1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 18:54:02 +01:00

Populate list of vectorizable functions for Accelerate library.

Summary:
This patch adds majority of supported by Accelerate library functions to the
list of vectorizable functions.

The full list of available vector functions could be found here:
https://developer.apple.com/library/mac/documentation/Performance/Conceptual/vecLib/index.html

Test Plan: Unit tests are added.

Reviewers: hfinkel, aschwaighofer, nadav

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D9543

llvm-svn: 236747
This commit is contained in:
Michael Zolotukhin 2015-05-07 17:11:51 +00:00
parent 8e8f3306ff
commit 5f8e19491e
2 changed files with 484 additions and 6 deletions

View File

@ -467,14 +467,42 @@ void TargetLibraryInfoImpl::addVectorizableFunctionsFromVecLib(
switch (VecLib) {
case Accelerate: {
const VecDesc VecFuncs[] = {
{"expf", "vexpf", 4},
{"llvm.exp.f32", "vexpf", 4},
{"logf", "vlogf", 4},
{"llvm.log.f32", "vlogf", 4},
{"sqrtf", "vsqrtf", 4},
{"llvm.sqrt.f32", "vsqrtf", 4},
// Floating-Point Arithmetic and Auxiliary Functions
{"ceilf", "vceilf", 4},
{"fabsf", "vfabsf", 4},
{"llvm.fabs.f32", "vfabsf", 4},
{"floorf", "vfloorf", 4},
{"sqrtf", "vsqrtf", 4},
{"llvm.sqrt.f32", "vsqrtf", 4},
// Exponential and Logarithmic Functions
{"expf", "vexpf", 4},
{"llvm.exp.f32", "vexpf", 4},
{"expm1f", "vexpm1f", 4},
{"logf", "vlogf", 4},
{"llvm.log.f32", "vlogf", 4},
{"log1pf", "vlog1pf", 4},
{"log10f", "vlog10f", 4},
{"llvm.log10.f32", "vlog10f", 4},
{"logbf", "vlogbf", 4},
// Trigonometric Functions
{"sinf", "vsinf", 4},
{"llvm.sin.f32", "vsinf", 4},
{"cosf", "vcosf", 4},
{"llvm.cos.f32", "vcosf", 4},
{"tanf", "vtanf", 4},
{"asinf", "vasinf", 4},
{"acosf", "vacosf", 4},
{"atanf", "vatanf", 4},
// Hyperbolic Functions
{"sinhf", "vsinhf", 4},
{"coshf", "vcoshf", 4},
{"tanhf", "vtanhf", 4},
{"asinhf", "vasinhf", 4},
{"acoshf", "vacoshf", 4},
{"atanhf", "vatanhf", 4},
};
addVectorizableFunctions(VecFuncs);
break;

View File

@ -180,3 +180,453 @@ for.body: ; preds = %entry, %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @ceil_f32(
;CHECK: vceilf{{.*}}<4 x float>
;CHECK: ret void
declare float @ceilf(float) nounwind readnone
define void @ceil_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @ceilf(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @floor_f32(
;CHECK: vfloorf{{.*}}<4 x float>
;CHECK: ret void
declare float @floorf(float) nounwind readnone
define void @floor_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @floorf(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @expm1_f32(
;CHECK: vexpm1f{{.*}}<4 x float>
;CHECK: ret void
declare float @expm1f(float) nounwind readnone
define void @expm1_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @expm1f(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @log1p_f32(
;CHECK: vlog1pf{{.*}}<4 x float>
;CHECK: ret void
declare float @log1pf(float) nounwind readnone
define void @log1p_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @log1pf(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @log10_f32(
;CHECK: vlog10f{{.*}}<4 x float>
;CHECK: ret void
declare float @log10f(float) nounwind readnone
define void @log10_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @log10f(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @logb_f32(
;CHECK: vlogbf{{.*}}<4 x float>
;CHECK: ret void
declare float @logbf(float) nounwind readnone
define void @logb_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @logbf(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @sin_f32(
;CHECK: vsinf{{.*}}<4 x float>
;CHECK: ret void
declare float @sinf(float) nounwind readnone
define void @sin_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @sinf(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @cos_f32(
;CHECK: vcosf{{.*}}<4 x float>
;CHECK: ret void
declare float @cosf(float) nounwind readnone
define void @cos_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @cosf(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @tan_f32(
;CHECK: vtanf{{.*}}<4 x float>
;CHECK: ret void
declare float @tanf(float) nounwind readnone
define void @tan_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @tanf(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @asin_f32(
;CHECK: vasinf{{.*}}<4 x float>
;CHECK: ret void
declare float @asinf(float) nounwind readnone
define void @asin_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @asinf(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @acos_f32(
;CHECK: vacosf{{.*}}<4 x float>
;CHECK: ret void
declare float @acosf(float) nounwind readnone
define void @acos_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @acosf(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @atan_f32(
;CHECK: vatanf{{.*}}<4 x float>
;CHECK: ret void
declare float @atanf(float) nounwind readnone
define void @atan_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @atanf(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @sinh_f32(
;CHECK: vsinhf{{.*}}<4 x float>
;CHECK: ret void
declare float @sinhf(float) nounwind readnone
define void @sinh_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @sinhf(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @cosh_f32(
;CHECK: vcoshf{{.*}}<4 x float>
;CHECK: ret void
declare float @coshf(float) nounwind readnone
define void @cosh_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @coshf(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @tanh_f32(
;CHECK: vtanhf{{.*}}<4 x float>
;CHECK: ret void
declare float @tanhf(float) nounwind readnone
define void @tanh_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @tanhf(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @asinh_f32(
;CHECK: vasinhf{{.*}}<4 x float>
;CHECK: ret void
declare float @asinhf(float) nounwind readnone
define void @asinh_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @asinhf(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @acosh_f32(
;CHECK: vacoshf{{.*}}<4 x float>
;CHECK: ret void
declare float @acoshf(float) nounwind readnone
define void @acosh_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @acoshf(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}
;CHECK-LABEL: @atanh_f32(
;CHECK: vatanhf{{.*}}<4 x float>
;CHECK: ret void
declare float @atanhf(float) nounwind readnone
define void @atanh_f32(i32 %n, float* noalias %y, float* noalias %x) nounwind uwtable {
entry:
%cmp6 = icmp sgt i32 %n, 0
br i1 %cmp6, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, float* %y, i64 %indvars.iv
%0 = load float, float* %arrayidx, align 4
%call = tail call float @atanhf(float %0) nounwind readnone
%arrayidx2 = getelementptr inbounds float, float* %x, i64 %indvars.iv
store float %call, float* %arrayidx2, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret void
}