summaryrefslogtreecommitdiffstats
path: root/test/Transforms/LoopVectorize/X86
diff options
context:
space:
mode:
Diffstat (limited to 'test/Transforms/LoopVectorize/X86')
-rw-r--r--test/Transforms/LoopVectorize/X86/avx1.ll49
-rw-r--r--test/Transforms/LoopVectorize/X86/conversion-cost.ll48
-rw-r--r--test/Transforms/LoopVectorize/X86/cost-model.ll38
-rw-r--r--test/Transforms/LoopVectorize/X86/gcc-examples.ll62
-rw-r--r--test/Transforms/LoopVectorize/X86/lit.local.cfg6
5 files changed, 203 insertions, 0 deletions
diff --git a/test/Transforms/LoopVectorize/X86/avx1.ll b/test/Transforms/LoopVectorize/X86/avx1.ll
new file mode 100644
index 0000000..a2d176a
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/avx1.ll
@@ -0,0 +1,49 @@
+; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -S | FileCheck %s
+
+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"
+
+;CHECK: @read_mod_write_single_ptr
+;CHECK: load <8 x float>
+;CHECK: ret i32
+define i32 @read_mod_write_single_ptr(float* nocapture %a, i32 %n) nounwind uwtable ssp {
+ %1 = icmp sgt i32 %n, 0
+ br i1 %1, label %.lr.ph, label %._crit_edge
+
+.lr.ph: ; preds = %0, %.lr.ph
+ %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
+ %2 = getelementptr inbounds float* %a, i64 %indvars.iv
+ %3 = load float* %2, align 4
+ %4 = fmul float %3, 3.000000e+00
+ store float %4, float* %2, 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 %._crit_edge, label %.lr.ph
+
+._crit_edge: ; preds = %.lr.ph, %0
+ ret i32 undef
+}
+
+
+;CHECK: @read_mod_i64
+;CHECK: load <8 x i64>
+;CHECK: ret i32
+define i32 @read_mod_i64(i64* nocapture %a, i32 %n) nounwind uwtable ssp {
+ %1 = icmp sgt i32 %n, 0
+ br i1 %1, label %.lr.ph, label %._crit_edge
+
+.lr.ph: ; preds = %0, %.lr.ph
+ %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 0, %0 ]
+ %2 = getelementptr inbounds i64* %a, i64 %indvars.iv
+ %3 = load i64* %2, align 4
+ %4 = mul i64 %3, 3
+ store i64 %4, i64* %2, 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 %._crit_edge, label %.lr.ph
+
+._crit_edge: ; preds = %.lr.ph, %0
+ ret i32 undef
+}
diff --git a/test/Transforms/LoopVectorize/X86/conversion-cost.ll b/test/Transforms/LoopVectorize/X86/conversion-cost.ll
new file mode 100644
index 0000000..8f1bb54
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/conversion-cost.ll
@@ -0,0 +1,48 @@
+; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -S | FileCheck %s
+
+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"
+
+;CHECK: @conversion_cost1
+;CHECK: store <2 x i8>
+;CHECK: ret
+define i32 @conversion_cost1(i32 %n, i8* nocapture %A, float* nocapture %B) nounwind uwtable ssp {
+ %1 = icmp sgt i32 %n, 3
+ br i1 %1, label %.lr.ph, label %._crit_edge
+
+.lr.ph: ; preds = %0, %.lr.ph
+ %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 3, %0 ]
+ %2 = trunc i64 %indvars.iv to i8
+ %3 = getelementptr inbounds i8* %A, i64 %indvars.iv
+ store i8 %2, i8* %3, align 1
+ %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 %._crit_edge, label %.lr.ph
+
+._crit_edge: ; preds = %.lr.ph, %0
+ ret i32 undef
+}
+
+;CHECK: @conversion_cost2
+;CHECK: <2 x float>
+;CHECK: ret
+define i32 @conversion_cost2(i32 %n, i8* nocapture %A, float* nocapture %B) nounwind uwtable ssp {
+ %1 = icmp sgt i32 %n, 9
+ br i1 %1, label %.lr.ph, label %._crit_edge
+
+.lr.ph: ; preds = %0, %.lr.ph
+ %indvars.iv = phi i64 [ %indvars.iv.next, %.lr.ph ], [ 9, %0 ]
+ %2 = add nsw i64 %indvars.iv, 3
+ %3 = trunc i64 %2 to i32
+ %4 = sitofp i32 %3 to float
+ %5 = getelementptr inbounds float* %B, i64 %indvars.iv
+ store float %4, float* %5, 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 %._crit_edge, label %.lr.ph
+
+._crit_edge: ; preds = %.lr.ph, %0
+ ret i32 undef
+}
diff --git a/test/Transforms/LoopVectorize/X86/cost-model.ll b/test/Transforms/LoopVectorize/X86/cost-model.ll
new file mode 100644
index 0000000..628f991
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/cost-model.ll
@@ -0,0 +1,38 @@
+; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -S | FileCheck %s
+
+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"
+
+@c = common global [2048 x i32] zeroinitializer, align 16
+@b = common global [2048 x i32] zeroinitializer, align 16
+@d = common global [2048 x i32] zeroinitializer, align 16
+@a = common global [2048 x i32] zeroinitializer, align 16
+
+;CHECK: cost_model_1
+;CHECK: <4 x i32>
+;CHECK: ret void
+define void @cost_model_1() nounwind uwtable noinline ssp {
+entry:
+ br label %for.body
+
+for.body: ; preds = %for.body, %entry
+ %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+ %0 = shl nsw i64 %indvars.iv, 1
+ %arrayidx = getelementptr inbounds [2048 x i32]* @c, i64 0, i64 %0
+ %1 = load i32* %arrayidx, align 8
+ %idxprom1 = sext i32 %1 to i64
+ %arrayidx2 = getelementptr inbounds [2048 x i32]* @b, i64 0, i64 %idxprom1
+ %2 = load i32* %arrayidx2, align 4
+ %arrayidx4 = getelementptr inbounds [2048 x i32]* @d, i64 0, i64 %indvars.iv
+ %3 = load i32* %arrayidx4, align 4
+ %idxprom5 = sext i32 %3 to i64
+ %arrayidx6 = getelementptr inbounds [2048 x i32]* @a, i64 0, i64 %idxprom5
+ store i32 %2, i32* %arrayidx6, 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, 256
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body
+ ret void
+}
diff --git a/test/Transforms/LoopVectorize/X86/gcc-examples.ll b/test/Transforms/LoopVectorize/X86/gcc-examples.ll
new file mode 100644
index 0000000..574c529
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/gcc-examples.ll
@@ -0,0 +1,62 @@
+; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7 -dce -instcombine -licm -S | FileCheck %s
+
+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"
+
+@b = common global [2048 x i32] zeroinitializer, align 16
+@c = common global [2048 x i32] zeroinitializer, align 16
+@a = common global [2048 x i32] zeroinitializer, align 16
+
+; Select VF = 8;
+;CHECK: @example1
+;CHECK: load <8 x i32>
+;CHECK: add nsw <8 x i32>
+;CHECK: store <8 x i32>
+;CHECK: ret void
+define void @example1() nounwind uwtable ssp {
+ br label %1
+
+; <label>:1 ; preds = %1, %0
+ %indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %1 ]
+ %2 = getelementptr inbounds [2048 x i32]* @b, i64 0, i64 %indvars.iv
+ %3 = load i32* %2, align 4
+ %4 = getelementptr inbounds [2048 x i32]* @c, i64 0, i64 %indvars.iv
+ %5 = load i32* %4, align 4
+ %6 = add nsw i32 %5, %3
+ %7 = getelementptr inbounds [2048 x i32]* @a, i64 0, i64 %indvars.iv
+ store i32 %6, i32* %7, 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, 256
+ br i1 %exitcond, label %8, label %1
+
+; <label>:8 ; preds = %1
+ ret void
+}
+
+
+; Select VF=4 because sext <8 x i1> to <8 x i32> is expensive.
+;CHECK: @example10b
+;CHECK: load <4 x i16>
+;CHECK: sext <4 x i16>
+;CHECK: store <4 x i32>
+;CHECK: ret void
+define void @example10b(i16* noalias nocapture %sa, i16* noalias nocapture %sb, i16* noalias nocapture %sc, i32* noalias nocapture %ia, i32* noalias nocapture %ib, i32* noalias nocapture %ic) nounwind uwtable ssp {
+ br label %1
+
+; <label>:1 ; preds = %1, %0
+ %indvars.iv = phi i64 [ 0, %0 ], [ %indvars.iv.next, %1 ]
+ %2 = getelementptr inbounds i16* %sb, i64 %indvars.iv
+ %3 = load i16* %2, align 2
+ %4 = sext i16 %3 to i32
+ %5 = getelementptr inbounds i32* %ia, i64 %indvars.iv
+ store i32 %4, i32* %5, 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, 1024
+ br i1 %exitcond, label %6, label %1
+
+; <label>:6 ; preds = %1
+ ret void
+}
+
diff --git a/test/Transforms/LoopVectorize/X86/lit.local.cfg b/test/Transforms/LoopVectorize/X86/lit.local.cfg
new file mode 100644
index 0000000..a8ad0f1
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/lit.local.cfg
@@ -0,0 +1,6 @@
+config.suffixes = ['.ll', '.c', '.cpp']
+
+targets = set(config.root.targets_to_build.split())
+if not 'X86' in targets:
+ config.unsupported = True
+
OpenPOWER on IntegriCloud