a1)
; CHECK-NEXT: call __gnu_h2f_ieee@plt
; CHECK-NEXT: fmv.s fs0, fa0
; CHECK-NEXT: mv a0, s1
; CHECK-NEXT: call __gnu_h2f_ieee@plt
; CHECK-NEXT: fadd.s fa0, fa0, fs0
; CHECK-NEXT: call __gnu_f2h_ieee@plt
; CHECK-NEXT: sh a0, 0(s0)
; CHECK-NEXT: fld fs0, 8(sp) # 8-byte Folded Reload
; CHECK-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; CHECK-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; CHECK-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 32
; CHECK-NEXT: ret
%a = load half, half* %p
%b = load half, half* %q
%r = fadd half %a, %b
store half %r, half* %p
ret void
}
define void @test_fmul(half* %p, half* %q) nounwind {
; CHECK-LABEL: test_fmul:
; CHECK: # %bb.0:
; CHECK-NEXT: addi sp, sp, -32
; CHECK-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; CHECK-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; CHECK-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
; CHECK-NEXT: fsd fs0, 8(sp) # 8-byte Folded Spill
; CHECK-NEXT: mv s0, a0
; CHECK-NEXT: lhu s1, 0(a0)
; CHECK-NEXT: lhu a0, 0(a1)
; CHECK-NEXT: call __gnu_h2f_ieee@plt
; CHECK-NEXT: fmv.s fs0, fa0
; CHECK-NEXT: mv a0, s1
; CHECK-NEXT: call __gnu_h2f_ieee@plt
; CHECK-NEXT: fmul.s fa0, fa0, fs0
; CHECK-NEXT: call __gnu_f2h_ieee@plt
; CHECK-NEXT: sh a0, 0(s0)
; CHECK-NEXT: fld fs0, 8(sp) # 8-byte Folded Reload
; CHECK-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; CHECK-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; CHECK-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 32
; CHECK-NEXT: ret
%a = load half, half* %p
%b = load half, half* %q
%r = fmul half %a, %b
store half %r, half* %p
ret void
}