1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-02-01 05:01:59 +01:00
llvm-mirror/test/CodeGen/ARM/t2-shrink-ldrpost.ll
Nicholas Guy f4899fdead [ARM] Rearrange SizeReduction when using -Oz
Move the Thumb2SizeReduce pass to before IfConversion when optimising
for minimal code size.

Running the Thumb2SizeReduction pass before IfConversionallows T1
instructions to propagate to the final output, rather than the
ifConverter modifying T2 instructions and preventing them from being
reduced later.

This change does introduce a regression regarding execution time, so
it's only applied when optimising for size.

Running the LLVM Test Suite with this change produces a geomean
difference of -0.1% for the size..text metric.

Differential Revision: https://reviews.llvm.org/D82439
2020-07-02 09:19:38 +01:00

77 lines
2.7 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s | FileCheck %s
target datalayout = "e-m:e-p:32:32-i1:8:32-i8:8:32-i16:16:32-f64:32:64-v64:32:64-v128:32:128-a:0:32-n32-S32"
target triple = "thumbv7m--linux-gnu"
; NOTE: When optimising for minimum size, an LDM is expected to be generated
define void @f(i32 %n, i32* nocapture %a, i32* nocapture readonly %b) optsize minsize {
; CHECK-LABEL: f:
; CHECK: @ %bb.0:
; CHECK-NEXT: cmp r0, #1
; CHECK-NEXT: blt .LBB0_2
; CHECK-NEXT: .LBB0_1: @ %.lr.ph
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldm r2!, {r3}
; CHECK-NEXT: adds r3, #3
; CHECK-NEXT: stm r1!, {r3}
; CHECK-NEXT: subs r0, #1
; CHECK-NEXT: bne .LBB0_1
; CHECK-NEXT: .LBB0_2: @ %._crit_edge
; CHECK-NEXT: bx lr
%1 = icmp sgt i32 %n, 0
br i1 %1, label %.lr.ph, label %._crit_edge
.lr.ph: ; preds = %.lr.ph, %0
%i.04 = phi i32 [ %6, %.lr.ph ], [ 0, %0 ]
%.03 = phi i32* [ %2, %.lr.ph ], [ %b, %0 ]
%.012 = phi i32* [ %5, %.lr.ph ], [ %a, %0 ]
%2 = getelementptr inbounds i32, i32* %.03, i32 1
%3 = load i32, i32* %.03, align 4
%4 = add nsw i32 %3, 3
%5 = getelementptr inbounds i32, i32* %.012, i32 1
store i32 %4, i32* %.012, align 4
%6 = add nsw i32 %i.04, 1
%exitcond = icmp eq i32 %6, %n
br i1 %exitcond, label %._crit_edge, label %.lr.ph
._crit_edge: ; preds = %.lr.ph, %0
ret void
}
; NOTE: When not optimising for minimum size, an LDM is expected not to be generated
define void @f_nominsize(i32 %n, i32* nocapture %a, i32* nocapture readonly %b) optsize {
; CHECK-LABEL: f_nominsize:
; CHECK: @ %bb.0:
; CHECK-NEXT: cmp r0, #1
; CHECK-NEXT: it lt
; CHECK-NEXT: bxlt lr
; CHECK-NEXT: .LBB1_1: @ %.lr.ph
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r3, [r2], #4
; CHECK-NEXT: subs r0, #1
; CHECK-NEXT: add.w r3, r3, #3
; CHECK-NEXT: str r3, [r1], #4
; CHECK-NEXT: bne .LBB1_1
; CHECK-NEXT: @ %bb.2: @ %._crit_edge
; CHECK-NEXT: bx lr
%1 = icmp sgt i32 %n, 0
br i1 %1, label %.lr.ph, label %._crit_edge
.lr.ph: ; preds = %.lr.ph, %0
%i.04 = phi i32 [ %6, %.lr.ph ], [ 0, %0 ]
%.03 = phi i32* [ %2, %.lr.ph ], [ %b, %0 ]
%.012 = phi i32* [ %5, %.lr.ph ], [ %a, %0 ]
%2 = getelementptr inbounds i32, i32* %.03, i32 1
%3 = load i32, i32* %.03, align 4
%4 = add nsw i32 %3, 3
%5 = getelementptr inbounds i32, i32* %.012, i32 1
store i32 %4, i32* %.012, align 4
%6 = add nsw i32 %i.04, 1
%exitcond = icmp eq i32 %6, %n
br i1 %exitcond, label %._crit_edge, label %.lr.ph
._crit_edge: ; preds = %.lr.ph, %0
ret void
}