1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 18:54:02 +01:00
llvm-mirror/test/CodeGen/X86/lrint-conv-i32.ll
Craig Topper ccc67b1eb8 [X86] Add custom lowering for lrint/llrint to either cvtss2si/cvtsd2si or fist.
lrint/llrint are defined as rounding using the current rounding
mode. Numbers that can't be converted raise FE_INVALID and an
implementation defined value is returned. They may also write to
errno.

I believe this means we can use cvtss2si/cvtsd2si or fist to
convert as long as -fno-math-errno is passed on the command line.
Clang will leave them as libcalls if errno is enabled so they
won't become ISD::LRINT/LLRINT in SelectionDAG.

For 64-bit results on a 32-bit target we can't use cvtss2si/cvtsd2si
but we can use fist since it can write to a 64-bit memory location.
Though maybe we could consider using vcvtps2qq/vcvtpd2qq on avx512dq
targets?

gcc also does this optimization.

I think we might be able to do this with STRICT_LRINT/LLRINT as
well, but I've left that for future work.

Differential Revision: https://reviews.llvm.org/D73859
2020-02-04 16:15:40 -08:00

108 lines
3.5 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown | FileCheck %s --check-prefixes=X86,X86-NOSSE
; RUN: llc < %s -mtriple=i686-unknown -mattr=sse2 | FileCheck %s --check-prefixes=X86,X86-SSE2
; RUN: llc < %s -mtriple=i686-unknown -mattr=avx | FileCheck %s --check-prefixes=X86,X86-AVX
; RUN: llc < %s -mtriple=i686-unknown -mattr=avx512f | FileCheck %s --check-prefixes=X86,X86-AVX
; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s --check-prefixes=X64,X64-SSE
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=avx | FileCheck %s --check-prefixes=X64,X64-AVX
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=avx512f | FileCheck %s --check-prefixes=X64,X64-AVX
define i32 @testmsws(float %x) {
; X86-NOSSE-LABEL: testmsws:
; X86-NOSSE: # %bb.0: # %entry
; X86-NOSSE-NEXT: pushl %eax
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 8
; X86-NOSSE-NEXT: flds {{[0-9]+}}(%esp)
; X86-NOSSE-NEXT: fistpl (%esp)
; X86-NOSSE-NEXT: movl (%esp), %eax
; X86-NOSSE-NEXT: popl %ecx
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 4
; X86-NOSSE-NEXT: retl
;
; X86-SSE2-LABEL: testmsws:
; X86-SSE2: # %bb.0: # %entry
; X86-SSE2-NEXT: cvtss2si {{[0-9]+}}(%esp), %eax
; X86-SSE2-NEXT: retl
;
; X86-AVX-LABEL: testmsws:
; X86-AVX: # %bb.0: # %entry
; X86-AVX-NEXT: vcvtss2si {{[0-9]+}}(%esp), %eax
; X86-AVX-NEXT: retl
;
; X64-SSE-LABEL: testmsws:
; X64-SSE: # %bb.0: # %entry
; X64-SSE-NEXT: cvtss2si %xmm0, %eax
; X64-SSE-NEXT: retq
;
; X64-AVX-LABEL: testmsws:
; X64-AVX: # %bb.0: # %entry
; X64-AVX-NEXT: vcvtss2si %xmm0, %eax
; X64-AVX-NEXT: retq
entry:
%0 = tail call i32 @llvm.lrint.i32.f32(float %x)
ret i32 %0
}
define i32 @testmswd(double %x) {
; X86-NOSSE-LABEL: testmswd:
; X86-NOSSE: # %bb.0: # %entry
; X86-NOSSE-NEXT: pushl %eax
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 8
; X86-NOSSE-NEXT: fldl {{[0-9]+}}(%esp)
; X86-NOSSE-NEXT: fistpl (%esp)
; X86-NOSSE-NEXT: movl (%esp), %eax
; X86-NOSSE-NEXT: popl %ecx
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 4
; X86-NOSSE-NEXT: retl
;
; X86-SSE2-LABEL: testmswd:
; X86-SSE2: # %bb.0: # %entry
; X86-SSE2-NEXT: cvtsd2si {{[0-9]+}}(%esp), %eax
; X86-SSE2-NEXT: retl
;
; X86-AVX-LABEL: testmswd:
; X86-AVX: # %bb.0: # %entry
; X86-AVX-NEXT: vcvtsd2si {{[0-9]+}}(%esp), %eax
; X86-AVX-NEXT: retl
;
; X64-SSE-LABEL: testmswd:
; X64-SSE: # %bb.0: # %entry
; X64-SSE-NEXT: cvtsd2si %xmm0, %eax
; X64-SSE-NEXT: retq
;
; X64-AVX-LABEL: testmswd:
; X64-AVX: # %bb.0: # %entry
; X64-AVX-NEXT: vcvtsd2si %xmm0, %eax
; X64-AVX-NEXT: retq
entry:
%0 = tail call i32 @llvm.lrint.i32.f64(double %x)
ret i32 %0
}
define i32 @testmsll(x86_fp80 %x) {
; X86-LABEL: testmsll:
; X86: # %bb.0: # %entry
; X86-NEXT: pushl %eax
; X86-NEXT: .cfi_def_cfa_offset 8
; X86-NEXT: fldt {{[0-9]+}}(%esp)
; X86-NEXT: fistpl (%esp)
; X86-NEXT: movl (%esp), %eax
; X86-NEXT: popl %ecx
; X86-NEXT: .cfi_def_cfa_offset 4
; X86-NEXT: retl
;
; X64-LABEL: testmsll:
; X64: # %bb.0: # %entry
; X64-NEXT: fldt {{[0-9]+}}(%rsp)
; X64-NEXT: fistpl -{{[0-9]+}}(%rsp)
; X64-NEXT: movl -{{[0-9]+}}(%rsp), %eax
; X64-NEXT: retq
entry:
%0 = tail call i32 @llvm.lrint.i32.f80(x86_fp80 %x)
ret i32 %0
}
declare i32 @llvm.lrint.i32.f32(float) nounwind readnone
declare i32 @llvm.lrint.i32.f64(double) nounwind readnone
declare i32 @llvm.lrint.i32.f80(x86_fp80) nounwind readnone