Hans Wennborg 395f4f4b2a Switch lowering: extract jump tables and bit tests before building binary tree (PR22262)
This is a re-commit of r235101, which also fixes the problems with the previous patch:

- Switches with only a default case and non-fallthrough were handled incorrectly

- The previous patch tickled a bug in PowerPC Early-Return Creation which is fixed here.

> This is a major rewrite of the SelectionDAG switch lowering. The previous code
> would lower switches as a binary tre, discovering clusters of cases
> suitable for lowering by jump tables or bit tests as it went along. To increase
> the likelihood of finding jump tables, the binary tree pivot was selected to
> maximize case density on both sides of the pivot.
>
> By not selecting the pivot in the middle, the binary trees would not always
> be balanced, leading to performance problems in the generated code.
>
> This patch rewrites the lowering to search for clusters of cases
> suitable for jump tables or bit tests first, and then builds the binary
> tree around those clusters. This way, the binary tree will always be balanced.
>
> This has the added benefit of decoupling the different aspects of the lowering:
> tree building and jump table or bit tests finding are now easier to tweak
> separately.
>
> For example, this will enable us to balance the tree based on profile info
> in the future.
>
> The algorithm for finding jump tables is quadratic, whereas the previous algorithm
> was O(n log n) for common cases, and quadratic only in the worst-case. This
> doesn't seem to be major problem in practice, e.g. compiling a file consisting
> of a 10k-case switch was only 30% slower, and such large switches should be rare
> in practice. Compiling e.g. gcc.c showed no compile-time difference.  If this
> does turn out to be a problem, we could limit the search space of the algorithm.
>
> This commit also disables all optimizations during switch lowering in -O0.
>
> Differential Revision: http://reviews.llvm.org/D8649

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@235560 91177308-0d34-0410-b5e6-96231b3b80d8
2015-04-22 23:14:56 +00:00

61 lines
2.0 KiB
LLVM

; RUN: llc -mcpu=pwr7 -code-model=medium <%s | FileCheck %s
; RUN: llc -mcpu=pwr7 -code-model=large <%s | FileCheck %s
; Test correct code generation for medium and large code model
; for loading the address of a jump table from the TOC.
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-f128:128:128-v128:128:128-n32:64"
target triple = "powerpc64-unknown-linux-gnu"
define signext i32 @test_jump_table(i32 signext %i) nounwind {
entry:
%i.addr = alloca i32, align 4
store i32 %i, i32* %i.addr, align 4
%0 = load i32, i32* %i.addr, align 4
switch i32 %0, label %sw.default [
i32 3, label %sw.bb
i32 4, label %sw.bb1
i32 5, label %sw.bb2
i32 6, label %sw.bb3
]
sw.default: ; preds = %entry
br label %sw.epilog
sw.bb: ; preds = %entry
%1 = load i32, i32* %i.addr, align 4
%mul = mul nsw i32 %1, 7
store i32 %mul, i32* %i.addr, align 4
br label %sw.bb1
sw.bb1: ; preds = %entry, %sw.bb
%2 = load i32, i32* %i.addr, align 4
%dec = add nsw i32 %2, -1
store i32 %dec, i32* %i.addr, align 4
br label %sw.bb2
sw.bb2: ; preds = %entry, %sw.bb1
%3 = load i32, i32* %i.addr, align 4
%add = add nsw i32 %3, 3
store i32 %add, i32* %i.addr, align 4
br label %sw.bb3
sw.bb3: ; preds = %entry, %sw.bb2
%4 = load i32, i32* %i.addr, align 4
%shl = shl i32 %4, 1
store i32 %shl, i32* %i.addr, align 4
br label %sw.epilog
sw.epilog: ; preds = %sw.bb3, %sw.default
%5 = load i32, i32* %i.addr, align 4
ret i32 %5
}
; CHECK-LABEL: test_jump_table:
; CHECK: addis [[REG1:[0-9]+]], 2, .LC[[TOCNUM:[0-9]+]]@toc@ha
; CHECK: ld [[REG2:[0-9]+]], .LC[[TOCNUM]]@toc@l([[REG1]])
; CHECK: ldx {{[0-9]+}}, {{[0-9]+}}, [[REG2]]
; CHECK: .section .toc
; CHECK: .LC[[TOCNUM]]:
; CHECK: .tc {{[a-z0-9A-Z_.]+}}[TC],{{[a-z0-9A-Z_.]+}}