1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00
llvm-mirror/test/CodeGen/Thumb2/m4-sched-regs.ll
David Green c39d16203a [ARM] Don't use the Machine Scheduler for cortex-m at minsize
The new cortex-m schedule in rL360768 helps performance, but can increase the
amount of high-registers used. This, on average, ends up increasing the
codesize by a fair amount (because less instructions are converted from T2 to
T1). On cortex-m at -Oz, where we are quite size-paranoid, it is better to use
the existing DAG scheduler with the RegPressure scheduling preference (at least
until the issues around T2 vs T1 instructions can be improved).

I have also made sure that the Sched::RegPressure dag scheduler is always
chosen for MinSize.

The test shows one case where we increase the number of registers used.

Differential Revision: https://reviews.llvm.org/D61882

llvm-svn: 360769
2019-05-15 12:58:02 +00:00

51 lines
2.1 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc %s -o - | FileCheck %s
target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "thumbv7em-arm-none-eabi"
%struct.a = type { i32, %struct.b*, i8, i8, i8, i8, i8*, %struct.b*, i16, i16, i16, i16, i16, i16, i16, i16, i32, i32, i32, i32, i32, i32, i32 }
%struct.b = type { i8, i8, i8, i8, i32, i16, i16, i32, i32, i32, i32, [16 x i8], [64 x i8], [128 x i8], i32, [68 x i8] }
define void @test(%struct.a* nocapture %dhcp, i16 zeroext %value) #0 {
; CHECK-LABEL: test:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: ldrh r2, [r0, #20]
; CHECK-NEXT: adds r3, r2, #1
; CHECK-NEXT: strh r3, [r0, #20]
; CHECK-NEXT: ldr r3, [r0, #16]
; CHECK-NEXT: add r2, r3
; CHECK-NEXT: lsrs r3, r1, #8
; CHECK-NEXT: strb.w r3, [r2, #240]
; CHECK-NEXT: ldrh r2, [r0, #20]
; CHECK-NEXT: adds r3, r2, #1
; CHECK-NEXT: strh r3, [r0, #20]
; CHECK-NEXT: ldr r0, [r0, #16]
; CHECK-NEXT: add r0, r2
; CHECK-NEXT: strb.w r1, [r0, #240]
; CHECK-NEXT: bx lr
entry:
%shr = lshr i16 %value, 8
%conv1 = trunc i16 %shr to i8
%msg_out = getelementptr inbounds %struct.a, %struct.a* %dhcp, i32 0, i32 7
%0 = load %struct.b*, %struct.b** %msg_out, align 4
%options_out_len = getelementptr inbounds %struct.a, %struct.a* %dhcp, i32 0, i32 8
%1 = load i16, i16* %options_out_len, align 4
%inc = add i16 %1, 1
store i16 %inc, i16* %options_out_len, align 4
%idxprom = zext i16 %1 to i32
%arrayidx = getelementptr inbounds %struct.b, %struct.b* %0, i32 0, i32 15, i32 %idxprom
store i8 %conv1, i8* %arrayidx, align 1
%conv4 = trunc i16 %value to i8
%2 = load %struct.b*, %struct.b** %msg_out, align 4
%3 = load i16, i16* %options_out_len, align 4
%inc8 = add i16 %3, 1
store i16 %inc8, i16* %options_out_len, align 4
%idxprom9 = zext i16 %3 to i32
%arrayidx10 = getelementptr inbounds %struct.b, %struct.b* %2, i32 0, i32 15, i32 %idxprom9
store i8 %conv4, i8* %arrayidx10, align 1
ret void
}
attributes #0 = { minsize optsize "target-cpu"="cortex-m4" }