From: Matthew Simpson Date: Tue, 7 Feb 2017 19:34:24 +0000 (+0000) Subject: [LV] Add new ARM/AArch64 interleaved access cost model tests (NFC) X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=9e8cc9ccc4fe933f3f70d21bb38afe3788a316d5;p=llvm [LV] Add new ARM/AArch64 interleaved access cost model tests (NFC) git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@294342 91177308-0d34-0410-b5e6-96231b3b80d8 --- diff --git a/test/Transforms/LoopVectorize/AArch64/interleaved_cost.ll b/test/Transforms/LoopVectorize/AArch64/interleaved_cost.ll index 4f78f3f5007..796f8c2bda8 100644 --- a/test/Transforms/LoopVectorize/AArch64/interleaved_cost.ll +++ b/test/Transforms/LoopVectorize/AArch64/interleaved_cost.ll @@ -1,4 +1,5 @@ ; RUN: opt -loop-vectorize -force-vector-width=2 -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefix=VF_2 +; RUN: opt -loop-vectorize -force-vector-width=4 -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefix=VF_4 ; RUN: opt -loop-vectorize -force-vector-width=8 -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefix=VF_8 ; RUN: opt -loop-vectorize -force-vector-width=16 -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefix=VF_16 ; REQUIRES: asserts @@ -37,6 +38,94 @@ for.end: ret void } +%i16.2 = type {i16, i16} +define void @i16_factor_2(%i16.2* %data, i64 %n) { +entry: + br label %for.body + +; VF_4-LABEL: Checking a loop in "i16_factor_2" +; VF_4: Found an estimated cost of 2 for VF 4 For instruction: %tmp2 = load i16, i16* %tmp0, align 2 +; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i16, i16* %tmp1, align 2 +; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp0, align 2 +; VF_4-NEXT: Found an estimated cost of 2 for VF 4 For instruction: store i16 0, i16* %tmp1, align 2 +; VF_8-LABEL: Checking a loop in "i16_factor_2" +; VF_8: Found an estimated cost of 2 for VF 8 For instruction: %tmp2 = load i16, i16* %tmp0, align 2 +; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i16, i16* %tmp1, align 2 +; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp0, align 2 +; VF_8-NEXT: Found an estimated cost of 2 for VF 8 For instruction: store i16 0, i16* %tmp1, align 2 +for.body: + %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ] + %tmp0 = getelementptr inbounds %i16.2, %i16.2* %data, i64 %i, i32 0 + %tmp1 = getelementptr inbounds %i16.2, %i16.2* %data, i64 %i, i32 1 + %tmp2 = load i16, i16* %tmp0, align 2 + %tmp3 = load i16, i16* %tmp1, align 2 + store i16 0, i16* %tmp0, align 2 + store i16 0, i16* %tmp1, align 2 + %i.next = add nuw nsw i64 %i, 1 + %cond = icmp slt i64 %i.next, %n + br i1 %cond, label %for.body, label %for.end + +for.end: + ret void +} + +%i32.2 = type {i32, i32} +define void @i32_factor_2(%i32.2* %data, i64 %n) { +entry: + br label %for.body + +; VF_2-LABEL: Checking a loop in "i32_factor_2" +; VF_2: Found an estimated cost of 2 for VF 2 For instruction: %tmp2 = load i32, i32* %tmp0, align 4 +; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i32, i32* %tmp1, align 4 +; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp0, align 4 +; VF_2-NEXT: Found an estimated cost of 2 for VF 2 For instruction: store i32 0, i32* %tmp1, align 4 +; VF_4-LABEL: Checking a loop in "i32_factor_2" +; VF_4: Found an estimated cost of 2 for VF 4 For instruction: %tmp2 = load i32, i32* %tmp0, align 4 +; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i32, i32* %tmp1, align 4 +; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp0, align 4 +; VF_4-NEXT: Found an estimated cost of 2 for VF 4 For instruction: store i32 0, i32* %tmp1, align 4 +for.body: + %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ] + %tmp0 = getelementptr inbounds %i32.2, %i32.2* %data, i64 %i, i32 0 + %tmp1 = getelementptr inbounds %i32.2, %i32.2* %data, i64 %i, i32 1 + %tmp2 = load i32, i32* %tmp0, align 4 + %tmp3 = load i32, i32* %tmp1, align 4 + store i32 0, i32* %tmp0, align 4 + store i32 0, i32* %tmp1, align 4 + %i.next = add nuw nsw i64 %i, 1 + %cond = icmp slt i64 %i.next, %n + br i1 %cond, label %for.body, label %for.end + +for.end: + ret void +} + +%i64.2 = type {i64, i64} +define void @i64_factor_2(%i64.2* %data, i64 %n) { +entry: + br label %for.body + +; VF_2-LABEL: Checking a loop in "i64_factor_2" +; VF_2: Found an estimated cost of 2 for VF 2 For instruction: %tmp2 = load i64, i64* %tmp0, align 8 +; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i64, i64* %tmp1, align 8 +; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i64 0, i64* %tmp0, align 8 +; VF_2-NEXT: Found an estimated cost of 2 for VF 2 For instruction: store i64 0, i64* %tmp1, align 8 +for.body: + %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ] + %tmp0 = getelementptr inbounds %i64.2, %i64.2* %data, i64 %i, i32 0 + %tmp1 = getelementptr inbounds %i64.2, %i64.2* %data, i64 %i, i32 1 + %tmp2 = load i64, i64* %tmp0, align 8 + %tmp3 = load i64, i64* %tmp1, align 8 + store i64 0, i64* %tmp0, align 8 + store i64 0, i64* %tmp1, align 8 + %i.next = add nuw nsw i64 %i, 1 + %cond = icmp slt i64 %i.next, %n + br i1 %cond, label %for.body, label %for.end + +for.end: + ret void +} + %i64.8 = type {i64, i64, i64, i64, i64, i64, i64, i64} define void @i64_factor_8(%i64.8* %data, i64 %n) { entry: diff --git a/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll b/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll index 3ccd9217eee..012a5fc1686 100644 --- a/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll +++ b/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll @@ -1,3 +1,5 @@ +; RUN: opt -loop-vectorize -force-vector-width=2 -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefix=VF_2 +; RUN: opt -loop-vectorize -force-vector-width=4 -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefix=VF_4 ; RUN: opt -loop-vectorize -force-vector-width=8 -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefix=VF_8 ; RUN: opt -loop-vectorize -force-vector-width=16 -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefix=VF_16 ; REQUIRES: asserts @@ -35,3 +37,65 @@ for.body: for.end: ret void } + +%i16.2 = type {i16, i16} +define void @i16_factor_2(%i16.2* %data, i64 %n) { +entry: + br label %for.body + +; VF_4-LABEL: Checking a loop in "i16_factor_2" +; VF_4: Found an estimated cost of 2 for VF 4 For instruction: %tmp2 = load i16, i16* %tmp0, align 2 +; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i16, i16* %tmp1, align 2 +; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp0, align 2 +; VF_4-NEXT: Found an estimated cost of 2 for VF 4 For instruction: store i16 0, i16* %tmp1, align 2 +; VF_8-LABEL: Checking a loop in "i16_factor_2" +; VF_8: Found an estimated cost of 2 for VF 8 For instruction: %tmp2 = load i16, i16* %tmp0, align 2 +; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i16, i16* %tmp1, align 2 +; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp0, align 2 +; VF_8-NEXT: Found an estimated cost of 2 for VF 8 For instruction: store i16 0, i16* %tmp1, align 2 +for.body: + %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ] + %tmp0 = getelementptr inbounds %i16.2, %i16.2* %data, i64 %i, i32 0 + %tmp1 = getelementptr inbounds %i16.2, %i16.2* %data, i64 %i, i32 1 + %tmp2 = load i16, i16* %tmp0, align 2 + %tmp3 = load i16, i16* %tmp1, align 2 + store i16 0, i16* %tmp0, align 2 + store i16 0, i16* %tmp1, align 2 + %i.next = add nuw nsw i64 %i, 1 + %cond = icmp slt i64 %i.next, %n + br i1 %cond, label %for.body, label %for.end + +for.end: + ret void +} + +%i32.2 = type {i32, i32} +define void @i32_factor_2(%i32.2* %data, i64 %n) { +entry: + br label %for.body + +; VF_2-LABEL: Checking a loop in "i32_factor_2" +; VF_2: Found an estimated cost of 2 for VF 2 For instruction: %tmp2 = load i32, i32* %tmp0, align 4 +; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp3 = load i32, i32* %tmp1, align 4 +; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp0, align 4 +; VF_2-NEXT: Found an estimated cost of 2 for VF 2 For instruction: store i32 0, i32* %tmp1, align 4 +; VF_4-LABEL: Checking a loop in "i32_factor_2" +; VF_4: Found an estimated cost of 2 for VF 4 For instruction: %tmp2 = load i32, i32* %tmp0, align 4 +; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp3 = load i32, i32* %tmp1, align 4 +; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp0, align 4 +; VF_4-NEXT: Found an estimated cost of 2 for VF 4 For instruction: store i32 0, i32* %tmp1, align 4 +for.body: + %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ] + %tmp0 = getelementptr inbounds %i32.2, %i32.2* %data, i64 %i, i32 0 + %tmp1 = getelementptr inbounds %i32.2, %i32.2* %data, i64 %i, i32 1 + %tmp2 = load i32, i32* %tmp0, align 4 + %tmp3 = load i32, i32* %tmp1, align 4 + store i32 0, i32* %tmp0, align 4 + store i32 0, i32* %tmp1, align 4 + %i.next = add nuw nsw i64 %i, 1 + %cond = icmp slt i64 %i.next, %n + br i1 %cond, label %for.body, label %for.end + +for.end: + ret void +}