llvm-6502/test/CodeGen/ARM/fp_convert.ll
Renato Golin 3382a84074 Avoid NEON SP-FP unless unsafe-math or Darwin
NEON is not IEEE 754 compliant, so we should avoid lowering single-precision
floating point operations with NEON unless unsafe-math is turned on. The
equivalent VFP instructions are IEEE 754 compliant, but in some cores they're
much slower, so some archs/OSs might still request it to be on by default,
such as Swift and Darwin.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@177651 91177308-0d34-0410-b5e6-96231b3b80d8
2013-03-21 18:47:47 +00:00

52 lines
1.3 KiB
LLVM

; RUN: llc < %s -march=arm -mattr=+vfp2 | FileCheck %s -check-prefix=VFP2
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s -check-prefix=VFP2
; RUN: llc < %s -march=arm -mcpu=cortex-a8 --enable-unsafe-fp-math | FileCheck %s -check-prefix=NEON
; RUN: llc < %s -march=arm -mcpu=cortex-a8 | FileCheck %s -check-prefix=VFP2
; RUN: llc < %s -march=arm -mcpu=cortex-a9 | FileCheck %s -check-prefix=VFP2
define i32 @test1(float %a, float %b) {
; VFP2: test1:
; VFP2: vcvt.s32.f32 s{{.}}, s{{.}}
; NEON: test1:
; NEON: vadd.f32 [[D0:d[0-9]+]]
; NEON: vcvt.s32.f32 d0, [[D0]]
entry:
%0 = fadd float %a, %b
%1 = fptosi float %0 to i32
ret i32 %1
}
define i32 @test2(float %a, float %b) {
; VFP2: test2:
; VFP2: vcvt.u32.f32 s{{.}}, s{{.}}
; NEON: test2:
; NEON: vadd.f32 [[D0:d[0-9]+]]
; NEON: vcvt.u32.f32 d0, [[D0]]
entry:
%0 = fadd float %a, %b
%1 = fptoui float %0 to i32
ret i32 %1
}
define float @test3(i32 %a, i32 %b) {
; VFP2: test3:
; VFP2: vcvt.f32.u32 s{{.}}, s{{.}}
; NEON: test3:
; NEON: vcvt.f32.u32 d
entry:
%0 = add i32 %a, %b
%1 = uitofp i32 %0 to float
ret float %1
}
define float @test4(i32 %a, i32 %b) {
; VFP2: test4:
; VFP2: vcvt.f32.s32 s{{.}}, s{{.}}
; NEON: test4:
; NEON: vcvt.f32.s32 d
entry:
%0 = add i32 %a, %b
%1 = sitofp i32 %0 to float
ret float %1
}