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

[DAGCombiner] Fold together mul and shl when both are by a constant 

This is intended to improve code generation for GEPs, as the index value is
shifted by the element size and in GEPs of multi-dimensional arrays the index
of higher dimensions is multiplied by the lower dimension size.

Differential Revision: http://reviews.llvm.org/D12197

llvm-svn: 245689
This commit is contained in:
John Brawn 2015-08-21 10:48:17 +00:00
parent 2ecb118a1d
commit eab960c46f
2 changed files with 85 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -4455,6 +4455,14 @@ SDValue DAGCombiner::visitSHL(SDNode *N) {
return DAG.getNode(ISD::ADD, SDLoc(N), VT, Shl0, Shl1);
}
// fold (shl (mul x, c1), c2) -> (mul x, c1 << c2)
if (N1C && N0.getOpcode() == ISD::MUL && N0.getNode()->hasOneUse()) {
if (ConstantSDNode *N0C1 = isConstOrConstSplat(N0.getOperand(1))) {
SDValue Folded = DAG.FoldConstantArithmetic(ISD::SHL, SDLoc(N1), VT, N0C1, N1C);
return DAG.getNode(ISD::MUL, SDLoc(N), VT, N0.getOperand(0), Folded);
}
}
if (N1C && !N1C->isOpaque())
if (SDValue NewSHL = visitShiftByConstant(N, N1C))
return NewSHL;

77
llvm/test/CodeGen/ARM/gep-optimization.ll Normal file
View File

@ -0,0 +1,77 @@
; RUN: llc < %s -mtriple=armv7a-eabi | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-AT2
; RUN: llc < %s -mtriple=thumbv7m-eabi | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-AT2
; RUN: llc < %s -mtriple=thumbv6m-eabi | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-T1
; This test checks that various kinds of getelementptr are all optimised to a
; simple multiply plus add, with the add being done by a register offset if the
; result is used in a load.
; CHECK-LABEL: calc_1d:
; CHECK: mov{{s?}} [[REG1:r[0-9]+]], #84
; CHECK-AT2: mla r0, r1, [[REG1]], r0
; CHECK-T1: muls [[REG2:r[0-9]+]], r1, [[REG1]]
; CHECK-T1: adds r0, r0, [[REG2]]
define i32* @calc_1d(i32* %p, i32 %n) {
entry:
%mul = mul nsw i32 %n, 21
%add.ptr = getelementptr inbounds i32, i32* %p, i32 %mul
ret i32* %add.ptr
}
; CHECK-LABEL: load_1d:
; CHECK: mov{{s?}} [[REG1:r[0-9]+]], #84
; CHECK: mul{{s?}} [[REG2:r[0-9]+]],{{( r1,)?}} [[REG1]]{{(, r1)?}}
; CHECK: ldr r0, [r0, [[REG2]]]
define i32 @load_1d(i32* %p, i32 %n) #1 {
entry:
%mul = mul nsw i32 %n, 21
%arrayidx = getelementptr inbounds i32, i32* %p, i32 %mul
%0 = load i32, i32* %arrayidx, align 4
ret i32 %0
}
; CHECK-LABEL: calc_2d_a:
; CHECK: mov{{s?}} [[REG1:r[0-9]+]], #84
; CHECK-AT2: mla r0, r1, [[REG1]], r0
; CHECK-T1: muls [[REG2:r[0-9]+]], r1, [[REG1]]
; CHECK-T1: adds r0, r0, [[REG2]]
define i32* @calc_2d_a([100 x i32]* %p, i32 %n) {
entry:
%mul = mul nsw i32 %n, 21
%arrayidx1 = getelementptr inbounds [100 x i32], [100 x i32]* %p, i32 0, i32 %mul
ret i32* %arrayidx1
}
; CHECK-LABEL: load_2d_a:
; CHECK: mov{{s?}} [[REG1:r[0-9]+]], #84
; CHECK: mul{{s?}} [[REG2:r[0-9]+]],{{( r1,)?}} [[REG1]]{{(, r1)?}}
; CHECK: ldr r0, [r0, [[REG2]]]
define i32 @load_2d_a([100 x i32]* %p, i32 %n) #1 {
entry:
%mul = mul nsw i32 %n, 21
%arrayidx1 = getelementptr inbounds [100 x i32], [100 x i32]* %p, i32 0, i32 %mul
%0 = load i32, i32* %arrayidx1, align 4
ret i32 %0
}
; CHECK-LABEL: calc_2d_b:
; CHECK: mov{{s?}} [[REG1:r[0-9]+]], #84
; CHECK-AT2: mla r0, r1, [[REG1]], r0
; CHECK-T1: muls [[REG2:r[0-9]+]], r1, [[REG1]]
; CHECK-T1: adds r0, r0, [[REG2]]
define i32* @calc_2d_b([21 x i32]* %p, i32 %n) {
entry:
%arrayidx1 = getelementptr inbounds [21 x i32], [21 x i32]* %p, i32 %n, i32 0
ret i32* %arrayidx1
}
; CHECK-LABEL: load_2d_b:
; CHECK: mov{{s?}} [[REG1:r[0-9]+]], #84
; CHECK: mul{{s?}} [[REG2:r[0-9]+]],{{( r1,)?}} [[REG1]]{{(, r1)?}}
; CHECK: ldr r0, [r0, [[REG2]]]
define i32 @load_2d_b([21 x i32]* %p, i32 %n) {
entry:
%arrayidx1 = getelementptr inbounds [21 x i32], [21 x i32]* %p, i32 %n, i32 0
%0 = load i32, i32* %arrayidx1, align 4
ret i32 %0
}