From 62d67d9e7c9c50bfed7d73aa3bfd769c61d5e8e9 Mon Sep 17 00:00:00 2001 From: Roman Lebedev Date: Wed, 6 Oct 2021 22:51:27 +0300 Subject: [PATCH] [NFC][X86][LoopVectorize] Autogenerate check lines in a few tests for ease of updating For D111220 --- .../Transforms/LoopVectorize/X86/gather-cost.ll | 66 ++++++++++++++- .../Transforms/LoopVectorize/X86/parallel-loops.ll | 99 ++++++++++++++++++++-- .../LoopVectorize/X86/strided_load_cost.ll | 26 +++--- .../LoopVectorize/X86/x86_fp80-vector-store.ll | 21 ++++- 4 files changed, 188 insertions(+), 24 deletions(-) diff --git a/llvm/test/Transforms/LoopVectorize/X86/gather-cost.ll b/llvm/test/Transforms/LoopVectorize/X86/gather-cost.ll index fd4981e..1126acf 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/gather-cost.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/gather-cost.ll @@ -1,3 +1,4 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; RUN: opt -loop-vectorize -mtriple=x86_64-apple-macosx -S -mcpu=corei7-avx -enable-interleaved-mem-accesses=false < %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" @@ -14,9 +15,72 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f3 ; expensive. This function represents a point where vectorization starts to ; become beneficial. ; Make sure we are conservative and don't vectorize it. -; CHECK-NOT: x float> define void @_Z4testmm(i64 %size, i64 %offset) { +; CHECK-LABEL: @_Z4testmm( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[CMP53:%.*]] = icmp eq i64 [[SIZE:%.*]], 0 +; CHECK-NEXT: br i1 [[CMP53]], label [[FOR_END:%.*]], label [[FOR_BODY_LR_PH:%.*]] +; CHECK: for.body.lr.ph: +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[R_057:%.*]] = phi float [ 0.000000e+00, [[FOR_BODY_LR_PH]] ], [ [[ADD10:%.*]], [[FOR_BODY]] ] +; CHECK-NEXT: [[G_056:%.*]] = phi float [ 0.000000e+00, [[FOR_BODY_LR_PH]] ], [ [[ADD20:%.*]], [[FOR_BODY]] ] +; CHECK-NEXT: [[V_055:%.*]] = phi i64 [ 0, [[FOR_BODY_LR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ] +; CHECK-NEXT: [[B_054:%.*]] = phi float [ 0.000000e+00, [[FOR_BODY_LR_PH]] ], [ [[ADD30:%.*]], [[FOR_BODY]] ] +; CHECK-NEXT: [[ADD:%.*]] = add i64 [[V_055]], [[OFFSET:%.*]] +; CHECK-NEXT: [[MUL:%.*]] = mul i64 [[ADD]], 3 +; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [1536 x float], [1536 x float]* @src_data, i64 0, i64 [[MUL]] +; CHECK-NEXT: [[TMP0:%.*]] = load float, float* [[ARRAYIDX]], align 4 +; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds [512 x float], [512 x float]* @kernel, i64 0, i64 [[V_055]] +; CHECK-NEXT: [[TMP1:%.*]] = load float, float* [[ARRAYIDX2]], align 4 +; CHECK-NEXT: [[MUL3:%.*]] = fmul fast float [[TMP0]], [[TMP1]] +; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds [512 x float], [512 x float]* @kernel2, i64 0, i64 [[V_055]] +; CHECK-NEXT: [[TMP2:%.*]] = load float, float* [[ARRAYIDX4]], align 4 +; CHECK-NEXT: [[MUL5:%.*]] = fmul fast float [[MUL3]], [[TMP2]] +; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds [512 x float], [512 x float]* @kernel3, i64 0, i64 [[V_055]] +; CHECK-NEXT: [[TMP3:%.*]] = load float, float* [[ARRAYIDX6]], align 4 +; CHECK-NEXT: [[MUL7:%.*]] = fmul fast float [[MUL5]], [[TMP3]] +; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds [512 x float], [512 x float]* @kernel4, i64 0, i64 [[V_055]] +; CHECK-NEXT: [[TMP4:%.*]] = load float, float* [[ARRAYIDX8]], align 4 +; CHECK-NEXT: [[MUL9:%.*]] = fmul fast float [[MUL7]], [[TMP4]] +; CHECK-NEXT: [[ADD10]] = fadd fast float [[R_057]], [[MUL9]] +; CHECK-NEXT: [[ARRAYIDX_SUM:%.*]] = add i64 [[MUL]], 1 +; CHECK-NEXT: [[ARRAYIDX11:%.*]] = getelementptr inbounds [1536 x float], [1536 x float]* @src_data, i64 0, i64 [[ARRAYIDX_SUM]] +; CHECK-NEXT: [[TMP5:%.*]] = load float, float* [[ARRAYIDX11]], align 4 +; CHECK-NEXT: [[MUL13:%.*]] = fmul fast float [[TMP1]], [[TMP5]] +; CHECK-NEXT: [[MUL15:%.*]] = fmul fast float [[TMP2]], [[MUL13]] +; CHECK-NEXT: [[MUL17:%.*]] = fmul fast float [[TMP3]], [[MUL15]] +; CHECK-NEXT: [[MUL19:%.*]] = fmul fast float [[TMP4]], [[MUL17]] +; CHECK-NEXT: [[ADD20]] = fadd fast float [[G_056]], [[MUL19]] +; CHECK-NEXT: [[ARRAYIDX_SUM52:%.*]] = add i64 [[MUL]], 2 +; CHECK-NEXT: [[ARRAYIDX21:%.*]] = getelementptr inbounds [1536 x float], [1536 x float]* @src_data, i64 0, i64 [[ARRAYIDX_SUM52]] +; CHECK-NEXT: [[TMP6:%.*]] = load float, float* [[ARRAYIDX21]], align 4 +; CHECK-NEXT: [[MUL23:%.*]] = fmul fast float [[TMP1]], [[TMP6]] +; CHECK-NEXT: [[MUL25:%.*]] = fmul fast float [[TMP2]], [[MUL23]] +; CHECK-NEXT: [[MUL27:%.*]] = fmul fast float [[TMP3]], [[MUL25]] +; CHECK-NEXT: [[MUL29:%.*]] = fmul fast float [[TMP4]], [[MUL27]] +; CHECK-NEXT: [[ADD30]] = fadd fast float [[B_054]], [[MUL29]] +; CHECK-NEXT: [[INC]] = add i64 [[V_055]], 1 +; CHECK-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[INC]], [[SIZE]] +; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_BODY]], label [[FOR_COND_FOR_END_CRIT_EDGE:%.*]] +; CHECK: for.cond.for.end_crit_edge: +; CHECK-NEXT: [[ADD30_LCSSA:%.*]] = phi float [ [[ADD30]], [[FOR_BODY]] ] +; CHECK-NEXT: [[ADD20_LCSSA:%.*]] = phi float [ [[ADD20]], [[FOR_BODY]] ] +; CHECK-NEXT: [[ADD10_LCSSA:%.*]] = phi float [ [[ADD10]], [[FOR_BODY]] ] +; CHECK-NEXT: [[PHITMP:%.*]] = fptoui float [[ADD10_LCSSA]] to i8 +; CHECK-NEXT: [[PHITMP60:%.*]] = fptoui float [[ADD20_LCSSA]] to i8 +; CHECK-NEXT: [[PHITMP61:%.*]] = fptoui float [[ADD30_LCSSA]] to i8 +; CHECK-NEXT: br label [[FOR_END]] +; CHECK: for.end: +; CHECK-NEXT: [[R_0_LCSSA:%.*]] = phi i8 [ [[PHITMP]], [[FOR_COND_FOR_END_CRIT_EDGE]] ], [ 0, [[ENTRY:%.*]] ] +; CHECK-NEXT: [[G_0_LCSSA:%.*]] = phi i8 [ [[PHITMP60]], [[FOR_COND_FOR_END_CRIT_EDGE]] ], [ 0, [[ENTRY]] ] +; CHECK-NEXT: [[B_0_LCSSA:%.*]] = phi i8 [ [[PHITMP61]], [[FOR_COND_FOR_END_CRIT_EDGE]] ], [ 0, [[ENTRY]] ] +; CHECK-NEXT: store i8 [[R_0_LCSSA]], i8* @r_, align 1 +; CHECK-NEXT: store i8 [[G_0_LCSSA]], i8* @g_, align 1 +; CHECK-NEXT: store i8 [[B_0_LCSSA]], i8* @b_, align 1 +; CHECK-NEXT: ret void +; entry: %cmp53 = icmp eq i64 %size, 0 br i1 %cmp53, label %for.end, label %for.body.lr.ph diff --git a/llvm/test/Transforms/LoopVectorize/X86/parallel-loops.ll b/llvm/test/Transforms/LoopVectorize/X86/parallel-loops.ll index be77885..c02d61f 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/parallel-loops.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/parallel-loops.ll @@ -1,3 +1,4 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -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" @@ -12,9 +13,29 @@ target triple = "x86_64-unknown-linux-gnu" ; } ;} -;CHECK-LABEL: @loop( -;CHECK-NOT: <4 x i32> define void @loop(i32* nocapture %a, i32* nocapture %b) nounwind uwtable { +; CHECK-LABEL: @loop( +; CHECK-NEXT: entry: +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ] +; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]] +; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4 +; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]] +; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4 +; CHECK-NEXT: [[IDXPROM3:%.*]] = sext i32 [[TMP1]] to i64 +; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[IDXPROM3]] +; CHECK-NEXT: store i32 [[TMP0]], i32* [[ARRAYIDX4]], align 4 +; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add i64 [[INDVARS_IV]], 1 +; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDVARS_IV_NEXT]] +; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX6]], align 4 +; CHECK-NEXT: store i32 [[TMP2]], i32* [[ARRAYIDX2]], align 4 +; CHECK-NEXT: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32 +; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], 512 +; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]] +; CHECK: for.end: +; CHECK-NEXT: ret void +; entry: br label %for.body @@ -42,9 +63,55 @@ for.end: ; preds = %for.body ; The same loop with parallel loop metadata added to the loop branch ; and the memory instructions. -;CHECK-LABEL: @parallel_loop( -;CHECK: <4 x i32> define void @parallel_loop(i32* nocapture %a, i32* nocapture %b) nounwind uwtable { +; CHECK-LABEL: @parallel_loop( +; CHECK-NEXT: entry: +; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]] +; CHECK: vector.ph: +; CHECK-NEXT: br label [[VECTOR_BODY:%.*]] +; CHECK: vector.body: +; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDEX]] +; CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[TMP0]] to <4 x i32>* +; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 4, !llvm.access.group !0 +; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDEX]] +; CHECK-NEXT: [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>* +; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4, !llvm.access.group !0 +; CHECK-NEXT: [[TMP4:%.*]] = sext <4 x i32> [[WIDE_LOAD1]] to <4 x i64> +; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x i64> [[TMP4]], i32 0 +; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP5]] +; CHECK-NEXT: [[TMP7:%.*]] = extractelement <4 x i64> [[TMP4]], i32 1 +; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP7]] +; CHECK-NEXT: [[TMP9:%.*]] = extractelement <4 x i64> [[TMP4]], i32 2 +; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP9]] +; CHECK-NEXT: [[TMP11:%.*]] = extractelement <4 x i64> [[TMP4]], i32 3 +; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP11]] +; CHECK-NEXT: [[TMP13:%.*]] = extractelement <4 x i32> [[WIDE_LOAD]], i32 0 +; CHECK-NEXT: store i32 [[TMP13]], i32* [[TMP6]], align 4, !llvm.access.group !1 +; CHECK-NEXT: [[TMP14:%.*]] = extractelement <4 x i32> [[WIDE_LOAD]], i32 1 +; CHECK-NEXT: store i32 [[TMP14]], i32* [[TMP8]], align 4, !llvm.access.group !1 +; CHECK-NEXT: [[TMP15:%.*]] = extractelement <4 x i32> [[WIDE_LOAD]], i32 2 +; CHECK-NEXT: store i32 [[TMP15]], i32* [[TMP10]], align 4, !llvm.access.group !1 +; CHECK-NEXT: [[TMP16:%.*]] = extractelement <4 x i32> [[WIDE_LOAD]], i32 3 +; CHECK-NEXT: store i32 [[TMP16]], i32* [[TMP12]], align 4, !llvm.access.group !1 +; CHECK-NEXT: [[TMP17:%.*]] = or i64 [[INDEX]], 1 +; CHECK-NEXT: [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[TMP17]] +; CHECK-NEXT: [[TMP19:%.*]] = bitcast i32* [[TMP18]] to <4 x i32>* +; CHECK-NEXT: [[WIDE_LOAD2:%.*]] = load <4 x i32>, <4 x i32>* [[TMP19]], align 4, !llvm.access.group !0 +; CHECK-NEXT: [[TMP20:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>* +; CHECK-NEXT: store <4 x i32> [[WIDE_LOAD2]], <4 x i32>* [[TMP20]], align 4, !llvm.access.group !0 +; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4 +; CHECK-NEXT: [[TMP21:%.*]] = icmp eq i64 [[INDEX_NEXT]], 512 +; CHECK-NEXT: br i1 [[TMP21]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]] +; CHECK: middle.block: +; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]] +; CHECK: scalar.ph: +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.body: +; CHECK-NEXT: br i1 undef, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]] +; CHECK: for.end: +; CHECK-NEXT: ret void +; entry: br label %for.body @@ -74,10 +141,30 @@ for.end: ; preds = %for.body ; The same loop with an illegal parallel loop metadata: the memory ; accesses refer to a different loop's identifier. -;CHECK-LABEL: @mixed_metadata( -;CHECK-NOT: <4 x i32> define void @mixed_metadata(i32* nocapture %a, i32* nocapture %b) nounwind uwtable { +; CHECK-LABEL: @mixed_metadata( +; CHECK-NEXT: entry: +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ] +; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]] +; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]], align 4, !llvm.access.group !7 +; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]] +; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4, !llvm.access.group !7 +; CHECK-NEXT: [[IDXPROM3:%.*]] = sext i32 [[TMP1]] to i64 +; CHECK-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[IDXPROM3]] +; CHECK-NEXT: store i32 [[TMP0]], i32* [[ARRAYIDX4]], align 4, !llvm.access.group !8 +; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add i64 [[INDVARS_IV]], 1 +; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDVARS_IV_NEXT]] +; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[ARRAYIDX6]], align 4, !llvm.access.group !7 +; CHECK-NEXT: store i32 [[TMP2]], i32* [[ARRAYIDX2]], align 4, !llvm.access.group !7 +; CHECK-NEXT: [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32 +; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], 512 +; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]] +; CHECK: for.end: +; CHECK-NEXT: ret void +; entry: br label %for.body diff --git a/llvm/test/Transforms/LoopVectorize/X86/strided_load_cost.ll b/llvm/test/Transforms/LoopVectorize/X86/strided_load_cost.ll index fea7913..6fc092e 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/strided_load_cost.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/strided_load_cost.ll @@ -30,7 +30,7 @@ define i32 @matrix_row_col([100 x i32]* nocapture readonly %data, i32 %i, i32 %j ; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds [100 x i32], [100 x i32]* [[DATA:%.*]], i64 [[IDXPROM]], i64 [[TMP0]] ; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[TMP8]], i32 0 ; CHECK-NEXT: [[TMP10:%.*]] = bitcast i32* [[TMP9]] to <8 x i32>* -; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <8 x i32>, <8 x i32>* [[TMP10]], align 4, [[TBAA1:!tbaa !.*]] +; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <8 x i32>, <8 x i32>* [[TMP10]], align 4, !tbaa [[TBAA1:![0-9]+]] ; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds [100 x i32], [100 x i32]* [[DATA]], i64 [[TMP0]], i64 [[IDXPROM5]] ; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds [100 x i32], [100 x i32]* [[DATA]], i64 [[TMP1]], i64 [[IDXPROM5]] ; CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds [100 x i32], [100 x i32]* [[DATA]], i64 [[TMP2]], i64 [[IDXPROM5]] @@ -39,14 +39,14 @@ define i32 @matrix_row_col([100 x i32]* nocapture readonly %data, i32 %i, i32 %j ; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds [100 x i32], [100 x i32]* [[DATA]], i64 [[TMP5]], i64 [[IDXPROM5]] ; CHECK-NEXT: [[TMP17:%.*]] = getelementptr inbounds [100 x i32], [100 x i32]* [[DATA]], i64 [[TMP6]], i64 [[IDXPROM5]] ; CHECK-NEXT: [[TMP18:%.*]] = getelementptr inbounds [100 x i32], [100 x i32]* [[DATA]], i64 [[TMP7]], i64 [[IDXPROM5]] -; CHECK-NEXT: [[TMP19:%.*]] = load i32, i32* [[TMP11]], align 4, [[TBAA1]] -; CHECK-NEXT: [[TMP20:%.*]] = load i32, i32* [[TMP12]], align 4, [[TBAA1]] -; CHECK-NEXT: [[TMP21:%.*]] = load i32, i32* [[TMP13]], align 4, [[TBAA1]] -; CHECK-NEXT: [[TMP22:%.*]] = load i32, i32* [[TMP14]], align 4, [[TBAA1]] -; CHECK-NEXT: [[TMP23:%.*]] = load i32, i32* [[TMP15]], align 4, [[TBAA1]] -; CHECK-NEXT: [[TMP24:%.*]] = load i32, i32* [[TMP16]], align 4, [[TBAA1]] -; CHECK-NEXT: [[TMP25:%.*]] = load i32, i32* [[TMP17]], align 4, [[TBAA1]] -; CHECK-NEXT: [[TMP26:%.*]] = load i32, i32* [[TMP18]], align 4, [[TBAA1]] +; CHECK-NEXT: [[TMP19:%.*]] = load i32, i32* [[TMP11]], align 4, !tbaa [[TBAA1]] +; CHECK-NEXT: [[TMP20:%.*]] = load i32, i32* [[TMP12]], align 4, !tbaa [[TBAA1]] +; CHECK-NEXT: [[TMP21:%.*]] = load i32, i32* [[TMP13]], align 4, !tbaa [[TBAA1]] +; CHECK-NEXT: [[TMP22:%.*]] = load i32, i32* [[TMP14]], align 4, !tbaa [[TBAA1]] +; CHECK-NEXT: [[TMP23:%.*]] = load i32, i32* [[TMP15]], align 4, !tbaa [[TBAA1]] +; CHECK-NEXT: [[TMP24:%.*]] = load i32, i32* [[TMP16]], align 4, !tbaa [[TBAA1]] +; CHECK-NEXT: [[TMP25:%.*]] = load i32, i32* [[TMP17]], align 4, !tbaa [[TBAA1]] +; CHECK-NEXT: [[TMP26:%.*]] = load i32, i32* [[TMP18]], align 4, !tbaa [[TBAA1]] ; CHECK-NEXT: [[TMP27:%.*]] = insertelement <8 x i32> poison, i32 [[TMP19]], i32 0 ; CHECK-NEXT: [[TMP28:%.*]] = insertelement <8 x i32> [[TMP27]], i32 [[TMP20]], i32 1 ; CHECK-NEXT: [[TMP29:%.*]] = insertelement <8 x i32> [[TMP28]], i32 [[TMP21]], i32 2 @@ -60,7 +60,7 @@ define i32 @matrix_row_col([100 x i32]* nocapture readonly %data, i32 %i, i32 %j ; CHECK-NEXT: [[TMP37]] = add <8 x i32> [[TMP36]], [[TMP35]] ; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8 ; CHECK-NEXT: [[TMP38:%.*]] = icmp eq i64 [[INDEX_NEXT]], 96 -; CHECK-NEXT: br i1 [[TMP38]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP5:!llvm.loop !.*]] +; CHECK-NEXT: br i1 [[TMP38]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]] ; CHECK: middle.block: ; CHECK-NEXT: [[TMP39:%.*]] = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> [[TMP37]]) ; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 100, 96 @@ -76,15 +76,15 @@ define i32 @matrix_row_col([100 x i32]* nocapture readonly %data, i32 %i, i32 %j ; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ] ; CHECK-NEXT: [[SUM_015:%.*]] = phi i32 [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[ADD7]], [[FOR_BODY]] ] ; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds [100 x i32], [100 x i32]* [[DATA]], i64 [[IDXPROM]], i64 [[INDVARS_IV]] -; CHECK-NEXT: [[TMP40:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4, [[TBAA1]] +; CHECK-NEXT: [[TMP40:%.*]] = load i32, i32* [[ARRAYIDX2]], align 4, !tbaa [[TBAA1]] ; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds [100 x i32], [100 x i32]* [[DATA]], i64 [[INDVARS_IV]], i64 [[IDXPROM5]] -; CHECK-NEXT: [[TMP41:%.*]] = load i32, i32* [[ARRAYIDX6]], align 4, [[TBAA1]] +; CHECK-NEXT: [[TMP41:%.*]] = load i32, i32* [[ARRAYIDX6]], align 4, !tbaa [[TBAA1]] ; CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP41]], [[TMP40]] ; CHECK-NEXT: [[ADD:%.*]] = add i32 [[SUM_015]], 4 ; CHECK-NEXT: [[ADD7]] = add i32 [[ADD]], [[MUL]] ; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1 ; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 100 -; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], [[LOOP7:!llvm.loop !.*]] +; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]] ; entry: %idxprom = sext i32 %i to i64 diff --git a/llvm/test/Transforms/LoopVectorize/X86/x86_fp80-vector-store.ll b/llvm/test/Transforms/LoopVectorize/X86/x86_fp80-vector-store.ll index 0debb33..5c9077f 100644 --- a/llvm/test/Transforms/LoopVectorize/X86/x86_fp80-vector-store.ll +++ b/llvm/test/Transforms/LoopVectorize/X86/x86_fp80-vector-store.ll @@ -1,3 +1,4 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; RUN: opt -O3 -loop-vectorize -force-vector-interleave=1 -force-vector-width=2 -S < %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" @@ -5,12 +6,24 @@ target triple = "x86_64-apple-macosx10.7.0" @x = common global [1024 x x86_fp80] zeroinitializer, align 16 -;CHECK-LABEL: @example( -;CHECK-NOT: bitcast x86_fp80* {{%[^ ]+}} to <{{[2-9][0-9]*}} x x86_fp80>* -;CHECK: store -;CHECK: ret void define void @example() nounwind ssp uwtable { +; CHECK-LABEL: @example( +; CHECK-NEXT: entry: +; CHECK-NEXT: br label [[VECTOR_BODY:%.*]] +; CHECK: vector.body: +; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ] +; CHECK-NEXT: [[TMP0:%.*]] = or i64 [[INDEX]], 1 +; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [1024 x x86_fp80], [1024 x x86_fp80]* @x, i64 0, i64 [[INDEX]] +; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds [1024 x x86_fp80], [1024 x x86_fp80]* @x, i64 0, i64 [[TMP0]] +; CHECK-NEXT: store x86_fp80 0xK3FFF8000000000000000, x86_fp80* [[TMP1]], align 16 +; CHECK-NEXT: store x86_fp80 0xK3FFF8000000000000000, x86_fp80* [[TMP2]], align 16 +; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2 +; CHECK-NEXT: [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024 +; CHECK-NEXT: br i1 [[TMP3]], label [[FOR_END:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]] +; CHECK: for.end: +; CHECK-NEXT: ret void +; entry: br label %for.body -- 2.7.4