1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 18:54:02 +01:00
llvm-mirror/test/CodeGen/PowerPC/vsx-spill.ll
QingShan Zhang 2f3956c41c [Power9] Enable the Out-of-Order scheduling model for P9 hw
When switched to the MI scheduler for P9, the hardware is modeled as out of order.
However, inside the MI Scheduler algorithm, we still use the in-order scheduling model
as the MicroOpBufferSize isn't set. The MI scheduler take it as the hw cannot buffer
the op. So, only when all the available instructions issued, the pending instruction
could be scheduled. That is not true for our P9 hw in fact.

This patch is trying to enable the Out-of-Order scheduling model. The buffer size 44 is
picked from the P9 hw spec, and the perf test indicate that, its value won't hurt the cpu2017.

With this patch, there are 3 specs improved over 3% and 1 spec deg over 3%. The detail is as follows:

x264_r: +6.95%
cactuBSSN_r: +6.94%
lbm_r: +4.11%
xz_r: -3.85%

And the GEOMEAN for all the C/C++ spec in spec2017 is about 0.18% improved. 

Reviewer: Nemanjai
Differential Revision: https://reviews.llvm.org/D55810

llvm-svn: 350285
2019-01-03 05:04:18 +00:00

108 lines
3.9 KiB
LLVM

; RUN: llc -verify-machineinstrs -mcpu=pwr7 -mattr=+vsx \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | FileCheck %s
; RUN: llc -verify-machineinstrs -mcpu=pwr7 -mattr=+vsx \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | FileCheck \
; RUN: -check-prefix=CHECK-REG %s
; RUN: llc -verify-machineinstrs -mcpu=pwr7 -mattr=+vsx -fast-isel -O0 \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | FileCheck %s
; RUN: llc -verify-machineinstrs -mcpu=pwr7 -mattr=+vsx -fast-isel -O0 \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | \
; RUN: FileCheck -check-prefix=CHECK-FISL %s
; RUN: llc -verify-machineinstrs -mcpu=pwr9 -ppc-vsr-nums-as-vr \
; RUN: -ppc-asm-full-reg-names < %s | FileCheck -check-prefix=CHECK-P9-REG %s
; RUN: llc -verify-machineinstrs -mcpu=pwr9 -fast-isel -O0 \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | FileCheck \
; RUN: -check-prefix=CHECK-P9-FISL %s
target datalayout = "E-m:e-i64:64-n32:64"
target triple = "powerpc64-unknown-linux-gnu"
define double @foo1(double %a) nounwind {
entry:
call void asm sideeffect "", "~{f0},~{f1},~{f2},~{f3},~{f4},~{f5},~{f6},~{f7},~{f8},~{f9},~{f10},~{f11},~{f12},~{f13},~{f14},~{f15},~{f16},~{f17},~{f18},~{f19},~{f20},~{f21},~{f22},~{f23},~{f24},~{f25},~{f26},~{f27},~{f28},~{f29},~{f30},~{f31}"() nounwind
br label %return
; CHECK-REG: @foo1
; CHECK-REG: xxlor v2, f1, f1
; CHECK-REG: xxlor f1, v2, v2
; CHECK-REG: blr
; CHECK-FISL: @foo1
; CHECK-FISL-NOT: lis
; CHECK-FISL-NOT: ori
; CHECK-FISL: li r3, -152
; CHECK-FISL-NOT: lis
; CHECK-FISL-NOT: ori
; CHECK-FISL: stxsdx f1, r1, r3
; CHECK-FISL: blr
; CHECK-P9-REG: @foo1
; CHECK-P9-REG: xscpsgndp v2, f1, f1
; CHECK-P9-REG: xscpsgndp f1, v2, v2
; CHECK-P9-REG: blr
; CHECK-P9-FISL: @foo1
; CHECK-P9-FISL: stfd f31, -8(r1)
; CHECK-P9-FISL: blr
return: ; preds = %entry
ret double %a
}
define double @foo2(double %a) nounwind {
entry:
%b = fadd double %a, %a
call void asm sideeffect "", "~{f0},~{f1},~{f2},~{f3},~{f4},~{f5},~{f6},~{f7},~{f8},~{f9},~{f10},~{f11},~{f12},~{f13},~{f14},~{f15},~{f16},~{f17},~{f18},~{f19},~{f20},~{f21},~{f22},~{f23},~{f24},~{f25},~{f26},~{f27},~{f28},~{f29},~{f30},~{f31}"() nounwind
br label %return
; CHECK-REG: @foo2
; CHECK-REG: {{xxlor|xsadddp}} v2, f1, f1
; CHECK-REG: {{xxlor|xsadddp}} f1, f0, f0
; CHECK-REG: blr
; CHECK-FISL: @foo2
; CHECK-FISL: xsadddp [[REG0:f[0-9]+]], f1, f1
; CHECK-FISL: stxsdx [[REG0]], r1, r3
; CHECK-FISL: lxsdx f1, r1, r3
; CHECK-FISL: blr
; CHECK-P9-REG: @foo2
; CHECK-P9-REG: {{xscpsgndp|xsadddp}} v2, f1, f1
; CHECK-P9-REG: {{xscpsgndp|xsadddp}} f1, v2, v2
; CHECK-P9-REG: blr
; CHECK-P9-FISL: @foo2
; CHECK-P9-FISL: xsadddp [[REG0:f[0-9]+]], f1, f1
; CHECK-P9-FISL: stfd [[REG0]], -152(r1)
; CHECK-P9-FISL: lfd f1, -152(r1)
; CHECK-P9-FISL: blr
return: ; preds = %entry
ret double %b
}
define double @foo3(double %a) nounwind {
entry:
call void asm sideeffect "", "~{f0},~{f1},~{f2},~{f3},~{f4},~{f5},~{f6},~{f7},~{f8},~{f9},~{f10},~{f11},~{f12},~{f13},~{f14},~{f15},~{f16},~{f17},~{f18},~{f19},~{f20},~{f21},~{f22},~{f23},~{f24},~{f25},~{f26},~{f27},~{f28},~{f29},~{f30},~{f31},~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"() nounwind
br label %return
; CHECK: @foo3
; CHECK: stxsdx f1, r1, r3
; CHECK: lxsdx f0, r1, r3
; CHECK: xsadddp f1, f0, f0
; CHECK: blr
; CHECK-P9-REG-LABEL: foo3
; CHECK-P9-REG: stdu r1, -400(r1)
; CHECK-P9-REG-DAG: lfd f30, 384(r1)
; CHECK-P9-REG-DAG: xsadddp f1, f0, f0
; CHECK-P9-FISL-LABEL: foo3
; CHECK-P9-FISL: stdu r1, -400(r1)
; CHECK-P9-FISL: lfd f0, 56(r1)
; CHECK-P9-FISL: xsadddp f1, f0, f0
return: ; preds = %entry
%b = fadd double %a, %a
ret double %b
}