maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

BlockGenerator: Simplify code generated for scop statements 

After having generated a new user statement a couple of inefficient or trivially
dead instructions may remain. This commit runs instruction simplification over
the newly generated blocks to ensure unneeded instructions are removed right
away.

This commit does not yet add simplification for non-affine subregions.

llvm-svn: 248681
This commit is contained in:
Tobias Grosser 2015-09-27 11:17:22 +00:00
parent aabc45b5ad
commit 1b9d25a42d
3 changed files with 10 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
polly/lib/CodeGen/BlockGenerators.cpp
View File

@ -28,6 +28,7 @@
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Module.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/Local.h"
#include "isl/aff.h"
#include "isl/ast.h"
#include "isl/ast_build.h"
@ -293,6 +294,10 @@ void BlockGenerator::copyStmt(ScopStmt &Stmt, LoopToScevMapT &LTS,
BasicBlock *BB = Stmt.getBasicBlock();
copyBB(Stmt, BB, BBMap, LTS, NewAccesses);
auto CopyBB = Builder.GetInsertBlock();
SimplifyInstructionsInBlock(CopyBB, nullptr);
Builder.SetInsertPoint(CopyBB->getTerminator());
}
BasicBlock *BlockGenerator::splitBB(BasicBlock *BB) {

3
polly/test/Isl/CodeGen/MemAccess/codegen_address_space.ll
View File

@ -40,5 +40,4 @@ for.end: ; preds = %for.cond
}
; CHECK: %polly.access.cast.A = bitcast [100 x i32] addrspace(5)* %A to i32 addrspace(5)*
; CHECK: %polly.access.A = getelementptr i32, i32 addrspace(5)* %polly.access.cast.A, i64 0
; CHECK: %tmp2_p_scalar_ = load i32, i32 addrspace(5)* %polly.access.A, align 4, !alias.scope !0, !noalias !2
; CHECK: %tmp2_p_scalar_ = load i32, i32 addrspace(5)* %polly.access.cast.A, align 4, !alias.scope !0, !noalias !2

8
polly/test/Isl/CodeGen/OpenMP/new_multidim_access.ll
View File

@ -20,14 +20,14 @@
; CHECK: new: [n, m] -> { Stmt_bb4[i0, i1] -> MemRef_A[i0, 43 + i1] };
; IR: %polly.access.mul.polly.subfunc.arg.A = mul i64 %polly.indvar, %polly.subfunc.arg.m
; IR: %8 = add nsw i64 %polly.indvar5, 13
; IR: %polly.access.add.polly.subfunc.arg.A = add i64 %polly.access.mul.polly.subfunc.arg.A, %8
; IR: %6 = add nsw i64 %polly.indvar5, 13
; IR: %polly.access.add.polly.subfunc.arg.A = add i64 %polly.access.mul.polly.subfunc.arg.A, %6
; IR: %polly.access.polly.subfunc.arg.A = getelementptr float, float* %polly.subfunc.arg.A, i64 %polly.access.add.polly.subfunc.arg.A
; IR: %tmp10_p_scalar_ = load float, float* %polly.access.polly.subfunc.arg.A, align 4, !alias.scope !0, !noalias !2, !llvm.mem.parallel_loop_access !3
; IR: %polly.access.mul.polly.subfunc.arg.A9 = mul i64 %polly.indvar, %polly.subfunc.arg.m
; IR: %9 = add nsw i64 %polly.indvar5, 43
; IR: %polly.access.add.polly.subfunc.arg.A10 = add i64 %polly.access.mul.polly.subfunc.arg.A9, %9
; IR: %7 = add nsw i64 %polly.indvar5, 43
; IR: %polly.access.add.polly.subfunc.arg.A10 = add i64 %polly.access.mul.polly.subfunc.arg.A9, %7
; IR: %polly.access.polly.subfunc.arg.A11 = getelementptr float, float* %polly.subfunc.arg.A, i64 %polly.access.add.polly.subfunc.arg.A10
; IR: store float %p_tmp11, float* %polly.access.polly.subfunc.arg.A11, align 4, !alias.scope !0, !noalias !2, !llvm.mem.parallel_
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"