mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-10-31 08:16:47 +00:00
87c977a52b
"Unroll" is not the appropriate name for this variable. Clang already uses the term "interleave" in pragmas and metadata for this. Differential Revision: http://reviews.llvm.org/D5066 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217528 91177308-0d34-0410-b5e6-96231b3b80d8
143 lines
5.3 KiB
LLVM
143 lines
5.3 KiB
LLVM
; RUN: opt -S -march=r600 -mcpu=cayman -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine < %s | FileCheck %s
|
|
|
|
; Artificial datalayout
|
|
target datalayout = "e-p:32:32:32-p1:16:16:16-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-v16:16:16-v24:32:32-v32:32:32-v48:64:64-v64:64:64-v96:128:128-v128:128:128-v192:256:256-v256:256:256-v512:512:512-v1024:1024:1024-v2048:2048:2048-n32:64"
|
|
|
|
|
|
define void @add_ints_1_1_1(i32 addrspace(1)* %a, i32 addrspace(1)* %b, i32 addrspace(1)* %c) #0 {
|
|
; CHECK-LABEL: @add_ints_1_1_1(
|
|
; CHECK: <4 x i32>
|
|
; CHECK: ret
|
|
entry:
|
|
br label %for.cond
|
|
|
|
for.cond: ; preds = %for.body, %entry
|
|
%i.0 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%cmp = icmp ult i64 %i.0, 200
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.body: ; preds = %for.cond
|
|
%arrayidx = getelementptr inbounds i32 addrspace(1)* %b, i64 %i.0
|
|
%0 = load i32 addrspace(1)* %arrayidx, align 4
|
|
%arrayidx1 = getelementptr inbounds i32 addrspace(1)* %c, i64 %i.0
|
|
%1 = load i32 addrspace(1)* %arrayidx1, align 4
|
|
%add = add nsw i32 %0, %1
|
|
%arrayidx2 = getelementptr inbounds i32 addrspace(1)* %a, i64 %i.0
|
|
store i32 %add, i32 addrspace(1)* %arrayidx2, align 4
|
|
%inc = add i64 %i.0, 1
|
|
br label %for.cond
|
|
|
|
for.end: ; preds = %for.cond
|
|
ret void
|
|
}
|
|
|
|
define void @add_ints_as_1_0_0(i32 addrspace(1)* %a, i32* %b, i32* %c) #0 {
|
|
; CHECK-LABEL: @add_ints_as_1_0_0(
|
|
; CHECK-NOT: <4 x i32>
|
|
; CHECK: ret
|
|
entry:
|
|
br label %for.cond
|
|
|
|
for.cond: ; preds = %for.body, %entry
|
|
%i.0 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%cmp = icmp ult i64 %i.0, 200
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.body: ; preds = %for.cond
|
|
%arrayidx = getelementptr inbounds i32* %b, i64 %i.0
|
|
%0 = load i32* %arrayidx, align 4
|
|
%arrayidx1 = getelementptr inbounds i32* %c, i64 %i.0
|
|
%1 = load i32* %arrayidx1, align 4
|
|
%add = add nsw i32 %0, %1
|
|
%arrayidx2 = getelementptr inbounds i32 addrspace(1)* %a, i64 %i.0
|
|
store i32 %add, i32 addrspace(1)* %arrayidx2, align 4
|
|
%inc = add i64 %i.0, 1
|
|
br label %for.cond
|
|
|
|
for.end: ; preds = %for.cond
|
|
ret void
|
|
}
|
|
|
|
define void @add_ints_as_0_1_0(i32* %a, i32 addrspace(1)* %b, i32* %c) #0 {
|
|
; CHECK-LABEL: @add_ints_as_0_1_0(
|
|
; CHECK-NOT: <4 x i32>
|
|
; CHECK: ret
|
|
entry:
|
|
br label %for.cond
|
|
|
|
for.cond: ; preds = %for.body, %entry
|
|
%i.0 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%cmp = icmp ult i64 %i.0, 200
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.body: ; preds = %for.cond
|
|
%arrayidx = getelementptr inbounds i32 addrspace(1)* %b, i64 %i.0
|
|
%0 = load i32 addrspace(1)* %arrayidx, align 4
|
|
%arrayidx1 = getelementptr inbounds i32* %c, i64 %i.0
|
|
%1 = load i32* %arrayidx1, align 4
|
|
%add = add nsw i32 %0, %1
|
|
%arrayidx2 = getelementptr inbounds i32* %a, i64 %i.0
|
|
store i32 %add, i32* %arrayidx2, align 4
|
|
%inc = add i64 %i.0, 1
|
|
br label %for.cond
|
|
|
|
for.end: ; preds = %for.cond
|
|
ret void
|
|
}
|
|
|
|
define void @add_ints_as_0_1_1(i32* %a, i32 addrspace(1)* %b, i32 addrspace(1)* %c) #0 {
|
|
; CHECK-LABEL: @add_ints_as_0_1_1(
|
|
; CHECK-NOT: <4 x i32>
|
|
; CHECK: ret
|
|
entry:
|
|
br label %for.cond
|
|
|
|
for.cond: ; preds = %for.body, %entry
|
|
%i.0 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%cmp = icmp ult i64 %i.0, 200
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.body: ; preds = %for.cond
|
|
%arrayidx = getelementptr inbounds i32 addrspace(1)* %b, i64 %i.0
|
|
%0 = load i32 addrspace(1)* %arrayidx, align 4
|
|
%arrayidx1 = getelementptr inbounds i32 addrspace(1)* %c, i64 %i.0
|
|
%1 = load i32 addrspace(1)* %arrayidx1, align 4
|
|
%add = add nsw i32 %0, %1
|
|
%arrayidx2 = getelementptr inbounds i32* %a, i64 %i.0
|
|
store i32 %add, i32* %arrayidx2, align 4
|
|
%inc = add i64 %i.0, 1
|
|
br label %for.cond
|
|
|
|
for.end: ; preds = %for.cond
|
|
ret void
|
|
}
|
|
|
|
define void @add_ints_as_0_1_2(i32* %a, i32 addrspace(1)* %b, i32 addrspace(2)* %c) #0 {
|
|
; CHECK-LABEL: @add_ints_as_0_1_2(
|
|
; CHECK-NOT: <4 x i32>
|
|
; CHECK: ret
|
|
entry:
|
|
br label %for.cond
|
|
|
|
for.cond: ; preds = %for.body, %entry
|
|
%i.0 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%cmp = icmp ult i64 %i.0, 200
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.body: ; preds = %for.cond
|
|
%arrayidx = getelementptr inbounds i32 addrspace(1)* %b, i64 %i.0
|
|
%0 = load i32 addrspace(1)* %arrayidx, align 4
|
|
%arrayidx1 = getelementptr inbounds i32 addrspace(2)* %c, i64 %i.0
|
|
%1 = load i32 addrspace(2)* %arrayidx1, align 4
|
|
%add = add nsw i32 %0, %1
|
|
%arrayidx2 = getelementptr inbounds i32* %a, i64 %i.0
|
|
store i32 %add, i32* %arrayidx2, align 4
|
|
%inc = add i64 %i.0, 1
|
|
br label %for.cond
|
|
|
|
for.end: ; preds = %for.cond
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
|