6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2026-04-21 23:17:16 +00:00
Code Issues Projects Releases Wiki Activity

[SLSR] handle candidate form (B + i * S)

Browse Source 
Summary:
With this patch, SLSR may rewrite

S1: X = B + i * S
S2: Y = B + i' * S

to

S2: Y = X + (i' - i) * S

A secondary improvement: if (i' - i) is a power of 2, emit Y as X + (S << log(i' - i)). (S << log(i' -i)) is in a canonical form and thus more likely GVN'ed than (i' - i) * S.

Test Plan: slsr-add.ll

Reviewers: hfinkel, sanjoy, meheff, broune, eliben

Reviewed By: eliben

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D8983

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@235019 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Jingyue Wu
2015-04-15 16:46:13 +00:00
parent 6d9fd9bc70
commit d4ceea3837
4 changed files with 340 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/Transforms/StraightLineStrengthReduce/X86/no-slsr.ll
+16 -2
View File
@@ -5,8 +5,8 @@ target triple = "x86_64-unknown-linux-gnu"
; Do not perform SLSR on &input[s] and &input[s * 2] which fit into addressing
; modes of X86.
define i32 @slsr_gep(i32* %input, i64 %s) {
; CHECK-LABEL: @slsr_gep(
define i32 @no_slsr_gep(i32* %input, i64 %s) {
; CHECK-LABEL: @no_slsr_gep(
; v0 = input[0];
%p0 = getelementptr inbounds i32, i32* %input, i64 0
%v0 = load i32, i32* %p0
@@ -28,3 +28,17 @@ define i32 @slsr_gep(i32* %input, i64 %s) {
ret i32 %2
}
define void @no_slsr_add(i32 %b, i32 %s) {
; CHECK-LABEL: @no_slsr_add(
%1 = add i32 %b, %s
; CHECK: add i32 %b, %s
call void @foo(i32 %1)
%s2 = mul i32 %s, 2
; CHECK: %s2 = mul i32 %s, 2
%2 = add i32 %b, %s2
; CHECK: add i32 %b, %s2
call void @foo(i32 %2)
ret void
}
declare void @foo(i32 %a)
test/Transforms/StraightLineStrengthReduce/slsr-add.ll
+101
View File
@@ -0,0 +1,101 @@
; RUN: opt < %s -slsr -gvn -dce -S | FileCheck %s
target datalayout = "e-i64:64-v16:16-v32:32-n16:32:64"
define void @shl(i32 %b, i32 %s) {
; CHECK-LABEL: @shl(
%1 = add i32 %b, %s
; [[BASIS:%[a-zA-Z0-9]+]] = add i32 %b, %s
call void @foo(i32 %1)
%s2 = shl i32 %s, 1
%2 = add i32 %b, %s2
; add i32 [[BASIS]], %s
call void @foo(i32 %2)
ret void
}
define void @stride_is_2s(i32 %b, i32 %s) {
; CHECK-LABEL: @stride_is_2s(
%s2 = shl i32 %s, 1
; CHECK: %s2 = shl i32 %s, 1
%1 = add i32 %b, %s2
; CHECK: [[t1:%[a-zA-Z0-9]+]] = add i32 %b, %s2
call void @foo(i32 %1)
%s4 = shl i32 %s, 2
%2 = add i32 %b, %s4
; CHECK: [[t2:%[a-zA-Z0-9]+]] = add i32 [[t1]], %s2
call void @foo(i32 %2)
%s6 = mul i32 %s, 6
%3 = add i32 %b, %s6
; CHECK: add i32 [[t2]], %s2
call void @foo(i32 %3)
ret void
}
define void @stride_is_3s(i32 %b, i32 %s) {
; CHECK-LABEL: @stride_is_3s(
%1 = add i32 %s, %b
; CHECK: [[t1:%[a-zA-Z0-9]+]] = add i32 %s, %b
call void @foo(i32 %1)
%s4 = shl i32 %s, 2
%2 = add i32 %s4, %b
; CHECK: [[bump:%[a-zA-Z0-9]+]] = mul i32 %s, 3
; CHECK: [[t2:%[a-zA-Z0-9]+]] = add i32 [[t1]], [[bump]]
call void @foo(i32 %2)
%s7 = mul i32 %s, 7
%3 = add i32 %s7, %b
; CHECK: add i32 [[t2]], [[bump]]
call void @foo(i32 %3)
ret void
}
; foo(b + 6 * s);
; foo(b + 4 * s);
; foo(b + 2 * s);
; =>
; t1 = b + 6 * s;
; foo(t1);
; s2 = 2 * s;
; t2 = t1 - s2;
; foo(t2);
; t3 = t2 - s2;
; foo(t3);
define void @stride_is_minus_2s(i32 %b, i32 %s) {
; CHECK-LABEL: @stride_is_minus_2s(
%s6 = mul i32 %s, 6
%1 = add i32 %b, %s6
; CHECK: [[t1:%[a-zA-Z0-9]+]] = add i32 %b, %s6
; CHECK: call void @foo(i32 [[t1]])
call void @foo(i32 %1)
%s4 = shl i32 %s, 2
%2 = add i32 %b, %s4
; CHECK: [[bump:%[a-zA-Z0-9]+]] = shl i32 %s, 1
; CHECK: [[t2:%[a-zA-Z0-9]+]] = sub i32 [[t1]], [[bump]]
call void @foo(i32 %2)
; CHECK: call void @foo(i32 [[t2]])
%s2 = shl i32 %s, 1
%3 = add i32 %b, %s2
; CHECK: [[t3:%[a-zA-Z0-9]+]] = sub i32 [[t2]], [[bump]]
call void @foo(i32 %3)
; CHECK: call void @foo(i32 [[t3]])
ret void
}
; t = b + (s << 3);
; foo(t);
; foo(b + s);
;
; do not rewrite b + s to t - 7 * s because the latter is more complicated.
define void @simple_enough(i32 %b, i32 %s) {
; CHECK-LABEL: @simple_enough(
%s8 = shl i32 %s, 3
%1 = add i32 %b, %s8
call void @foo(i32 %1)
%2 = add i32 %b, %s
; CHECK: [[t:%[a-zA-Z0-9]+]] = add i32 %b, %s{{$}}
call void @foo(i32 %2)
; CHECK: call void @foo(i32 [[t]])
ret void
}
declare void @foo(i32 %a)
test/Transforms/StraightLineStrengthReduce/slsr-mul.ll
+1 -1
View File
@@ -79,7 +79,7 @@ define i32 @slsr3(i32 %b, i32 %s) {
%b1 = add i32 %b, 2
%mul1 = mul i32 %b1, %s
; CHECK: [[BUMP:%[a-zA-Z0-9]+]] = mul i32 %s, 2
; CHECK: [[BUMP:%[a-zA-Z0-9]+]] = shl i32 %s, 1
; CHECK: %mul1 = add i32 %mul0, [[BUMP]]
%v1 = call i32 @foo(i32 %mul1)