mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-29 10:32:47 +00:00
1ef70ff39b
Now that `Metadata` is typeless, reflect that in the assembly. These
are the matching assembly changes for the metadata/value split in
r223802.
- Only use the `metadata` type when referencing metadata from a call
intrinsic -- i.e., only when it's used as a `Value`.
- Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode`
when referencing it from call intrinsics.
So, assembly like this:
define @foo(i32 %v) {
call void @llvm.foo(metadata !{i32 %v}, metadata !0)
call void @llvm.foo(metadata !{i32 7}, metadata !0)
call void @llvm.foo(metadata !1, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{metadata !3}, metadata !0)
ret void, !bar !2
}
!0 = metadata !{metadata !2}
!1 = metadata !{i32* @global}
!2 = metadata !{metadata !3}
!3 = metadata !{}
turns into this:
define @foo(i32 %v) {
call void @llvm.foo(metadata i32 %v, metadata !0)
call void @llvm.foo(metadata i32 7, metadata !0)
call void @llvm.foo(metadata i32* @global, metadata !0)
call void @llvm.foo(metadata !3, metadata !0)
call void @llvm.foo(metadata !{!3}, metadata !0)
ret void, !bar !2
}
!0 = !{!2}
!1 = !{i32* @global}
!2 = !{!3}
!3 = !{}
I wrote an upgrade script that handled almost all of the tests in llvm
and many of the tests in cfe (even handling many `CHECK` lines). I've
attached it (or will attach it in a moment if you're speedy) to PR21532
to help everyone update their out-of-tree testcases.
This is part of PR21532.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@224257 91177308-0d34-0410-b5e6-96231b3b80d8
74 lines
2.6 KiB
LLVM
74 lines
2.6 KiB
LLVM
; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -debug-only=loop-vectorize -stats -S -vectorizer-min-trip-count=21 2>&1 | FileCheck %s
|
|
; REQUIRES: asserts
|
|
|
|
; CHECK: LV: Loop hints: force=enabled
|
|
; CHECK: LV: Loop hints: force=?
|
|
; No more loops in the module
|
|
; CHECK-NOT: LV: Loop hints: force=
|
|
; CHECK: 2 loop-vectorize - Number of loops analyzed for vectorization
|
|
; CHECK: 1 loop-vectorize - Number of loops vectorized
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-apple-macosx10.8.0"
|
|
|
|
;
|
|
; The source code for the test:
|
|
;
|
|
; void foo(float* restrict A, float* restrict B)
|
|
; {
|
|
; for (int i = 0; i < 20; ++i) A[i] += B[i];
|
|
; }
|
|
;
|
|
|
|
;
|
|
; This loop will be vectorized, although the trip count is below the threshold, but vectorization is explicitly forced in metadata.
|
|
;
|
|
define void @vectorized(float* noalias nocapture %A, float* noalias nocapture readonly %B) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds float* %B, i64 %indvars.iv
|
|
%0 = load float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !1
|
|
%arrayidx2 = getelementptr inbounds float* %A, i64 %indvars.iv
|
|
%1 = load float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !1
|
|
%add = fadd fast float %0, %1
|
|
store float %add, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !1
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp eq i64 %indvars.iv.next, 20
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !1
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
!1 = !{!1, !2}
|
|
!2 = !{!"llvm.loop.vectorize.enable", i1 true}
|
|
|
|
;
|
|
; This loop will not be vectorized as the trip count is below the threshold.
|
|
;
|
|
define void @not_vectorized(float* noalias nocapture %A, float* noalias nocapture readonly %B) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds float* %B, i64 %indvars.iv
|
|
%0 = load float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
|
|
%arrayidx2 = getelementptr inbounds float* %A, i64 %indvars.iv
|
|
%1 = load float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
|
|
%add = fadd fast float %0, %1
|
|
store float %add, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%exitcond = icmp eq i64 %indvars.iv.next, 20
|
|
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !3
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
!3 = !{!3}
|
|
|