mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 04:02:41 +01:00
6b7238f3b4
Currently only "add nsw" are widened. This patch eliminates tons of "sext" instructions for 64 bit code (and the corresponding target code) in cases like:
int N = 100;
float **A;
void foo(int x0, int x1)
{
float * A_cur = &A[0][0];
float * A_next = &A[1][0];
for(int x = x0; x < x1; ++x).
{
// Currently only [x+N] case is widened. Others 2 cases lead to sext.
// This patch fixes it, so all 3 cases do not need sext.
const float div = A_cur[x + N] + A_cur[x - N] + A_cur[x * N];
A_next[x] = div;
}
}
...
> clang++ test.cpp -march=core-avx2 -Ofast -fno-unroll-loops -fno-tree-vectorize -S -o -
Differential Revision: http://reviews.llvm.org/D4695
llvm-svn: 216160
40 lines
1.3 KiB
LLVM
40 lines
1.3 KiB
LLVM
; RUN: opt < %s -indvars -S | FileCheck %s
|
|
; Test WidenIV::GetExtendedOperandRecurrence.
|
|
; %add, %sub and %mul should be extended to i64 because it is nsw, even though its
|
|
; sext cannot be hoisted outside the loop.
|
|
|
|
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"
|
|
|
|
define void @test() nounwind {
|
|
entry:
|
|
br i1 undef, label %for.body11, label %for.end285
|
|
|
|
for.body11: ; preds = %entry
|
|
%shl = shl i32 1, 1
|
|
%shl132 = shl i32 %shl, 1
|
|
br label %for.body153
|
|
|
|
for.body153: ; preds = %for.body153, %for.body11
|
|
br i1 undef, label %for.body170, label %for.body153
|
|
|
|
; CHECK: add nsw i64 %indvars.iv, 1
|
|
; CHECK: sub nsw i64 %indvars.iv, 2
|
|
; CHECK: mul nsw i64 %indvars.iv, 4
|
|
for.body170: ; preds = %for.body170, %for.body153
|
|
%i2.19 = phi i32 [ %add249, %for.body170 ], [ 0, %for.body153 ]
|
|
|
|
%add = add nsw i32 %i2.19, 1
|
|
%add.idxprom = sext i32 %add to i64
|
|
|
|
%sub = sub nsw i32 %i2.19, 2
|
|
%sub.idxprom = sext i32 %sub to i64
|
|
|
|
%mul = mul nsw i32 %i2.19, 4
|
|
%mul.idxprom = sext i32 %mul to i64
|
|
|
|
%add249 = add nsw i32 %i2.19, %shl132
|
|
br label %for.body170
|
|
for.end285: ; preds = %entry
|
|
ret void
|
|
}
|