RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 02:33:06 +01:00
Code Issues Projects Releases Wiki Activity

[AArch64] Add Fujitsu A64FX scheduling model

Browse Source 
Basic support of A64FX was added in D75594 but its scheduling model
was missing. This commit adds the scheduling model. Also, this commit
amends/adds some subtarget parameters of A64FX.

The A64FX Microarchitecture Manual, which is source information of
this commit, is on GitHub.

https://github.com/fujitsu/A64FX/

Differential Revision: https://reviews.llvm.org/D93791
This commit is contained in:
KAWASHIMA Takahiro 2021-01-04 11:25:42 +09:00
parent 4f287c334a
commit 008c1588a4
5 changed files with 3904 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
lib/Target/AArch64/AArch64.td
View File

@ -553,6 +553,7 @@ include "AArch64SchedExynosM4.td"
include "AArch64SchedExynosM5.td"
include "AArch64SchedThunderX.td"
include "AArch64SchedThunderX2T99.td"
include "AArch64SchedA64FX.td"
include "AArch64SchedThunderX3T110.td"
include "AArch64SchedTSV110.td"
@ -743,7 +744,10 @@ def ProcA64FX : SubtargetFeature<"a64fx", "ARMProcFamily", "A64FX",
FeatureFullFP16,
FeatureSVE,
FeaturePostRAScheduler,
FeatureComplxNum
FeatureComplxNum,
FeatureAggressiveFMA,
FeatureArithmeticBccFusion,
FeaturePredictableSelectIsExpensive
]>;
def ProcCarmel : SubtargetFeature<"carmel", "ARMProcFamily", "Carmel",
@ -1152,8 +1156,7 @@ def : ProcessorModel<"apple-s5", CycloneModel, [ProcAppleA12]>;
def : ProcessorModel<"apple-latest", CycloneModel, [ProcAppleA13]>;
// Fujitsu A64FX
// FIXME: Scheduling model is not implemented yet.
def : ProcessorModel<"a64fx", NoSchedModel, [ProcA64FX]>;
def : ProcessorModel<"a64fx", A64FXModel, [ProcA64FX]>;
// Nvidia Carmel
def : ProcessorModel<"carmel", NoSchedModel, [ProcCarmel]>;

3890
lib/Target/AArch64/AArch64SchedA64FX.td Normal file
View File

File diff suppressed because it is too large Load Diff

8
lib/Target/AArch64/AArch64Subtarget.cpp
View File

@ -110,8 +110,12 @@ void AArch64Subtarget::initializeProperties() {
break;
case A64FX:
CacheLineSize = 256;
PrefFunctionLogAlignment = 5;
PrefLoopLogAlignment = 5;
PrefFunctionLogAlignment = 3;
PrefLoopLogAlignment = 2;
MaxInterleaveFactor = 4;
PrefetchDistance = 128;
MinPrefetchStride = 1024;
MaxPrefetchIterationsAhead = 4;
break;
case AppleA7:
case AppleA10:

1
test/CodeGen/AArch64/machine-combiner-madd.ll
View File

@ -1,4 +1,5 @@
; Test all AArch64 subarches with scheduling models.
; RUN: llc -mtriple=aarch64-linux-gnu -mcpu=a64fx < %s | FileCheck %s
; RUN: llc -mtriple=aarch64-linux-gnu -mcpu=cortex-a57 < %s | FileCheck %s
; RUN: llc -mtriple=aarch64-linux-gnu -mcpu=cortex-a72 < %s | FileCheck %s
; RUN: llc -mtriple=aarch64-linux-gnu -mcpu=cortex-a73 < %s | FileCheck %s

2
test/CodeGen/AArch64/preferred-function-alignment.ll
View File

@ -8,7 +8,7 @@
; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=cortex-a73 < %s | FileCheck --check-prefixes=ALIGN4,CHECK %s
; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=cortex-a75 < %s | FileCheck --check-prefixes=ALIGN4,CHECK %s
; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=cortex-a76 < %s | FileCheck --check-prefixes=ALIGN4,CHECK %s
; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=a64fx < %s | FileCheck --check-prefixes=ALIGN5,CHECK %s
; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=a64fx < %s | FileCheck --check-prefixes=ALIGN3,CHECK %s
; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=cyclone < %s | FileCheck --check-prefixes=ALIGN2,CHECK %s
; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=falkor < %s | FileCheck --check-prefixes=ALIGN2,CHECK %s
; RUN: llc -mtriple=aarch64-unknown-linux -mcpu=kryo < %s | FileCheck --check-prefixes=ALIGN2,CHECK %s