nils.hoelscher
/
llvm-for-llvmta
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
llvm-for-llvmta/test/CodeGen/X86/fp-intrinsics.ll

2832 lines
90 KiB
LLVM
Raw Permalink Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -O3 -mtriple=i686-pc-linux -mattr=+cmov < %s | FileCheck %s --check-prefix=X87
; RUN: llc -O3 -mtriple=i686-pc-linux -mattr=sse2 < %s | FileCheck %s --check-prefix=X86-SSE
; RUN: llc -O3 -mtriple=x86_64-pc-linux < %s | FileCheck %s --check-prefix=SSE
; RUN: llc -O3 -mtriple=x86_64-pc-linux -mattr=+avx < %s | FileCheck %s --check-prefixes=AVX,AVX1
; RUN: llc -O3 -mtriple=x86_64-pc-linux -mattr=+avx512f < %s | FileCheck %s --check-prefixes=AVX,AVX512
; RUN: llc -O3 -mtriple=x86_64-pc-linux -mattr=+avx512dq < %s | FileCheck %s --check-prefixes=AVX,AVX512
; Verify that constants aren't folded to inexact results when the rounding mode
; is unknown.
;
; double f1() {
; // Because 0.1 cannot be represented exactly, this shouldn't be folded.
; return 1.0/10.0;
; }
;
define double @f1() #0 {
; X87-LABEL: f1:
; X87: # %bb.0: # %entry
; X87-NEXT: fld1
; X87-NEXT: fdivs {{\.LCPI.*}}
; X87-NEXT: wait
; X87-NEXT: retl
;
; X86-SSE-LABEL: f1:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: divsd {{\.LCPI.*}}, %xmm0
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: fldl (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f1:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT: divsd {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: f1:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT: vdivsd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%div = call double @llvm.experimental.constrained.fdiv.f64(
double 1.000000e+00,
double 1.000000e+01,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %div
}
; Verify that 'a - 0' isn't simplified to 'a' when the rounding mode is unknown.
;
; double f2(double a) {
; // Because the result of '0 - 0' is negative zero if rounding mode is
; // downward, this shouldn't be simplified.
; return a - 0;
; }
;
define double @f2(double %a) #0 {
; X87-LABEL: f2:
; X87: # %bb.0: # %entry
; X87-NEXT: fldz
; X87-NEXT: fsubrl {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: retl
;
; X86-SSE-LABEL: f2:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: xorpd %xmm1, %xmm1
; X86-SSE-NEXT: subsd %xmm1, %xmm0
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: fldl (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f2:
; SSE: # %bb.0: # %entry
; SSE-NEXT: xorpd %xmm1, %xmm1
; SSE-NEXT: subsd %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: f2:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vxorpd %xmm1, %xmm1, %xmm1
; AVX-NEXT: vsubsd %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%sub = call double @llvm.experimental.constrained.fsub.f64(
double %a,
double 0.000000e+00,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %sub
}
; Verify that '-((-a)*b)' isn't simplified to 'a*b' when the rounding mode is
; unknown.
;
; double f3(double a, double b) {
; // Because the intermediate value involved in this calculation may require
; // rounding, this shouldn't be simplified.
; return -((-a)*b);
; }
;
define double @f3(double %a, double %b) #0 {
; X87-LABEL: f3:
; X87: # %bb.0: # %entry
; X87-NEXT: fldz
; X87-NEXT: fchs
; X87-NEXT: fld %st(0)
; X87-NEXT: fsubl {{[0-9]+}}(%esp)
; X87-NEXT: fmull {{[0-9]+}}(%esp)
; X87-NEXT: fsubrp %st, %st(1)
; X87-NEXT: wait
; X87-NEXT: retl
;
; X86-SSE-LABEL: f3:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movapd %xmm0, %xmm1
; X86-SSE-NEXT: subsd {{[0-9]+}}(%esp), %xmm1
; X86-SSE-NEXT: mulsd {{[0-9]+}}(%esp), %xmm1
; X86-SSE-NEXT: subsd %xmm1, %xmm0
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: fldl (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f3:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movsd {{.*#+}} xmm2 = mem[0],zero
; SSE-NEXT: movapd %xmm2, %xmm3
; SSE-NEXT: subsd %xmm0, %xmm3
; SSE-NEXT: mulsd %xmm1, %xmm3
; SSE-NEXT: subsd %xmm3, %xmm2
; SSE-NEXT: movapd %xmm2, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: f3:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vmovsd {{.*#+}} xmm2 = mem[0],zero
; AVX-NEXT: vsubsd %xmm0, %xmm2, %xmm0
; AVX-NEXT: vmulsd %xmm1, %xmm0, %xmm0
; AVX-NEXT: vsubsd %xmm0, %xmm2, %xmm0
; AVX-NEXT: retq
entry:
%sub = call double @llvm.experimental.constrained.fsub.f64(
double -0.000000e+00, double %a,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
%mul = call double @llvm.experimental.constrained.fmul.f64(
double %sub, double %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
%ret = call double @llvm.experimental.constrained.fsub.f64(
double -0.000000e+00,
double %mul,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %ret
}
; Verify that FP operations are not performed speculatively when FP exceptions
; are not being ignored.
;
; double f4(int n, double a) {
; // Because a + 1 may overflow, this should not be simplified.
; if (n > 0)
; return a + 1.0;
; return a;
; }
;
;
define double @f4(i32 %n, double %a) #0 {
; X87-LABEL: f4:
; X87: # %bb.0: # %entry
; X87-NEXT: fldl {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: cmpl $0, {{[0-9]+}}(%esp)
; X87-NEXT: jle .LBB3_2
; X87-NEXT: # %bb.1: # %if.then
; X87-NEXT: fld1
; X87-NEXT: faddp %st, %st(1)
; X87-NEXT: wait
; X87-NEXT: .LBB3_2: # %if.end
; X87-NEXT: retl
;
; X86-SSE-LABEL: f4:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: cmpl $0, {{[0-9]+}}(%esp)
; X86-SSE-NEXT: jle .LBB3_2
; X86-SSE-NEXT: # %bb.1: # %if.then
; X86-SSE-NEXT: addsd {{\.LCPI.*}}, %xmm0
; X86-SSE-NEXT: .LBB3_2: # %if.end
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: fldl (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f4:
; SSE: # %bb.0: # %entry
; SSE-NEXT: testl %edi, %edi
; SSE-NEXT: jle .LBB3_2
; SSE-NEXT: # %bb.1: # %if.then
; SSE-NEXT: addsd {{.*}}(%rip), %xmm0
; SSE-NEXT: .LBB3_2: # %if.end
; SSE-NEXT: retq
;
; AVX-LABEL: f4:
; AVX: # %bb.0: # %entry
; AVX-NEXT: testl %edi, %edi
; AVX-NEXT: jle .LBB3_2
; AVX-NEXT: # %bb.1: # %if.then
; AVX-NEXT: vaddsd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: .LBB3_2: # %if.end
; AVX-NEXT: retq
entry:
%cmp = icmp sgt i32 %n, 0
br i1 %cmp, label %if.then, label %if.end
if.then:
%add = call double @llvm.experimental.constrained.fadd.f64(
double 1.000000e+00, double %a,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
br label %if.end
if.end:
%a.0 = phi double [%add, %if.then], [ %a, %entry ]
ret double %a.0
}
; Verify that sqrt(42.0) isn't simplified when the rounding mode is unknown.
define double @f5() #0 {
; X87-LABEL: f5:
; X87: # %bb.0: # %entry
; X87-NEXT: flds {{\.LCPI.*}}
; X87-NEXT: fsqrt
; X87-NEXT: wait
; X87-NEXT: retl
;
; X86-SSE-LABEL: f5:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: sqrtsd %xmm0, %xmm0
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: fldl (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f5:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT: sqrtsd %xmm0, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: f5:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT: vsqrtsd %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.sqrt.f64(double 42.0,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
; Verify that pow(42.1, 3.0) isn't simplified when the rounding mode is unknown.
define double @f6() #0 {
; X87-LABEL: f6:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $28, %esp
; X87-NEXT: .cfi_def_cfa_offset 32
; X87-NEXT: flds {{\.LCPI.*}}
; X87-NEXT: fstpl {{[0-9]+}}(%esp)
; X87-NEXT: fldl {{\.LCPI.*}}
; X87-NEXT: fstpl (%esp)
; X87-NEXT: wait
; X87-NEXT: calll pow
; X87-NEXT: addl $28, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f6:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $28, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 32
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, {{[0-9]+}}(%esp)
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: calll pow
; X86-SSE-NEXT: addl $28, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f6:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
; SSE-NEXT: callq pow
; SSE-NEXT: popq %rax
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f6:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT: callq pow
; AVX-NEXT: popq %rax
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.pow.f64(double 42.1,
double 3.0,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
; Verify that powi(42.1, 3) isn't simplified when the rounding mode is unknown.
define double @f7() #0 {
; X87-LABEL: f7:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: fldl {{\.LCPI.*}}
; X87-NEXT: fstpl (%esp)
; X87-NEXT: wait
; X87-NEXT: movl $3, {{[0-9]+}}(%esp)
; X87-NEXT: calll __powidf2
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f7:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: movl $3, {{[0-9]+}}(%esp)
; X86-SSE-NEXT: calll __powidf2
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f7:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT: movl $3, %edi
; SSE-NEXT: callq __powidf2
; SSE-NEXT: popq %rax
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f7:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT: movl $3, %edi
; AVX-NEXT: callq __powidf2
; AVX-NEXT: popq %rax
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.powi.f64(double 42.1,
i32 3,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
; Verify that sin(42.0) isn't simplified when the rounding mode is unknown.
define double @f8() #0 {
; X87-LABEL: f8:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: flds {{\.LCPI.*}}
; X87-NEXT: fstpl (%esp)
; X87-NEXT: wait
; X87-NEXT: calll sin
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f8:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: calll sin
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f8:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT: callq sin
; SSE-NEXT: popq %rax
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f8:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT: callq sin
; AVX-NEXT: popq %rax
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.sin.f64(double 42.0,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
; Verify that cos(42.0) isn't simplified when the rounding mode is unknown.
define double @f9() #0 {
; X87-LABEL: f9:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: flds {{\.LCPI.*}}
; X87-NEXT: fstpl (%esp)
; X87-NEXT: wait
; X87-NEXT: calll cos
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f9:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: calll cos
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f9:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT: callq cos
; SSE-NEXT: popq %rax
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f9:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT: callq cos
; AVX-NEXT: popq %rax
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.cos.f64(double 42.0,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
; Verify that exp(42.0) isn't simplified when the rounding mode is unknown.
define double @f10() #0 {
; X87-LABEL: f10:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: flds {{\.LCPI.*}}
; X87-NEXT: fstpl (%esp)
; X87-NEXT: wait
; X87-NEXT: calll exp
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f10:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: calll exp
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f10:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT: callq exp
; SSE-NEXT: popq %rax
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f10:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT: callq exp
; AVX-NEXT: popq %rax
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.exp.f64(double 42.0,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
; Verify that exp2(42.1) isn't simplified when the rounding mode is unknown.
define double @f11() #0 {
; X87-LABEL: f11:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: fldl {{\.LCPI.*}}
; X87-NEXT: fstpl (%esp)
; X87-NEXT: wait
; X87-NEXT: calll exp2
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f11:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: calll exp2
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f11:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT: callq exp2
; SSE-NEXT: popq %rax
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f11:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT: callq exp2
; AVX-NEXT: popq %rax
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.exp2.f64(double 42.1,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
; Verify that log(42.0) isn't simplified when the rounding mode is unknown.
define double @f12() #0 {
; X87-LABEL: f12:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: flds {{\.LCPI.*}}
; X87-NEXT: fstpl (%esp)
; X87-NEXT: wait
; X87-NEXT: calll log
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f12:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: calll log
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f12:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT: callq log
; SSE-NEXT: popq %rax
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f12:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT: callq log
; AVX-NEXT: popq %rax
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.log.f64(double 42.0,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
; Verify that log10(42.0) isn't simplified when the rounding mode is unknown.
define double @f13() #0 {
; X87-LABEL: f13:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: flds {{\.LCPI.*}}
; X87-NEXT: fstpl (%esp)
; X87-NEXT: wait
; X87-NEXT: calll log10
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f13:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: calll log10
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f13:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT: callq log10
; SSE-NEXT: popq %rax
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f13:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT: callq log10
; AVX-NEXT: popq %rax
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.log10.f64(double 42.0,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
; Verify that log2(42.0) isn't simplified when the rounding mode is unknown.
define double @f14() #0 {
; X87-LABEL: f14:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: flds {{\.LCPI.*}}
; X87-NEXT: fstpl (%esp)
; X87-NEXT: wait
; X87-NEXT: calll log2
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f14:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: calll log2
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f14:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT: callq log2
; SSE-NEXT: popq %rax
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f14:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT: callq log2
; AVX-NEXT: popq %rax
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.log2.f64(double 42.0,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
; Verify that rint(42.1) isn't simplified when the rounding mode is unknown.
define double @f15() #0 {
; X87-LABEL: f15:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: fldl {{\.LCPI.*}}
; X87-NEXT: fstpl (%esp)
; X87-NEXT: wait
; X87-NEXT: calll rint
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f15:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: calll rint
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f15:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT: callq rint
; SSE-NEXT: popq %rax
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f15:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT: vroundsd $4, %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.rint.f64(double 42.1,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
; Verify that nearbyint(42.1) isn't simplified when the rounding mode is
; unknown.
define double @f16() #0 {
; X87-LABEL: f16:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: fldl {{\.LCPI.*}}
; X87-NEXT: fstpl (%esp)
; X87-NEXT: wait
; X87-NEXT: calll nearbyint
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f16:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: calll nearbyint
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f16:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT: callq nearbyint
; SSE-NEXT: popq %rax
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f16:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT: vroundsd $12, %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.nearbyint.f64(
double 42.1,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
define double @f19() #0 {
; X87-LABEL: f19:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $28, %esp
; X87-NEXT: .cfi_def_cfa_offset 32
; X87-NEXT: flds {{\.LCPI.*}}
; X87-NEXT: fstpl {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: movl $1072693248, {{[0-9]+}}(%esp) # imm = 0x3FF00000
; X87-NEXT: movl $0, (%esp)
; X87-NEXT: calll fmod
; X87-NEXT: addl $28, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f19:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $28, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 32
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, {{[0-9]+}}(%esp)
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: calll fmod
; X86-SSE-NEXT: addl $28, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f19:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
; SSE-NEXT: callq fmod
; SSE-NEXT: popq %rax
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f19:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT: callq fmod
; AVX-NEXT: popq %rax
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%rem = call double @llvm.experimental.constrained.frem.f64(
double 1.000000e+00,
double 1.000000e+01,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %rem
}
; Verify that fptosi(%x) isn't simplified when the rounding mode is
; unknown.
; Verify that no gross errors happen.
; FIXME: The SSE/AVX code does not raise an invalid exception for all values
; that don't fit in i8.
define i8 @f20s8(double %x) #0 {
; X87-LABEL: f20s8:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $8, %esp
; X87-NEXT: .cfi_def_cfa_offset 12
; X87-NEXT: fldl {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: fnstcw {{[0-9]+}}(%esp)
; X87-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X87-NEXT: orl $3072, %eax # imm = 0xC00
; X87-NEXT: movw %ax, {{[0-9]+}}(%esp)
; X87-NEXT: fldcw {{[0-9]+}}(%esp)
; X87-NEXT: fistps {{[0-9]+}}(%esp)
; X87-NEXT: fldcw {{[0-9]+}}(%esp)
; X87-NEXT: movb {{[0-9]+}}(%esp), %al
; X87-NEXT: addl $8, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f20s8:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: cvttsd2si {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: # kill: def $al killed $al killed $eax
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f20s8:
; SSE: # %bb.0: # %entry
; SSE-NEXT: cvttsd2si %xmm0, %eax
; SSE-NEXT: # kill: def $al killed $al killed $eax
; SSE-NEXT: retq
;
; AVX-LABEL: f20s8:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vcvttsd2si %xmm0, %eax
; AVX-NEXT: # kill: def $al killed $al killed $eax
; AVX-NEXT: retq
entry:
%result = call i8 @llvm.experimental.constrained.fptosi.i8.f64(double %x,
metadata !"fpexcept.strict") #0
ret i8 %result
}
; Verify that fptosi(%x) isn't simplified when the rounding mode is
; unknown.
; Verify that no gross errors happen.
; FIXME: The SSE/AVX code does not raise an invalid exception for all values
; that don't fit in i16.
define i16 @f20s16(double %x) #0 {
; X87-LABEL: f20s16:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $8, %esp
; X87-NEXT: .cfi_def_cfa_offset 12
; X87-NEXT: fldl {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: fnstcw {{[0-9]+}}(%esp)
; X87-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X87-NEXT: orl $3072, %eax # imm = 0xC00
; X87-NEXT: movw %ax, {{[0-9]+}}(%esp)
; X87-NEXT: fldcw {{[0-9]+}}(%esp)
; X87-NEXT: fistps {{[0-9]+}}(%esp)
; X87-NEXT: fldcw {{[0-9]+}}(%esp)
; X87-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X87-NEXT: addl $8, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f20s16:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: cvttsd2si {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: # kill: def $ax killed $ax killed $eax
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f20s16:
; SSE: # %bb.0: # %entry
; SSE-NEXT: cvttsd2si %xmm0, %eax
; SSE-NEXT: # kill: def $ax killed $ax killed $eax
; SSE-NEXT: retq
;
; AVX-LABEL: f20s16:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vcvttsd2si %xmm0, %eax
; AVX-NEXT: # kill: def $ax killed $ax killed $eax
; AVX-NEXT: retq
entry:
%result = call i16 @llvm.experimental.constrained.fptosi.i16.f64(double %x,
metadata !"fpexcept.strict") #0
ret i16 %result
}
; Verify that fptosi(%x) isn't simplified when the rounding mode is
; unknown.
; Verify that no gross errors happen.
define i32 @f20s(double %x) #0 {
; X87-LABEL: f20s:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $8, %esp
; X87-NEXT: .cfi_def_cfa_offset 12
; X87-NEXT: fldl {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: fnstcw (%esp)
; X87-NEXT: movzwl (%esp), %eax
; X87-NEXT: orl $3072, %eax # imm = 0xC00
; X87-NEXT: movw %ax, {{[0-9]+}}(%esp)
; X87-NEXT: fldcw {{[0-9]+}}(%esp)
; X87-NEXT: fistpl {{[0-9]+}}(%esp)
; X87-NEXT: fldcw (%esp)
; X87-NEXT: movl {{[0-9]+}}(%esp), %eax
; X87-NEXT: addl $8, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f20s:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: cvttsd2si {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f20s:
; SSE: # %bb.0: # %entry
; SSE-NEXT: cvttsd2si %xmm0, %eax
; SSE-NEXT: retq
;
; AVX-LABEL: f20s:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vcvttsd2si %xmm0, %eax
; AVX-NEXT: retq
entry:
%result = call i32 @llvm.experimental.constrained.fptosi.i32.f64(double %x,
metadata !"fpexcept.strict") #0
ret i32 %result
}
; Verify that fptoui(%x) isn't simplified when the rounding mode is
; unknown.
; Verify that no gross errors happen.
; FIXME: This code generates spurious inexact exceptions.
define i64 @f20s64(double %x) #0 {
; X87-LABEL: f20s64:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $20, %esp
; X87-NEXT: .cfi_def_cfa_offset 24
; X87-NEXT: fldl {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: fnstcw {{[0-9]+}}(%esp)
; X87-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X87-NEXT: orl $3072, %eax # imm = 0xC00
; X87-NEXT: movw %ax, {{[0-9]+}}(%esp)
; X87-NEXT: fldcw {{[0-9]+}}(%esp)
; X87-NEXT: fistpll {{[0-9]+}}(%esp)
; X87-NEXT: fldcw {{[0-9]+}}(%esp)
; X87-NEXT: movl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movl {{[0-9]+}}(%esp), %edx
; X87-NEXT: addl $20, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f20s64:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $20, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 24
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, {{[0-9]+}}(%esp)
; X86-SSE-NEXT: fldl {{[0-9]+}}(%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: fnstcw {{[0-9]+}}(%esp)
; X86-SSE-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: orl $3072, %eax # imm = 0xC00
; X86-SSE-NEXT: movw %ax, {{[0-9]+}}(%esp)
; X86-SSE-NEXT: fldcw {{[0-9]+}}(%esp)
; X86-SSE-NEXT: fistpll {{[0-9]+}}(%esp)
; X86-SSE-NEXT: fldcw {{[0-9]+}}(%esp)
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-SSE-NEXT: addl $20, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f20s64:
; SSE: # %bb.0: # %entry
; SSE-NEXT: cvttsd2si %xmm0, %rax
; SSE-NEXT: retq
;
; AVX-LABEL: f20s64:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vcvttsd2si %xmm0, %rax
; AVX-NEXT: retq
entry:
%result = call i64 @llvm.experimental.constrained.fptosi.i64.f64(double %x,
metadata !"fpexcept.strict") #0
ret i64 %result
}
; Verify that fptoui(%x) isn't simplified when the rounding mode is
; unknown.
; Verify that no gross errors happen.
define i128 @f20s128(double %x) nounwind strictfp {
; X87-LABEL: f20s128:
; X87: # %bb.0: # %entry
; X87-NEXT: pushl %edi
; X87-NEXT: pushl %esi
; X87-NEXT: subl $36, %esp
; X87-NEXT: movl {{[0-9]+}}(%esp), %esi
; X87-NEXT: fldl {{[0-9]+}}(%esp)
; X87-NEXT: fstpl {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: leal {{[0-9]+}}(%esp), %eax
; X87-NEXT: movl %eax, (%esp)
; X87-NEXT: calll __fixdfti
; X87-NEXT: subl $4, %esp
; X87-NEXT: movl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X87-NEXT: movl {{[0-9]+}}(%esp), %edx
; X87-NEXT: movl {{[0-9]+}}(%esp), %edi
; X87-NEXT: movl %edi, 8(%esi)
; X87-NEXT: movl %edx, 12(%esi)
; X87-NEXT: movl %eax, (%esi)
; X87-NEXT: movl %ecx, 4(%esi)
; X87-NEXT: movl %esi, %eax
; X87-NEXT: addl $36, %esp
; X87-NEXT: popl %esi
; X87-NEXT: popl %edi
; X87-NEXT: retl $4
;
; X86-SSE-LABEL: f20s128:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: pushl %edi
; X86-SSE-NEXT: pushl %esi
; X86-SSE-NEXT: subl $36, %esp
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, {{[0-9]+}}(%esp)
; X86-SSE-NEXT: leal {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: movl %eax, (%esp)
; X86-SSE-NEXT: calll __fixdfti
; X86-SSE-NEXT: subl $4, %esp
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %edi
; X86-SSE-NEXT: movl %edi, 8(%esi)
; X86-SSE-NEXT: movl %edx, 12(%esi)
; X86-SSE-NEXT: movl %eax, (%esi)
; X86-SSE-NEXT: movl %ecx, 4(%esi)
; X86-SSE-NEXT: movl %esi, %eax
; X86-SSE-NEXT: addl $36, %esp
; X86-SSE-NEXT: popl %esi
; X86-SSE-NEXT: popl %edi
; X86-SSE-NEXT: retl $4
;
; SSE-LABEL: f20s128:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: callq __fixdfti
; SSE-NEXT: popq %rcx
; SSE-NEXT: retq
;
; AVX-LABEL: f20s128:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: callq __fixdfti
; AVX-NEXT: popq %rcx
; AVX-NEXT: retq
entry:
%result = call i128 @llvm.experimental.constrained.fptosi.i128.f64(double %x,
metadata !"fpexcept.strict") #0
ret i128 %result
}
; Verify that fptoui(%x) isn't simplified when the rounding mode is
; unknown.
; Verify that no gross errors happen.
; FIXME: The SSE/AVX code does not raise an invalid exception for all values
; that don't fit in i8.
define i8 @f20u8(double %x) #0 {
; X87-LABEL: f20u8:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $8, %esp
; X87-NEXT: .cfi_def_cfa_offset 12
; X87-NEXT: fldl {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: fnstcw {{[0-9]+}}(%esp)
; X87-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X87-NEXT: orl $3072, %eax # imm = 0xC00
; X87-NEXT: movw %ax, {{[0-9]+}}(%esp)
; X87-NEXT: fldcw {{[0-9]+}}(%esp)
; X87-NEXT: fistps {{[0-9]+}}(%esp)
; X87-NEXT: fldcw {{[0-9]+}}(%esp)
; X87-NEXT: movb {{[0-9]+}}(%esp), %al
; X87-NEXT: addl $8, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f20u8:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: cvttsd2si {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: # kill: def $al killed $al killed $eax
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f20u8:
; SSE: # %bb.0: # %entry
; SSE-NEXT: cvttsd2si %xmm0, %eax
; SSE-NEXT: # kill: def $al killed $al killed $eax
; SSE-NEXT: retq
;
; AVX-LABEL: f20u8:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vcvttsd2si %xmm0, %eax
; AVX-NEXT: # kill: def $al killed $al killed $eax
; AVX-NEXT: retq
entry:
%result = call i8 @llvm.experimental.constrained.fptoui.i8.f64(double %x,
metadata !"fpexcept.strict") #0
ret i8 %result
}
; Verify that fptoui(%x) isn't simplified when the rounding mode is
; unknown.
; Verify that no gross errors happen.
; FIXME: The SSE/AVX code does not raise an invalid exception for all values
; that don't fit in i16.
define i16 @f20u16(double %x) #0 {
; X87-LABEL: f20u16:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $8, %esp
; X87-NEXT: .cfi_def_cfa_offset 12
; X87-NEXT: fldl {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: fnstcw (%esp)
; X87-NEXT: movzwl (%esp), %eax
; X87-NEXT: orl $3072, %eax # imm = 0xC00
; X87-NEXT: movw %ax, {{[0-9]+}}(%esp)
; X87-NEXT: fldcw {{[0-9]+}}(%esp)
; X87-NEXT: fistpl {{[0-9]+}}(%esp)
; X87-NEXT: fldcw (%esp)
; X87-NEXT: movl {{[0-9]+}}(%esp), %eax
; X87-NEXT: # kill: def $ax killed $ax killed $eax
; X87-NEXT: addl $8, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f20u16:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: cvttsd2si {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: # kill: def $ax killed $ax killed $eax
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f20u16:
; SSE: # %bb.0: # %entry
; SSE-NEXT: cvttsd2si %xmm0, %eax
; SSE-NEXT: # kill: def $ax killed $ax killed $eax
; SSE-NEXT: retq
;
; AVX-LABEL: f20u16:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vcvttsd2si %xmm0, %eax
; AVX-NEXT: # kill: def $ax killed $ax killed $eax
; AVX-NEXT: retq
entry:
%result = call i16 @llvm.experimental.constrained.fptoui.i16.f64(double %x,
metadata !"fpexcept.strict") #0
ret i16 %result
}
; Verify that fptoui(%x) isn't simplified when the rounding mode is
; unknown.
; Verify that no gross errors happen.
; FIXME: The X87/SSE/AVX1 code does not raise an invalid exception for all
; values that don't fit in i32. The AVX512 code does.
define i32 @f20u(double %x) #0 {
; X87-LABEL: f20u:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $20, %esp
; X87-NEXT: .cfi_def_cfa_offset 24
; X87-NEXT: fldl {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: fnstcw {{[0-9]+}}(%esp)
; X87-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X87-NEXT: orl $3072, %eax # imm = 0xC00
; X87-NEXT: movw %ax, {{[0-9]+}}(%esp)
; X87-NEXT: fldcw {{[0-9]+}}(%esp)
; X87-NEXT: fistpll {{[0-9]+}}(%esp)
; X87-NEXT: fldcw {{[0-9]+}}(%esp)
; X87-NEXT: movl {{[0-9]+}}(%esp), %eax
; X87-NEXT: addl $20, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f20u:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd {{.*#+}} xmm2 = mem[0],zero
; X86-SSE-NEXT: comisd %xmm0, %xmm2
; X86-SSE-NEXT: xorpd %xmm1, %xmm1
; X86-SSE-NEXT: ja .LBB24_2
; X86-SSE-NEXT: # %bb.1: # %entry
; X86-SSE-NEXT: movapd %xmm2, %xmm1
; X86-SSE-NEXT: .LBB24_2: # %entry
; X86-SSE-NEXT: setbe %al
; X86-SSE-NEXT: movzbl %al, %ecx
; X86-SSE-NEXT: shll $31, %ecx
; X86-SSE-NEXT: subsd %xmm1, %xmm0
; X86-SSE-NEXT: cvttsd2si %xmm0, %eax
; X86-SSE-NEXT: xorl %ecx, %eax
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f20u:
; SSE: # %bb.0: # %entry
; SSE-NEXT: cvttsd2si %xmm0, %rax
; SSE-NEXT: # kill: def $eax killed $eax killed $rax
; SSE-NEXT: retq
;
; AVX1-LABEL: f20u:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vcvttsd2si %xmm0, %rax
; AVX1-NEXT: # kill: def $eax killed $eax killed $rax
; AVX1-NEXT: retq
;
; AVX512-LABEL: f20u:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vcvttsd2usi %xmm0, %eax
; AVX512-NEXT: retq
entry:
%result = call i32 @llvm.experimental.constrained.fptoui.i32.f64(double %x,
metadata !"fpexcept.strict") #0
ret i32 %result
}
; Verify that fptoui(%x) isn't simplified when the rounding mode is
; unknown.
; Verify that no gross errors happen.
; FIXME: This code generates spurious inexact exceptions.
define i64 @f20u64(double %x) #0 {
; X87-LABEL: f20u64:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $20, %esp
; X87-NEXT: .cfi_def_cfa_offset 24
; X87-NEXT: fldl {{[0-9]+}}(%esp)
; X87-NEXT: flds {{\.LCPI.*}}
; X87-NEXT: wait
; X87-NEXT: xorl %edx, %edx
; X87-NEXT: fcomi %st(1), %st
; X87-NEXT: wait
; X87-NEXT: setbe %dl
; X87-NEXT: fldz
; X87-NEXT: fcmovbe %st(1), %st
; X87-NEXT: fstp %st(1)
; X87-NEXT: fsubrp %st, %st(1)
; X87-NEXT: wait
; X87-NEXT: fnstcw {{[0-9]+}}(%esp)
; X87-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X87-NEXT: orl $3072, %eax # imm = 0xC00
; X87-NEXT: movw %ax, {{[0-9]+}}(%esp)
; X87-NEXT: fldcw {{[0-9]+}}(%esp)
; X87-NEXT: fistpll {{[0-9]+}}(%esp)
; X87-NEXT: fldcw {{[0-9]+}}(%esp)
; X87-NEXT: shll $31, %edx
; X87-NEXT: xorl {{[0-9]+}}(%esp), %edx
; X87-NEXT: movl {{[0-9]+}}(%esp), %eax
; X87-NEXT: addl $20, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f20u64:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $20, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 24
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
; X86-SSE-NEXT: comisd %xmm0, %xmm1
; X86-SSE-NEXT: jbe .LBB25_2
; X86-SSE-NEXT: # %bb.1: # %entry
; X86-SSE-NEXT: xorpd %xmm1, %xmm1
; X86-SSE-NEXT: .LBB25_2: # %entry
; X86-SSE-NEXT: subsd %xmm1, %xmm0
; X86-SSE-NEXT: movsd %xmm0, {{[0-9]+}}(%esp)
; X86-SSE-NEXT: setbe %al
; X86-SSE-NEXT: fldl {{[0-9]+}}(%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: fnstcw {{[0-9]+}}(%esp)
; X86-SSE-NEXT: movzwl {{[0-9]+}}(%esp), %ecx
; X86-SSE-NEXT: orl $3072, %ecx # imm = 0xC00
; X86-SSE-NEXT: movw %cx, {{[0-9]+}}(%esp)
; X86-SSE-NEXT: fldcw {{[0-9]+}}(%esp)
; X86-SSE-NEXT: fistpll {{[0-9]+}}(%esp)
; X86-SSE-NEXT: fldcw {{[0-9]+}}(%esp)
; X86-SSE-NEXT: movzbl %al, %edx
; X86-SSE-NEXT: shll $31, %edx
; X86-SSE-NEXT: xorl {{[0-9]+}}(%esp), %edx
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: addl $20, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f20u64:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movsd {{.*#+}} xmm2 = mem[0],zero
; SSE-NEXT: comisd %xmm2, %xmm0
; SSE-NEXT: xorpd %xmm1, %xmm1
; SSE-NEXT: jb .LBB25_2
; SSE-NEXT: # %bb.1: # %entry
; SSE-NEXT: movapd %xmm2, %xmm1
; SSE-NEXT: .LBB25_2: # %entry
; SSE-NEXT: subsd %xmm1, %xmm0
; SSE-NEXT: cvttsd2si %xmm0, %rcx
; SSE-NEXT: setae %al
; SSE-NEXT: movzbl %al, %eax
; SSE-NEXT: shlq $63, %rax
; SSE-NEXT: xorq %rcx, %rax
; SSE-NEXT: retq
;
; AVX1-LABEL: f20u64:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX1-NEXT: vcomisd %xmm1, %xmm0
; AVX1-NEXT: vxorpd %xmm2, %xmm2, %xmm2
; AVX1-NEXT: jb .LBB25_2
; AVX1-NEXT: # %bb.1: # %entry
; AVX1-NEXT: vmovapd %xmm1, %xmm2
; AVX1-NEXT: .LBB25_2: # %entry
; AVX1-NEXT: vsubsd %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vcvttsd2si %xmm0, %rcx
; AVX1-NEXT: setae %al
; AVX1-NEXT: movzbl %al, %eax
; AVX1-NEXT: shlq $63, %rax
; AVX1-NEXT: xorq %rcx, %rax
; AVX1-NEXT: retq
;
; AVX512-LABEL: f20u64:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vcvttsd2usi %xmm0, %rax
; AVX512-NEXT: retq
entry:
%result = call i64 @llvm.experimental.constrained.fptoui.i64.f64(double %x,
metadata !"fpexcept.strict") #0
ret i64 %result
}
; Verify that fptoui(%x) isn't simplified when the rounding mode is
; unknown.
; Verify that no gross errors happen.
define i128 @f20u128(double %x) nounwind strictfp {
; X87-LABEL: f20u128:
; X87: # %bb.0: # %entry
; X87-NEXT: pushl %edi
; X87-NEXT: pushl %esi
; X87-NEXT: subl $36, %esp
; X87-NEXT: movl {{[0-9]+}}(%esp), %esi
; X87-NEXT: fldl {{[0-9]+}}(%esp)
; X87-NEXT: fstpl {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: leal {{[0-9]+}}(%esp), %eax
; X87-NEXT: movl %eax, (%esp)
; X87-NEXT: calll __fixunsdfti
; X87-NEXT: subl $4, %esp
; X87-NEXT: movl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X87-NEXT: movl {{[0-9]+}}(%esp), %edx
; X87-NEXT: movl {{[0-9]+}}(%esp), %edi
; X87-NEXT: movl %edi, 8(%esi)
; X87-NEXT: movl %edx, 12(%esi)
; X87-NEXT: movl %eax, (%esi)
; X87-NEXT: movl %ecx, 4(%esi)
; X87-NEXT: movl %esi, %eax
; X87-NEXT: addl $36, %esp
; X87-NEXT: popl %esi
; X87-NEXT: popl %edi
; X87-NEXT: retl $4
;
; X86-SSE-LABEL: f20u128:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: pushl %edi
; X86-SSE-NEXT: pushl %esi
; X86-SSE-NEXT: subl $36, %esp
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, {{[0-9]+}}(%esp)
; X86-SSE-NEXT: leal {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: movl %eax, (%esp)
; X86-SSE-NEXT: calll __fixunsdfti
; X86-SSE-NEXT: subl $4, %esp
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %edi
; X86-SSE-NEXT: movl %edi, 8(%esi)
; X86-SSE-NEXT: movl %edx, 12(%esi)
; X86-SSE-NEXT: movl %eax, (%esi)
; X86-SSE-NEXT: movl %ecx, 4(%esi)
; X86-SSE-NEXT: movl %esi, %eax
; X86-SSE-NEXT: addl $36, %esp
; X86-SSE-NEXT: popl %esi
; X86-SSE-NEXT: popl %edi
; X86-SSE-NEXT: retl $4
;
; SSE-LABEL: f20u128:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: callq __fixunsdfti
; SSE-NEXT: popq %rcx
; SSE-NEXT: retq
;
; AVX-LABEL: f20u128:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: callq __fixunsdfti
; AVX-NEXT: popq %rcx
; AVX-NEXT: retq
entry:
%result = call i128 @llvm.experimental.constrained.fptoui.i128.f64(double %x,
metadata !"fpexcept.strict") #0
ret i128 %result
}
; Verify that round(42.1) isn't simplified when the rounding mode is
; unknown.
; Verify that no gross errors happen.
define float @f21() #0 {
; X87-LABEL: f21:
; X87: # %bb.0: # %entry
; X87-NEXT: pushl %eax
; X87-NEXT: .cfi_def_cfa_offset 8
; X87-NEXT: fldl {{\.LCPI.*}}
; X87-NEXT: fstps (%esp)
; X87-NEXT: flds (%esp)
; X87-NEXT: wait
; X87-NEXT: popl %eax
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f21:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: pushl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 8
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: cvtsd2ss %xmm0, %xmm0
; X86-SSE-NEXT: movss %xmm0, (%esp)
; X86-SSE-NEXT: flds (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: popl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f21:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE-NEXT: cvtsd2ss %xmm0, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: f21:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT: vcvtsd2ss %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call float @llvm.experimental.constrained.fptrunc.f32.f64(
double 42.1,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret float %result
}
define double @f22(float %x) #0 {
; X87-LABEL: f22:
; X87: # %bb.0: # %entry
; X87-NEXT: flds {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: retl
;
; X86-SSE-LABEL: f22:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-SSE-NEXT: cvtss2sd %xmm0, %xmm0
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: fldl (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f22:
; SSE: # %bb.0: # %entry
; SSE-NEXT: cvtss2sd %xmm0, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: f22:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vcvtss2sd %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.fpext.f64.f32(float %x,
metadata !"fpexcept.strict") #0
ret double %result
}
define i32 @f23(double %x) #0 {
; X87-LABEL: f23:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: fldl {{[0-9]+}}(%esp)
; X87-NEXT: fstpl (%esp)
; X87-NEXT: wait
; X87-NEXT: calll lrint
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f23:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: calll lrint
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f23:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: callq lrint
; SSE-NEXT: popq %rcx
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f23:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: callq lrint
; AVX-NEXT: popq %rcx
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call i32 @llvm.experimental.constrained.lrint.i32.f64(double %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret i32 %result
}
define i32 @f24(float %x) #0 {
; X87-LABEL: f24:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: flds {{[0-9]+}}(%esp)
; X87-NEXT: fstps (%esp)
; X87-NEXT: wait
; X87-NEXT: calll lrintf
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f24:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-SSE-NEXT: movss %xmm0, (%esp)
; X86-SSE-NEXT: calll lrintf
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f24:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: callq lrintf
; SSE-NEXT: popq %rcx
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f24:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: callq lrintf
; AVX-NEXT: popq %rcx
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call i32 @llvm.experimental.constrained.lrint.i32.f32(float %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret i32 %result
}
define i64 @f25(double %x) #0 {
; X87-LABEL: f25:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: fldl {{[0-9]+}}(%esp)
; X87-NEXT: fstpl (%esp)
; X87-NEXT: wait
; X87-NEXT: calll llrint
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f25:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: calll llrint
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f25:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: callq llrint
; SSE-NEXT: popq %rcx
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f25:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: callq llrint
; AVX-NEXT: popq %rcx
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call i64 @llvm.experimental.constrained.llrint.i64.f64(double %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret i64 %result
}
define i64 @f26(float %x) #0 {
; X87-LABEL: f26:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: flds {{[0-9]+}}(%esp)
; X87-NEXT: fstps (%esp)
; X87-NEXT: wait
; X87-NEXT: calll llrintf
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f26:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-SSE-NEXT: movss %xmm0, (%esp)
; X86-SSE-NEXT: calll llrintf
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f26:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: callq llrintf
; SSE-NEXT: popq %rcx
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f26:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: callq llrintf
; AVX-NEXT: popq %rcx
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call i64 @llvm.experimental.constrained.llrint.i64.f32(float %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret i64 %result
}
define i32 @f27(double %x) #0 {
; X87-LABEL: f27:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: fldl {{[0-9]+}}(%esp)
; X87-NEXT: fstpl (%esp)
; X87-NEXT: wait
; X87-NEXT: calll lround
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f27:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: calll lround
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f27:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: callq lround
; SSE-NEXT: popq %rcx
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f27:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: callq lround
; AVX-NEXT: popq %rcx
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call i32 @llvm.experimental.constrained.lround.i32.f64(double %x,
metadata !"fpexcept.strict") #0
ret i32 %result
}
define i32 @f28(float %x) #0 {
; X87-LABEL: f28:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: flds {{[0-9]+}}(%esp)
; X87-NEXT: fstps (%esp)
; X87-NEXT: wait
; X87-NEXT: calll lroundf
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f28:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-SSE-NEXT: movss %xmm0, (%esp)
; X86-SSE-NEXT: calll lroundf
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f28:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: callq lroundf
; SSE-NEXT: popq %rcx
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f28:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: callq lroundf
; AVX-NEXT: popq %rcx
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call i32 @llvm.experimental.constrained.lround.i32.f32(float %x,
metadata !"fpexcept.strict") #0
ret i32 %result
}
define i64 @f29(double %x) #0 {
; X87-LABEL: f29:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: fldl {{[0-9]+}}(%esp)
; X87-NEXT: fstpl (%esp)
; X87-NEXT: wait
; X87-NEXT: calll llround
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f29:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: calll llround
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f29:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: callq llround
; SSE-NEXT: popq %rcx
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f29:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: callq llround
; AVX-NEXT: popq %rcx
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call i64 @llvm.experimental.constrained.llround.i64.f64(double %x,
metadata !"fpexcept.strict") #0
ret i64 %result
}
define i64 @f30(float %x) #0 {
; X87-LABEL: f30:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: flds {{[0-9]+}}(%esp)
; X87-NEXT: fstps (%esp)
; X87-NEXT: wait
; X87-NEXT: calll llroundf
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: f30:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-SSE-NEXT: movss %xmm0, (%esp)
; X86-SSE-NEXT: calll llroundf
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: f30:
; SSE: # %bb.0: # %entry
; SSE-NEXT: pushq %rax
; SSE-NEXT: .cfi_def_cfa_offset 16
; SSE-NEXT: callq llroundf
; SSE-NEXT: popq %rcx
; SSE-NEXT: .cfi_def_cfa_offset 8
; SSE-NEXT: retq
;
; AVX-LABEL: f30:
; AVX: # %bb.0: # %entry
; AVX-NEXT: pushq %rax
; AVX-NEXT: .cfi_def_cfa_offset 16
; AVX-NEXT: callq llroundf
; AVX-NEXT: popq %rcx
; AVX-NEXT: .cfi_def_cfa_offset 8
; AVX-NEXT: retq
entry:
%result = call i64 @llvm.experimental.constrained.llround.i64.f32(float %x,
metadata !"fpexcept.strict") #0
ret i64 %result
}
; Verify that sitofp(%x) isn't simplified when the rounding mode is
; unknown.
; Verify that no gross errors happen.
define double @sifdb(i8 %x) #0 {
; X87-LABEL: sifdb:
; X87: # %bb.0: # %entry
; X87-NEXT: pushl %eax
; X87-NEXT: .cfi_def_cfa_offset 8
; X87-NEXT: movsbl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movw %ax, {{[0-9]+}}(%esp)
; X87-NEXT: filds {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: popl %eax
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: sifdb:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movsbl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: cvtsi2sd %eax, %xmm0
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: fldl (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: sifdb:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movsbl %dil, %eax
; SSE-NEXT: cvtsi2sd %eax, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: sifdb:
; AVX: # %bb.0: # %entry
; AVX-NEXT: movsbl %dil, %eax
; AVX-NEXT: vcvtsi2sd %eax, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.sitofp.f64.i8(i8 %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
define double @sifdw(i16 %x) #0 {
; X87-LABEL: sifdw:
; X87: # %bb.0: # %entry
; X87-NEXT: pushl %eax
; X87-NEXT: .cfi_def_cfa_offset 8
; X87-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movw %ax, {{[0-9]+}}(%esp)
; X87-NEXT: filds {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: popl %eax
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: sifdw:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movswl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: cvtsi2sd %eax, %xmm0
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: fldl (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: sifdw:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movswl %di, %eax
; SSE-NEXT: cvtsi2sd %eax, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: sifdw:
; AVX: # %bb.0: # %entry
; AVX-NEXT: movswl %di, %eax
; AVX-NEXT: vcvtsi2sd %eax, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.sitofp.f64.i16(i16 %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
define double @sifdi(i32 %x) #0 {
; X87-LABEL: sifdi:
; X87: # %bb.0: # %entry
; X87-NEXT: pushl %eax
; X87-NEXT: .cfi_def_cfa_offset 8
; X87-NEXT: movl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movl %eax, (%esp)
; X87-NEXT: fildl (%esp)
; X87-NEXT: wait
; X87-NEXT: popl %eax
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: sifdi:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: cvtsi2sdl {{[0-9]+}}(%esp), %xmm0
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: fldl (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: sifdi:
; SSE: # %bb.0: # %entry
; SSE-NEXT: cvtsi2sd %edi, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: sifdi:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vcvtsi2sd %edi, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.sitofp.f64.i32(i32 %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
define float @siffb(i8 %x) #0 {
; X87-LABEL: siffb:
; X87: # %bb.0: # %entry
; X87-NEXT: pushl %eax
; X87-NEXT: .cfi_def_cfa_offset 8
; X87-NEXT: movsbl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movw %ax, {{[0-9]+}}(%esp)
; X87-NEXT: filds {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: popl %eax
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: siffb:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: pushl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 8
; X86-SSE-NEXT: movsbl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: cvtsi2ss %eax, %xmm0
; X86-SSE-NEXT: movss %xmm0, (%esp)
; X86-SSE-NEXT: flds (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: popl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: siffb:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movsbl %dil, %eax
; SSE-NEXT: cvtsi2ss %eax, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: siffb:
; AVX: # %bb.0: # %entry
; AVX-NEXT: movsbl %dil, %eax
; AVX-NEXT: vcvtsi2ss %eax, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call float @llvm.experimental.constrained.sitofp.f32.i8(i8 %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret float %result
}
define float @siffw(i16 %x) #0 {
; X87-LABEL: siffw:
; X87: # %bb.0: # %entry
; X87-NEXT: pushl %eax
; X87-NEXT: .cfi_def_cfa_offset 8
; X87-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movw %ax, {{[0-9]+}}(%esp)
; X87-NEXT: filds {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: popl %eax
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: siffw:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: pushl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 8
; X86-SSE-NEXT: movswl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: cvtsi2ss %eax, %xmm0
; X86-SSE-NEXT: movss %xmm0, (%esp)
; X86-SSE-NEXT: flds (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: popl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: siffw:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movswl %di, %eax
; SSE-NEXT: cvtsi2ss %eax, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: siffw:
; AVX: # %bb.0: # %entry
; AVX-NEXT: movswl %di, %eax
; AVX-NEXT: vcvtsi2ss %eax, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call float @llvm.experimental.constrained.sitofp.f32.i16(i16 %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret float %result
}
define float @siffi(i32 %x) #0 {
; X87-LABEL: siffi:
; X87: # %bb.0: # %entry
; X87-NEXT: pushl %eax
; X87-NEXT: .cfi_def_cfa_offset 8
; X87-NEXT: movl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movl %eax, (%esp)
; X87-NEXT: fildl (%esp)
; X87-NEXT: wait
; X87-NEXT: popl %eax
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: siffi:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: pushl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 8
; X86-SSE-NEXT: cvtsi2ssl {{[0-9]+}}(%esp), %xmm0
; X86-SSE-NEXT: movss %xmm0, (%esp)
; X86-SSE-NEXT: flds (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: popl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: siffi:
; SSE: # %bb.0: # %entry
; SSE-NEXT: cvtsi2ss %edi, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: siffi:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vcvtsi2ss %edi, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call float @llvm.experimental.constrained.sitofp.f32.i32(i32 %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret float %result
}
define double @sifdl(i64 %x) #0 {
; X87-LABEL: sifdl:
; X87: # %bb.0: # %entry
; X87-NEXT: fildll {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: retl
;
; X86-SSE-LABEL: sifdl:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: fildll {{[0-9]+}}(%esp)
; X86-SSE-NEXT: fstpl (%esp)
; X86-SSE-NEXT: fldl (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: sifdl:
; SSE: # %bb.0: # %entry
; SSE-NEXT: cvtsi2sd %rdi, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: sifdl:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vcvtsi2sd %rdi, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.sitofp.f64.i64(i64 %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
define float @siffl(i64 %x) #0 {
; X87-LABEL: siffl:
; X87: # %bb.0: # %entry
; X87-NEXT: fildll {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: retl
;
; X86-SSE-LABEL: siffl:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: pushl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 8
; X86-SSE-NEXT: fildll {{[0-9]+}}(%esp)
; X86-SSE-NEXT: fstps (%esp)
; X86-SSE-NEXT: flds (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: popl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: siffl:
; SSE: # %bb.0: # %entry
; SSE-NEXT: cvtsi2ss %rdi, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: siffl:
; AVX: # %bb.0: # %entry
; AVX-NEXT: vcvtsi2ss %rdi, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call float @llvm.experimental.constrained.sitofp.f32.i64(i64 %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret float %result
}
; Verify that uitofp(%x) isn't simplified when the rounding mode is
; unknown.
; Verify that no gross errors happen.
define double @uifdb(i8 %x) #0 {
; X87-LABEL: uifdb:
; X87: # %bb.0: # %entry
; X87-NEXT: pushl %eax
; X87-NEXT: .cfi_def_cfa_offset 8
; X87-NEXT: movzbl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movw %ax, {{[0-9]+}}(%esp)
; X87-NEXT: filds {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: popl %eax
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: uifdb:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movzbl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: cvtsi2sd %eax, %xmm0
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: fldl (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: uifdb:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movzbl %dil, %eax
; SSE-NEXT: cvtsi2sd %eax, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: uifdb:
; AVX: # %bb.0: # %entry
; AVX-NEXT: movzbl %dil, %eax
; AVX-NEXT: vcvtsi2sd %eax, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.uitofp.f64.i8(i8 %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
define double @uifdw(i16 %x) #0 {
; X87-LABEL: uifdw:
; X87: # %bb.0: # %entry
; X87-NEXT: pushl %eax
; X87-NEXT: .cfi_def_cfa_offset 8
; X87-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movl %eax, (%esp)
; X87-NEXT: fildl (%esp)
; X87-NEXT: wait
; X87-NEXT: popl %eax
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: uifdw:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: cvtsi2sd %eax, %xmm0
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: fldl (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: uifdw:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movzwl %di, %eax
; SSE-NEXT: cvtsi2sd %eax, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: uifdw:
; AVX: # %bb.0: # %entry
; AVX-NEXT: movzwl %di, %eax
; AVX-NEXT: vcvtsi2sd %eax, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.uitofp.f64.i16(i16 %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
define double @uifdi(i32 %x) #0 {
; X87-LABEL: uifdi:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: movl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movl %eax, (%esp)
; X87-NEXT: movl $0, {{[0-9]+}}(%esp)
; X87-NEXT: fildll (%esp)
; X87-NEXT: wait
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: uifdi:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 16
; X86-SSE-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-SSE-NEXT: orpd {{\.LCPI.*}}, %xmm0
; X86-SSE-NEXT: subsd {{\.LCPI.*}}, %xmm0
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: fldl (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: addl $12, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: uifdi:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movl %edi, %eax
; SSE-NEXT: cvtsi2sd %rax, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: uifdi:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: movl %edi, %eax
; AVX1-NEXT: vcvtsi2sd %rax, %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX512-LABEL: uifdi:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vcvtusi2sd %edi, %xmm0, %xmm0
; AVX512-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.uitofp.f64.i32(i32 %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
define double @uifdl(i64 %x) #0 {
; X87-LABEL: uifdl:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $20, %esp
; X87-NEXT: .cfi_def_cfa_offset 24
; X87-NEXT: movl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X87-NEXT: movl %ecx, {{[0-9]+}}(%esp)
; X87-NEXT: movl %eax, (%esp)
; X87-NEXT: shrl $31, %ecx
; X87-NEXT: fildll (%esp)
; X87-NEXT: fadds {{\.LCPI.*}}(,%ecx,4)
; X87-NEXT: fstpl {{[0-9]+}}(%esp)
; X87-NEXT: fldl {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: addl $20, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: uifdl:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $28, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 32
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movlps %xmm0, {{[0-9]+}}(%esp)
; X86-SSE-NEXT: shrl $31, %eax
; X86-SSE-NEXT: fildll {{[0-9]+}}(%esp)
; X86-SSE-NEXT: fadds {{\.LCPI.*}}(,%eax,4)
; X86-SSE-NEXT: fstpl {{[0-9]+}}(%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movsd %xmm0, (%esp)
; X86-SSE-NEXT: fldl (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: addl $28, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: uifdl:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movq %rdi, %rax
; SSE-NEXT: shrq %rax
; SSE-NEXT: movl %edi, %ecx
; SSE-NEXT: andl $1, %ecx
; SSE-NEXT: orq %rax, %rcx
; SSE-NEXT: testq %rdi, %rdi
; SSE-NEXT: cmovnsq %rdi, %rcx
; SSE-NEXT: cvtsi2sd %rcx, %xmm0
; SSE-NEXT: jns .LBB48_2
; SSE-NEXT: # %bb.1:
; SSE-NEXT: addsd %xmm0, %xmm0
; SSE-NEXT: .LBB48_2: # %entry
; SSE-NEXT: retq
;
; AVX1-LABEL: uifdl:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: movq %rdi, %rax
; AVX1-NEXT: shrq %rax
; AVX1-NEXT: movl %edi, %ecx
; AVX1-NEXT: andl $1, %ecx
; AVX1-NEXT: orq %rax, %rcx
; AVX1-NEXT: testq %rdi, %rdi
; AVX1-NEXT: cmovnsq %rdi, %rcx
; AVX1-NEXT: vcvtsi2sd %rcx, %xmm0, %xmm0
; AVX1-NEXT: jns .LBB48_2
; AVX1-NEXT: # %bb.1:
; AVX1-NEXT: vaddsd %xmm0, %xmm0, %xmm0
; AVX1-NEXT: .LBB48_2: # %entry
; AVX1-NEXT: retq
;
; AVX512-LABEL: uifdl:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vcvtusi2sd %rdi, %xmm0, %xmm0
; AVX512-NEXT: retq
entry:
%result = call double @llvm.experimental.constrained.uitofp.f64.i64(i64 %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret double %result
}
define float @uiffb(i8 %x) #0 {
; X87-LABEL: uiffb:
; X87: # %bb.0: # %entry
; X87-NEXT: pushl %eax
; X87-NEXT: .cfi_def_cfa_offset 8
; X87-NEXT: movzbl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movw %ax, {{[0-9]+}}(%esp)
; X87-NEXT: filds {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: popl %eax
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: uiffb:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: pushl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 8
; X86-SSE-NEXT: movzbl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: cvtsi2ss %eax, %xmm0
; X86-SSE-NEXT: movss %xmm0, (%esp)
; X86-SSE-NEXT: flds (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: popl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: uiffb:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movzbl %dil, %eax
; SSE-NEXT: cvtsi2ss %eax, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: uiffb:
; AVX: # %bb.0: # %entry
; AVX-NEXT: movzbl %dil, %eax
; AVX-NEXT: vcvtsi2ss %eax, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call float @llvm.experimental.constrained.uitofp.f32.i8(i8 %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret float %result
}
define float @uiffw(i16 %x) #0 {
; X87-LABEL: uiffw:
; X87: # %bb.0: # %entry
; X87-NEXT: pushl %eax
; X87-NEXT: .cfi_def_cfa_offset 8
; X87-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movl %eax, (%esp)
; X87-NEXT: fildl (%esp)
; X87-NEXT: wait
; X87-NEXT: popl %eax
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: uiffw:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: pushl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 8
; X86-SSE-NEXT: movzwl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: cvtsi2ss %eax, %xmm0
; X86-SSE-NEXT: movss %xmm0, (%esp)
; X86-SSE-NEXT: flds (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: popl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: uiffw:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movzwl %di, %eax
; SSE-NEXT: cvtsi2ss %eax, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: uiffw:
; AVX: # %bb.0: # %entry
; AVX-NEXT: movzwl %di, %eax
; AVX-NEXT: vcvtsi2ss %eax, %xmm0, %xmm0
; AVX-NEXT: retq
entry:
%result = call float @llvm.experimental.constrained.uitofp.f32.i16(i16 %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret float %result
}
define float @uiffi(i32 %x) #0 {
; X87-LABEL: uiffi:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 16
; X87-NEXT: movl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movl %eax, (%esp)
; X87-NEXT: movl $0, {{[0-9]+}}(%esp)
; X87-NEXT: fildll (%esp)
; X87-NEXT: wait
; X87-NEXT: addl $12, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: uiffi:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: pushl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 8
; X86-SSE-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-SSE-NEXT: orpd {{\.LCPI.*}}, %xmm0
; X86-SSE-NEXT: subsd {{\.LCPI.*}}, %xmm0
; X86-SSE-NEXT: cvtsd2ss %xmm0, %xmm0
; X86-SSE-NEXT: movss %xmm0, (%esp)
; X86-SSE-NEXT: flds (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: popl %eax
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: uiffi:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movl %edi, %eax
; SSE-NEXT: cvtsi2ss %rax, %xmm0
; SSE-NEXT: retq
;
; AVX1-LABEL: uiffi:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: movl %edi, %eax
; AVX1-NEXT: vcvtsi2ss %rax, %xmm0, %xmm0
; AVX1-NEXT: retq
;
; AVX512-LABEL: uiffi:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vcvtusi2ss %edi, %xmm0, %xmm0
; AVX512-NEXT: retq
entry:
%result = call float @llvm.experimental.constrained.uitofp.f32.i32(i32 %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret float %result
}
define float @uiffl(i64 %x) #0 {
; X87-LABEL: uiffl:
; X87: # %bb.0: # %entry
; X87-NEXT: subl $20, %esp
; X87-NEXT: .cfi_def_cfa_offset 24
; X87-NEXT: movl {{[0-9]+}}(%esp), %eax
; X87-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X87-NEXT: movl %ecx, {{[0-9]+}}(%esp)
; X87-NEXT: movl %eax, {{[0-9]+}}(%esp)
; X87-NEXT: shrl $31, %ecx
; X87-NEXT: fildll {{[0-9]+}}(%esp)
; X87-NEXT: fadds {{\.LCPI.*}}(,%ecx,4)
; X87-NEXT: fstps {{[0-9]+}}(%esp)
; X87-NEXT: flds {{[0-9]+}}(%esp)
; X87-NEXT: wait
; X87-NEXT: addl $20, %esp
; X87-NEXT: .cfi_def_cfa_offset 4
; X87-NEXT: retl
;
; X86-SSE-LABEL: uiffl:
; X86-SSE: # %bb.0: # %entry
; X86-SSE-NEXT: subl $20, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 24
; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-SSE-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; X86-SSE-NEXT: movlps %xmm0, {{[0-9]+}}(%esp)
; X86-SSE-NEXT: shrl $31, %eax
; X86-SSE-NEXT: fildll {{[0-9]+}}(%esp)
; X86-SSE-NEXT: fadds {{\.LCPI.*}}(,%eax,4)
; X86-SSE-NEXT: fstps {{[0-9]+}}(%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-SSE-NEXT: movss %xmm0, (%esp)
; X86-SSE-NEXT: flds (%esp)
; X86-SSE-NEXT: wait
; X86-SSE-NEXT: addl $20, %esp
; X86-SSE-NEXT: .cfi_def_cfa_offset 4
; X86-SSE-NEXT: retl
;
; SSE-LABEL: uiffl:
; SSE: # %bb.0: # %entry
; SSE-NEXT: movq %rdi, %rax
; SSE-NEXT: shrq %rax
; SSE-NEXT: movl %edi, %ecx
; SSE-NEXT: andl $1, %ecx
; SSE-NEXT: orq %rax, %rcx
; SSE-NEXT: testq %rdi, %rdi
; SSE-NEXT: cmovnsq %rdi, %rcx
; SSE-NEXT: cvtsi2ss %rcx, %xmm0
; SSE-NEXT: jns .LBB52_2
; SSE-NEXT: # %bb.1:
; SSE-NEXT: addss %xmm0, %xmm0
; SSE-NEXT: .LBB52_2: # %entry
; SSE-NEXT: retq
;
; AVX1-LABEL: uiffl:
; AVX1: # %bb.0: # %entry
; AVX1-NEXT: movq %rdi, %rax
; AVX1-NEXT: shrq %rax
; AVX1-NEXT: movl %edi, %ecx
; AVX1-NEXT: andl $1, %ecx
; AVX1-NEXT: orq %rax, %rcx
; AVX1-NEXT: testq %rdi, %rdi
; AVX1-NEXT: cmovnsq %rdi, %rcx
; AVX1-NEXT: vcvtsi2ss %rcx, %xmm0, %xmm0
; AVX1-NEXT: jns .LBB52_2
; AVX1-NEXT: # %bb.1:
; AVX1-NEXT: vaddss %xmm0, %xmm0, %xmm0
; AVX1-NEXT: .LBB52_2: # %entry
; AVX1-NEXT: retq
;
; AVX512-LABEL: uiffl:
; AVX512: # %bb.0: # %entry
; AVX512-NEXT: vcvtusi2ss %rdi, %xmm0, %xmm0
; AVX512-NEXT: retq
entry:
%result = call float @llvm.experimental.constrained.uitofp.f32.i64(i64 %x,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
ret float %result
}
attributes #0 = { strictfp }
@llvm.fp.env = thread_local global i8 zeroinitializer, section "llvm.metadata"
declare double @llvm.experimental.constrained.fadd.f64(double, double, metadata, metadata)
declare double @llvm.experimental.constrained.fsub.f64(double, double, metadata, metadata)
declare double @llvm.experimental.constrained.fmul.f64(double, double, metadata, metadata)
declare double @llvm.experimental.constrained.fdiv.f64(double, double, metadata, metadata)
declare double @llvm.experimental.constrained.frem.f64(double, double, metadata, metadata)
declare double @llvm.experimental.constrained.sqrt.f64(double, metadata, metadata)
declare double @llvm.experimental.constrained.pow.f64(double, double, metadata, metadata)
declare double @llvm.experimental.constrained.powi.f64(double, i32, metadata, metadata)
declare double @llvm.experimental.constrained.sin.f64(double, metadata, metadata)
declare double @llvm.experimental.constrained.cos.f64(double, metadata, metadata)
declare double @llvm.experimental.constrained.exp.f64(double, metadata, metadata)
declare double @llvm.experimental.constrained.exp2.f64(double, metadata, metadata)
declare double @llvm.experimental.constrained.log.f64(double, metadata, metadata)
declare double @llvm.experimental.constrained.log10.f64(double, metadata, metadata)
declare double @llvm.experimental.constrained.log2.f64(double, metadata, metadata)
declare double @llvm.experimental.constrained.rint.f64(double, metadata, metadata)
declare double @llvm.experimental.constrained.nearbyint.f64(double, metadata, metadata)
declare i8 @llvm.experimental.constrained.fptosi.i8.f64(double, metadata)
declare i16 @llvm.experimental.constrained.fptosi.i16.f64(double, metadata)
declare i32 @llvm.experimental.constrained.fptosi.i32.f64(double, metadata)
declare i64 @llvm.experimental.constrained.fptosi.i64.f64(double, metadata)
declare i128 @llvm.experimental.constrained.fptosi.i128.f64(double, metadata)
declare i8 @llvm.experimental.constrained.fptoui.i8.f64(double, metadata)
declare i16 @llvm.experimental.constrained.fptoui.i16.f64(double, metadata)
declare i32 @llvm.experimental.constrained.fptoui.i32.f64(double, metadata)
declare i64 @llvm.experimental.constrained.fptoui.i64.f64(double, metadata)
declare i128 @llvm.experimental.constrained.fptoui.i128.f64(double, metadata)
declare float @llvm.experimental.constrained.fptrunc.f32.f64(double, metadata, metadata)
declare double @llvm.experimental.constrained.fpext.f64.f32(float, metadata)
declare i32 @llvm.experimental.constrained.lrint.i32.f64(double, metadata, metadata)
declare i32 @llvm.experimental.constrained.lrint.i32.f32(float, metadata, metadata)
declare i64 @llvm.experimental.constrained.llrint.i64.f64(double, metadata, metadata)
declare i64 @llvm.experimental.constrained.llrint.i64.f32(float, metadata, metadata)
declare i32 @llvm.experimental.constrained.lround.i32.f64(double, metadata)
declare i32 @llvm.experimental.constrained.lround.i32.f32(float, metadata)
declare i64 @llvm.experimental.constrained.llround.i64.f64(double, metadata)
declare i64 @llvm.experimental.constrained.llround.i64.f32(float, metadata)
declare double @llvm.experimental.constrained.sitofp.f64.i8(i8, metadata, metadata)
declare double @llvm.experimental.constrained.sitofp.f64.i16(i16, metadata, metadata)
declare double @llvm.experimental.constrained.sitofp.f64.i32(i32, metadata, metadata)
declare double @llvm.experimental.constrained.sitofp.f64.i64(i64, metadata, metadata)
declare float @llvm.experimental.constrained.sitofp.f32.i8(i8, metadata, metadata)
declare float @llvm.experimental.constrained.sitofp.f32.i16(i16, metadata, metadata)
declare float @llvm.experimental.constrained.sitofp.f32.i32(i32, metadata, metadata)
declare float @llvm.experimental.constrained.sitofp.f32.i64(i64, metadata, metadata)
declare double @llvm.experimental.constrained.uitofp.f64.i8(i8, metadata, metadata)
declare double @llvm.experimental.constrained.uitofp.f64.i16(i16, metadata, metadata)
declare double @llvm.experimental.constrained.uitofp.f64.i32(i32, metadata, metadata)
declare double @llvm.experimental.constrained.uitofp.f64.i64(i64, metadata, metadata)
declare float @llvm.experimental.constrained.uitofp.f32.i8(i8, metadata, metadata)
declare float @llvm.experimental.constrained.uitofp.f32.i16(i16, metadata, metadata)
declare float @llvm.experimental.constrained.uitofp.f32.i32(i32, metadata, metadata)
declare float @llvm.experimental.constrained.uitofp.f32.i64(i64, metadata, metadata)
Reference in New Issue View Git Blame Copy Permalink