[ARM] Cortex-A57 scheduling model for ARM backend (AArch32)

This patch implements the Cortex-A57 scheduling model.
The main code is in ARMScheduleA57.td, ARMScheduleA57WriteRes.td.
Small changes in cpp,.h files to support required scheduling predicates.

Scheduling model implemented according to:
 http://infocenter.arm.com/help/topic/com.arm.doc.uan0015b/Cortex_A57_Software_Optimization_Guide_external.pdf.

Patch by : Andrew Zhogin (submitted on his behalf, as requested).
Rewiewed by: Renato Golin, Diana Picus, Javed Absar, Kristof Beyls.
Differential Revision: https://reviews.llvm.org/D28152

llvm-svn: 304530

1 files changed, 53 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/ARM/cortex-a57-misched-basic.ll b/llvm/test/CodeGen/ARM/cortex-a57-misched-basic.ll
new file mode 100644
index 00000000000..2ec50b9d334
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/cortex-a57-misched-basic.ll
@@ -0,0 +1,53 @@
+; REQUIRES: asserts
+; RUN: llc < %s -mtriple=armv8r-eabi -mcpu=cortex-a57 -enable-misched -verify-misched -debug-only=machine-scheduler -o - 2>&1 > /dev/null | FileCheck %s --check-prefix=CHECK --check-prefix=A57_SCHED
+; RUN: llc < %s -mtriple=armv8r-eabi -mcpu=generic    -enable-misched -verify-misched -debug-only=machine-scheduler -o - 2>&1 > /dev/null | FileCheck %s --check-prefix=CHECK --check-prefix=GENERIC
+
+; Check the latency for instructions for both generic and cortex-a57.
+; SDIV should be scheduled at the block's begin (20 cyc of independent M unit).
+;
+; CHECK:       ********** MI Scheduling **********
+; CHECK:      foo:BB#0 entry
+
+; GENERIC:    SDIV
+; GENERIC:    Latency    : 1
+; GENERIC:    EORrr
+; GENERIC:    Latency    : 1
+; GENERIC:    LDRi12
+; GENERIC:    Latency    : 4
+; GENERIC:    ADDrr
+; GENERIC:    Latency    : 1
+; GENERIC:    SUBrr
+; GENERIC:    Latency    : 1
+
+; A57_SCHED:  SDIV
+; A57_SCHED:  Latency    : 20
+; A57_SCHED:  EORrr
+; A57_SCHED:  Latency    : 1
+; A57_SCHED:  LDRi12
+; A57_SCHED:  Latency    : 4
+; A57_SCHED:  ADDrr
+; A57_SCHED:  Latency    : 1
+; A57_SCHED:  SUBrr
+; A57_SCHED:  Latency    : 1
+
+; CHECK:      ** Final schedule for BB#0 ***
+; GENERIC:    LDRi12
+; GENERIC:    SDIV
+; A57_SCHED:  SDIV
+; A57_SCHED:  LDRi12
+; CHECK:      ********** INTERVALS **********
+
+target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
+target triple = "armv8r-arm-none-eabi"
+
+; Function Attrs: norecurse nounwind readnone
+define hidden i32 @foo(i32 %a, i32 %b, i32 %c, i32* %d) local_unnamed_addr #0 {
+entry:
+  %xor = xor i32 %c, %b
+  %ld = load i32, i32* %d
+  %add = add nsw i32 %xor, %ld
+  %div = sdiv i32 %a, %b
+  %sub = sub i32 %div, %add
+  ret i32 %sub
+}
+