mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 12:12:47 +01:00
ccc67b1eb8
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
189 lines
6.4 KiB
LLVM
189 lines
6.4 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 i64 @testmsxs(float %x) {
|
|
; X86-NOSSE-LABEL: testmsxs:
|
|
; X86-NOSSE: # %bb.0: # %entry
|
|
; X86-NOSSE-NEXT: pushl %ebp
|
|
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 8
|
|
; X86-NOSSE-NEXT: .cfi_offset %ebp, -8
|
|
; X86-NOSSE-NEXT: movl %esp, %ebp
|
|
; X86-NOSSE-NEXT: .cfi_def_cfa_register %ebp
|
|
; X86-NOSSE-NEXT: andl $-8, %esp
|
|
; X86-NOSSE-NEXT: subl $8, %esp
|
|
; X86-NOSSE-NEXT: flds 8(%ebp)
|
|
; X86-NOSSE-NEXT: fistpll (%esp)
|
|
; X86-NOSSE-NEXT: movl (%esp), %eax
|
|
; X86-NOSSE-NEXT: movl {{[0-9]+}}(%esp), %edx
|
|
; X86-NOSSE-NEXT: movl %ebp, %esp
|
|
; X86-NOSSE-NEXT: popl %ebp
|
|
; X86-NOSSE-NEXT: .cfi_def_cfa %esp, 4
|
|
; X86-NOSSE-NEXT: retl
|
|
;
|
|
; X86-SSE2-LABEL: testmsxs:
|
|
; X86-SSE2: # %bb.0: # %entry
|
|
; X86-SSE2-NEXT: pushl %ebp
|
|
; X86-SSE2-NEXT: .cfi_def_cfa_offset 8
|
|
; X86-SSE2-NEXT: .cfi_offset %ebp, -8
|
|
; X86-SSE2-NEXT: movl %esp, %ebp
|
|
; X86-SSE2-NEXT: .cfi_def_cfa_register %ebp
|
|
; X86-SSE2-NEXT: andl $-8, %esp
|
|
; X86-SSE2-NEXT: subl $8, %esp
|
|
; X86-SSE2-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; X86-SSE2-NEXT: movss %xmm0, (%esp)
|
|
; X86-SSE2-NEXT: flds (%esp)
|
|
; X86-SSE2-NEXT: fistpll (%esp)
|
|
; X86-SSE2-NEXT: movl (%esp), %eax
|
|
; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %edx
|
|
; X86-SSE2-NEXT: movl %ebp, %esp
|
|
; X86-SSE2-NEXT: popl %ebp
|
|
; X86-SSE2-NEXT: .cfi_def_cfa %esp, 4
|
|
; X86-SSE2-NEXT: retl
|
|
;
|
|
; X86-AVX-LABEL: testmsxs:
|
|
; X86-AVX: # %bb.0: # %entry
|
|
; X86-AVX-NEXT: pushl %ebp
|
|
; X86-AVX-NEXT: .cfi_def_cfa_offset 8
|
|
; X86-AVX-NEXT: .cfi_offset %ebp, -8
|
|
; X86-AVX-NEXT: movl %esp, %ebp
|
|
; X86-AVX-NEXT: .cfi_def_cfa_register %ebp
|
|
; X86-AVX-NEXT: andl $-8, %esp
|
|
; X86-AVX-NEXT: subl $8, %esp
|
|
; X86-AVX-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; X86-AVX-NEXT: vmovss %xmm0, (%esp)
|
|
; X86-AVX-NEXT: flds (%esp)
|
|
; X86-AVX-NEXT: fistpll (%esp)
|
|
; X86-AVX-NEXT: movl (%esp), %eax
|
|
; X86-AVX-NEXT: movl {{[0-9]+}}(%esp), %edx
|
|
; X86-AVX-NEXT: movl %ebp, %esp
|
|
; X86-AVX-NEXT: popl %ebp
|
|
; X86-AVX-NEXT: .cfi_def_cfa %esp, 4
|
|
; X86-AVX-NEXT: retl
|
|
;
|
|
; X64-SSE-LABEL: testmsxs:
|
|
; X64-SSE: # %bb.0: # %entry
|
|
; X64-SSE-NEXT: cvtss2si %xmm0, %rax
|
|
; X64-SSE-NEXT: retq
|
|
;
|
|
; X64-AVX-LABEL: testmsxs:
|
|
; X64-AVX: # %bb.0: # %entry
|
|
; X64-AVX-NEXT: vcvtss2si %xmm0, %rax
|
|
; X64-AVX-NEXT: retq
|
|
entry:
|
|
%0 = tail call i64 @llvm.llrint.f32(float %x)
|
|
ret i64 %0
|
|
}
|
|
|
|
define i64 @testmsxd(double %x) {
|
|
; X86-NOSSE-LABEL: testmsxd:
|
|
; X86-NOSSE: # %bb.0: # %entry
|
|
; X86-NOSSE-NEXT: pushl %ebp
|
|
; X86-NOSSE-NEXT: .cfi_def_cfa_offset 8
|
|
; X86-NOSSE-NEXT: .cfi_offset %ebp, -8
|
|
; X86-NOSSE-NEXT: movl %esp, %ebp
|
|
; X86-NOSSE-NEXT: .cfi_def_cfa_register %ebp
|
|
; X86-NOSSE-NEXT: andl $-8, %esp
|
|
; X86-NOSSE-NEXT: subl $8, %esp
|
|
; X86-NOSSE-NEXT: fldl 8(%ebp)
|
|
; X86-NOSSE-NEXT: fistpll (%esp)
|
|
; X86-NOSSE-NEXT: movl (%esp), %eax
|
|
; X86-NOSSE-NEXT: movl {{[0-9]+}}(%esp), %edx
|
|
; X86-NOSSE-NEXT: movl %ebp, %esp
|
|
; X86-NOSSE-NEXT: popl %ebp
|
|
; X86-NOSSE-NEXT: .cfi_def_cfa %esp, 4
|
|
; X86-NOSSE-NEXT: retl
|
|
;
|
|
; X86-SSE2-LABEL: testmsxd:
|
|
; X86-SSE2: # %bb.0: # %entry
|
|
; X86-SSE2-NEXT: pushl %ebp
|
|
; X86-SSE2-NEXT: .cfi_def_cfa_offset 8
|
|
; X86-SSE2-NEXT: .cfi_offset %ebp, -8
|
|
; X86-SSE2-NEXT: movl %esp, %ebp
|
|
; X86-SSE2-NEXT: .cfi_def_cfa_register %ebp
|
|
; X86-SSE2-NEXT: andl $-8, %esp
|
|
; X86-SSE2-NEXT: subl $8, %esp
|
|
; X86-SSE2-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
|
|
; X86-SSE2-NEXT: movsd %xmm0, (%esp)
|
|
; X86-SSE2-NEXT: fldl (%esp)
|
|
; X86-SSE2-NEXT: fistpll (%esp)
|
|
; X86-SSE2-NEXT: movl (%esp), %eax
|
|
; X86-SSE2-NEXT: movl {{[0-9]+}}(%esp), %edx
|
|
; X86-SSE2-NEXT: movl %ebp, %esp
|
|
; X86-SSE2-NEXT: popl %ebp
|
|
; X86-SSE2-NEXT: .cfi_def_cfa %esp, 4
|
|
; X86-SSE2-NEXT: retl
|
|
;
|
|
; X86-AVX-LABEL: testmsxd:
|
|
; X86-AVX: # %bb.0: # %entry
|
|
; X86-AVX-NEXT: pushl %ebp
|
|
; X86-AVX-NEXT: .cfi_def_cfa_offset 8
|
|
; X86-AVX-NEXT: .cfi_offset %ebp, -8
|
|
; X86-AVX-NEXT: movl %esp, %ebp
|
|
; X86-AVX-NEXT: .cfi_def_cfa_register %ebp
|
|
; X86-AVX-NEXT: andl $-8, %esp
|
|
; X86-AVX-NEXT: subl $8, %esp
|
|
; X86-AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
|
|
; X86-AVX-NEXT: vmovsd %xmm0, (%esp)
|
|
; X86-AVX-NEXT: fldl (%esp)
|
|
; X86-AVX-NEXT: fistpll (%esp)
|
|
; X86-AVX-NEXT: movl (%esp), %eax
|
|
; X86-AVX-NEXT: movl {{[0-9]+}}(%esp), %edx
|
|
; X86-AVX-NEXT: movl %ebp, %esp
|
|
; X86-AVX-NEXT: popl %ebp
|
|
; X86-AVX-NEXT: .cfi_def_cfa %esp, 4
|
|
; X86-AVX-NEXT: retl
|
|
;
|
|
; X64-SSE-LABEL: testmsxd:
|
|
; X64-SSE: # %bb.0: # %entry
|
|
; X64-SSE-NEXT: cvtsd2si %xmm0, %rax
|
|
; X64-SSE-NEXT: retq
|
|
;
|
|
; X64-AVX-LABEL: testmsxd:
|
|
; X64-AVX: # %bb.0: # %entry
|
|
; X64-AVX-NEXT: vcvtsd2si %xmm0, %rax
|
|
; X64-AVX-NEXT: retq
|
|
entry:
|
|
%0 = tail call i64 @llvm.llrint.f64(double %x)
|
|
ret i64 %0
|
|
}
|
|
|
|
define i64 @testmsll(x86_fp80 %x) {
|
|
; X86-LABEL: testmsll:
|
|
; X86: # %bb.0: # %entry
|
|
; X86-NEXT: pushl %ebp
|
|
; X86-NEXT: .cfi_def_cfa_offset 8
|
|
; X86-NEXT: .cfi_offset %ebp, -8
|
|
; X86-NEXT: movl %esp, %ebp
|
|
; X86-NEXT: .cfi_def_cfa_register %ebp
|
|
; X86-NEXT: andl $-8, %esp
|
|
; X86-NEXT: subl $8, %esp
|
|
; X86-NEXT: fldt 8(%ebp)
|
|
; X86-NEXT: fistpll (%esp)
|
|
; X86-NEXT: movl (%esp), %eax
|
|
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
|
|
; X86-NEXT: movl %ebp, %esp
|
|
; X86-NEXT: popl %ebp
|
|
; X86-NEXT: .cfi_def_cfa %esp, 4
|
|
; X86-NEXT: retl
|
|
;
|
|
; X64-LABEL: testmsll:
|
|
; X64: # %bb.0: # %entry
|
|
; X64-NEXT: fldt {{[0-9]+}}(%rsp)
|
|
; X64-NEXT: fistpll -{{[0-9]+}}(%rsp)
|
|
; X64-NEXT: movq -{{[0-9]+}}(%rsp), %rax
|
|
; X64-NEXT: retq
|
|
entry:
|
|
%0 = tail call i64 @llvm.llrint.f80(x86_fp80 %x)
|
|
ret i64 %0
|
|
}
|
|
|
|
declare i64 @llvm.llrint.f32(float) nounwind readnone
|
|
declare i64 @llvm.llrint.f64(double) nounwind readnone
|
|
declare i64 @llvm.llrint.f80(x86_fp80) nounwind readnone
|