300e1293de
We are going to remove the old 'perfect shuffle' optimization since it brings performance penalty in hot loop around vectors. For example, in following loop sharing the same mask: %v.1 = shufflevector ... <0,1,2,3,8,9,10,11,16,17,18,19,24,25,26,27> %v.2 = shufflevector ... <0,1,2,3,8,9,10,11,16,17,18,19,24,25,26,27> The generated instructions will be `vmrglw-vmrghw-vmrglw-vmrghw` instead of `vperm-vperm`. In some large loop cases, this causes 20%+ performance penalty. The original attempt to resolve this is to pre-record masks of every shufflevector operation in DAG, but that is somewhat complex and brings unnecessary computation (to scan all nodes) in optimization. Here we disable it by default. There're indeed some cases becoming worse after this, which will be fixed in a more careful way in future patches. Reviewed By: jsji Differential Revision: https://reviews.llvm.org/D121082
286 lines
10 KiB
LLVM
286 lines
10 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
|
|
; RUN: -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr \
|
|
; RUN: -mcpu=pwr7 < %s | FileCheck %s --check-prefix=CHECK-LE-P7
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
|
|
; RUN: -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr \
|
|
; RUN: -mcpu=pwr8 < %s | FileCheck %s --check-prefix=CHECK-LE-P8
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le-unknown-linux-gnu \
|
|
; RUN: -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr \
|
|
; RUN: -mcpu=pwr9 < %s | FileCheck %s --check-prefix=CHECK-LE-P9
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-linux-gnu \
|
|
; RUN: -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr \
|
|
; RUN: -mcpu=pwr7 < %s | FileCheck %s --check-prefix=CHECK-BE-P7
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-linux-gnu \
|
|
; RUN: -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr \
|
|
; RUN: -mcpu=pwr8 < %s | FileCheck %s --check-prefix=CHECK-BE-P8
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64-unknown-linux-gnu \
|
|
; RUN: -ppc-asm-full-reg-names -ppc-vsr-nums-as-vr \
|
|
; RUN: -mcpu=pwr9 < %s | FileCheck %s --check-prefix=CHECK-BE-P9
|
|
; xscvdpsxws and xscvdpsxws is only available on Power7 and above
|
|
; Codgen is different for Power7, Power8, and Power9.
|
|
|
|
define dso_local <4 x i32> @test(<4 x i32> %a, double %b) {
|
|
; CHECK-LE-P7-LABEL: test:
|
|
; CHECK-LE-P7: # %bb.0: # %entry
|
|
; CHECK-LE-P7-NEXT: xscvdpsxws f0, f1
|
|
; CHECK-LE-P7-NEXT: addi r3, r1, -4
|
|
; CHECK-LE-P7-NEXT: addis r4, r2, .LCPI0_0@toc@ha
|
|
; CHECK-LE-P7-NEXT: addi r4, r4, .LCPI0_0@toc@l
|
|
; CHECK-LE-P7-NEXT: lvx v3, 0, r4
|
|
; CHECK-LE-P7-NEXT: stfiwx f0, 0, r3
|
|
; CHECK-LE-P7-NEXT: lwz r3, -4(r1)
|
|
; CHECK-LE-P7-NEXT: stw r3, -32(r1)
|
|
; CHECK-LE-P7-NEXT: addi r3, r1, -32
|
|
; CHECK-LE-P7-NEXT: lvx v4, 0, r3
|
|
; CHECK-LE-P7-NEXT: vperm v2, v4, v2, v3
|
|
; CHECK-LE-P7-NEXT: blr
|
|
;
|
|
; CHECK-LE-P8-LABEL: test:
|
|
; CHECK-LE-P8: # %bb.0: # %entry
|
|
; CHECK-LE-P8-NEXT: xscvdpsxws v3, f1
|
|
; CHECK-LE-P8-NEXT: addis r3, r2, .LCPI0_0@toc@ha
|
|
; CHECK-LE-P8-NEXT: addi r3, r3, .LCPI0_0@toc@l
|
|
; CHECK-LE-P8-NEXT: lvx v4, 0, r3
|
|
; CHECK-LE-P8-NEXT: vperm v2, v3, v2, v4
|
|
; CHECK-LE-P8-NEXT: blr
|
|
;
|
|
; CHECK-LE-P9-LABEL: test:
|
|
; CHECK-LE-P9: # %bb.0: # %entry
|
|
; CHECK-LE-P9-NEXT: xscvdpsxws f0, f1
|
|
; CHECK-LE-P9-NEXT: xxinsertw v2, vs0, 0
|
|
; CHECK-LE-P9-NEXT: blr
|
|
;
|
|
; CHECK-BE-P7-LABEL: test:
|
|
; CHECK-BE-P7: # %bb.0: # %entry
|
|
; CHECK-BE-P7-NEXT: xscvdpsxws f0, f1
|
|
; CHECK-BE-P7-NEXT: addi r3, r1, -4
|
|
; CHECK-BE-P7-NEXT: addis r4, r2, .LCPI0_0@toc@ha
|
|
; CHECK-BE-P7-NEXT: stfiwx f0, 0, r3
|
|
; CHECK-BE-P7-NEXT: lwz r3, -4(r1)
|
|
; CHECK-BE-P7-NEXT: stw r3, -32(r1)
|
|
; CHECK-BE-P7-NEXT: addi r3, r4, .LCPI0_0@toc@l
|
|
; CHECK-BE-P7-NEXT: addi r4, r1, -32
|
|
; CHECK-BE-P7-NEXT: lxvw4x v3, 0, r3
|
|
; CHECK-BE-P7-NEXT: lxvw4x v4, 0, r4
|
|
; CHECK-BE-P7-NEXT: vperm v2, v2, v4, v3
|
|
; CHECK-BE-P7-NEXT: blr
|
|
;
|
|
; CHECK-BE-P8-LABEL: test:
|
|
; CHECK-BE-P8: # %bb.0: # %entry
|
|
; CHECK-BE-P8-NEXT: xscvdpsxws v3, f1
|
|
; CHECK-BE-P8-NEXT: addis r3, r2, .LCPI0_0@toc@ha
|
|
; CHECK-BE-P8-NEXT: addi r3, r3, .LCPI0_0@toc@l
|
|
; CHECK-BE-P8-NEXT: lxvw4x v4, 0, r3
|
|
; CHECK-BE-P8-NEXT: vperm v2, v2, v3, v4
|
|
; CHECK-BE-P8-NEXT: blr
|
|
;
|
|
; CHECK-BE-P9-LABEL: test:
|
|
; CHECK-BE-P9: # %bb.0: # %entry
|
|
; CHECK-BE-P9-NEXT: xscvdpsxws f0, f1
|
|
; CHECK-BE-P9-NEXT: xxinsertw v2, vs0, 12
|
|
; CHECK-BE-P9-NEXT: blr
|
|
entry:
|
|
%conv = fptosi double %b to i32
|
|
%vecins = insertelement <4 x i32> %a, i32 %conv, i32 3
|
|
ret <4 x i32> %vecins
|
|
}
|
|
|
|
define dso_local <4 x i32> @test2(<4 x i32> %a, float %b) {
|
|
; CHECK-LE-P7-LABEL: test2:
|
|
; CHECK-LE-P7: # %bb.0: # %entry
|
|
; CHECK-LE-P7-NEXT: xscvdpsxws f0, f1
|
|
; CHECK-LE-P7-NEXT: addi r3, r1, -4
|
|
; CHECK-LE-P7-NEXT: addis r4, r2, .LCPI1_0@toc@ha
|
|
; CHECK-LE-P7-NEXT: addi r4, r4, .LCPI1_0@toc@l
|
|
; CHECK-LE-P7-NEXT: lvx v3, 0, r4
|
|
; CHECK-LE-P7-NEXT: stfiwx f0, 0, r3
|
|
; CHECK-LE-P7-NEXT: lwz r3, -4(r1)
|
|
; CHECK-LE-P7-NEXT: stw r3, -32(r1)
|
|
; CHECK-LE-P7-NEXT: addi r3, r1, -32
|
|
; CHECK-LE-P7-NEXT: lvx v4, 0, r3
|
|
; CHECK-LE-P7-NEXT: vperm v2, v4, v2, v3
|
|
; CHECK-LE-P7-NEXT: blr
|
|
;
|
|
; CHECK-LE-P8-LABEL: test2:
|
|
; CHECK-LE-P8: # %bb.0: # %entry
|
|
; CHECK-LE-P8-NEXT: xscvdpsxws v3, f1
|
|
; CHECK-LE-P8-NEXT: addis r3, r2, .LCPI1_0@toc@ha
|
|
; CHECK-LE-P8-NEXT: addi r3, r3, .LCPI1_0@toc@l
|
|
; CHECK-LE-P8-NEXT: lvx v4, 0, r3
|
|
; CHECK-LE-P8-NEXT: vperm v2, v3, v2, v4
|
|
; CHECK-LE-P8-NEXT: blr
|
|
;
|
|
; CHECK-LE-P9-LABEL: test2:
|
|
; CHECK-LE-P9: # %bb.0: # %entry
|
|
; CHECK-LE-P9-NEXT: xscvdpsxws f0, f1
|
|
; CHECK-LE-P9-NEXT: xxinsertw v2, vs0, 0
|
|
; CHECK-LE-P9-NEXT: blr
|
|
;
|
|
; CHECK-BE-P7-LABEL: test2:
|
|
; CHECK-BE-P7: # %bb.0: # %entry
|
|
; CHECK-BE-P7-NEXT: xscvdpsxws f0, f1
|
|
; CHECK-BE-P7-NEXT: addi r3, r1, -4
|
|
; CHECK-BE-P7-NEXT: addis r4, r2, .LCPI1_0@toc@ha
|
|
; CHECK-BE-P7-NEXT: stfiwx f0, 0, r3
|
|
; CHECK-BE-P7-NEXT: lwz r3, -4(r1)
|
|
; CHECK-BE-P7-NEXT: stw r3, -32(r1)
|
|
; CHECK-BE-P7-NEXT: addi r3, r4, .LCPI1_0@toc@l
|
|
; CHECK-BE-P7-NEXT: addi r4, r1, -32
|
|
; CHECK-BE-P7-NEXT: lxvw4x v3, 0, r3
|
|
; CHECK-BE-P7-NEXT: lxvw4x v4, 0, r4
|
|
; CHECK-BE-P7-NEXT: vperm v2, v2, v4, v3
|
|
; CHECK-BE-P7-NEXT: blr
|
|
;
|
|
; CHECK-BE-P8-LABEL: test2:
|
|
; CHECK-BE-P8: # %bb.0: # %entry
|
|
; CHECK-BE-P8-NEXT: xscvdpsxws v3, f1
|
|
; CHECK-BE-P8-NEXT: addis r3, r2, .LCPI1_0@toc@ha
|
|
; CHECK-BE-P8-NEXT: addi r3, r3, .LCPI1_0@toc@l
|
|
; CHECK-BE-P8-NEXT: lxvw4x v4, 0, r3
|
|
; CHECK-BE-P8-NEXT: vperm v2, v2, v3, v4
|
|
; CHECK-BE-P8-NEXT: blr
|
|
;
|
|
; CHECK-BE-P9-LABEL: test2:
|
|
; CHECK-BE-P9: # %bb.0: # %entry
|
|
; CHECK-BE-P9-NEXT: xscvdpsxws f0, f1
|
|
; CHECK-BE-P9-NEXT: xxinsertw v2, vs0, 12
|
|
; CHECK-BE-P9-NEXT: blr
|
|
entry:
|
|
%conv = fptosi float %b to i32
|
|
%vecins = insertelement <4 x i32> %a, i32 %conv, i32 3
|
|
ret <4 x i32> %vecins
|
|
}
|
|
|
|
define dso_local <4 x i32> @test3(<4 x i32> %a, double %b) {
|
|
; CHECK-LE-P7-LABEL: test3:
|
|
; CHECK-LE-P7: # %bb.0: # %entry
|
|
; CHECK-LE-P7-NEXT: xscvdpuxws f0, f1
|
|
; CHECK-LE-P7-NEXT: addi r3, r1, -4
|
|
; CHECK-LE-P7-NEXT: addis r4, r2, .LCPI2_0@toc@ha
|
|
; CHECK-LE-P7-NEXT: addi r4, r4, .LCPI2_0@toc@l
|
|
; CHECK-LE-P7-NEXT: lvx v3, 0, r4
|
|
; CHECK-LE-P7-NEXT: stfiwx f0, 0, r3
|
|
; CHECK-LE-P7-NEXT: lwz r3, -4(r1)
|
|
; CHECK-LE-P7-NEXT: stw r3, -32(r1)
|
|
; CHECK-LE-P7-NEXT: addi r3, r1, -32
|
|
; CHECK-LE-P7-NEXT: lvx v4, 0, r3
|
|
; CHECK-LE-P7-NEXT: vperm v2, v4, v2, v3
|
|
; CHECK-LE-P7-NEXT: blr
|
|
;
|
|
; CHECK-LE-P8-LABEL: test3:
|
|
; CHECK-LE-P8: # %bb.0: # %entry
|
|
; CHECK-LE-P8-NEXT: xscvdpuxws v3, f1
|
|
; CHECK-LE-P8-NEXT: addis r3, r2, .LCPI2_0@toc@ha
|
|
; CHECK-LE-P8-NEXT: addi r3, r3, .LCPI2_0@toc@l
|
|
; CHECK-LE-P8-NEXT: lvx v4, 0, r3
|
|
; CHECK-LE-P8-NEXT: vperm v2, v3, v2, v4
|
|
; CHECK-LE-P8-NEXT: blr
|
|
;
|
|
; CHECK-LE-P9-LABEL: test3:
|
|
; CHECK-LE-P9: # %bb.0: # %entry
|
|
; CHECK-LE-P9-NEXT: xscvdpuxws f0, f1
|
|
; CHECK-LE-P9-NEXT: xxinsertw v2, vs0, 0
|
|
; CHECK-LE-P9-NEXT: blr
|
|
;
|
|
; CHECK-BE-P7-LABEL: test3:
|
|
; CHECK-BE-P7: # %bb.0: # %entry
|
|
; CHECK-BE-P7-NEXT: xscvdpuxws f0, f1
|
|
; CHECK-BE-P7-NEXT: addi r3, r1, -4
|
|
; CHECK-BE-P7-NEXT: addis r4, r2, .LCPI2_0@toc@ha
|
|
; CHECK-BE-P7-NEXT: stfiwx f0, 0, r3
|
|
; CHECK-BE-P7-NEXT: lwz r3, -4(r1)
|
|
; CHECK-BE-P7-NEXT: stw r3, -32(r1)
|
|
; CHECK-BE-P7-NEXT: addi r3, r4, .LCPI2_0@toc@l
|
|
; CHECK-BE-P7-NEXT: addi r4, r1, -32
|
|
; CHECK-BE-P7-NEXT: lxvw4x v3, 0, r3
|
|
; CHECK-BE-P7-NEXT: lxvw4x v4, 0, r4
|
|
; CHECK-BE-P7-NEXT: vperm v2, v2, v4, v3
|
|
; CHECK-BE-P7-NEXT: blr
|
|
;
|
|
; CHECK-BE-P8-LABEL: test3:
|
|
; CHECK-BE-P8: # %bb.0: # %entry
|
|
; CHECK-BE-P8-NEXT: xscvdpuxws v3, f1
|
|
; CHECK-BE-P8-NEXT: addis r3, r2, .LCPI2_0@toc@ha
|
|
; CHECK-BE-P8-NEXT: addi r3, r3, .LCPI2_0@toc@l
|
|
; CHECK-BE-P8-NEXT: lxvw4x v4, 0, r3
|
|
; CHECK-BE-P8-NEXT: vperm v2, v2, v3, v4
|
|
; CHECK-BE-P8-NEXT: blr
|
|
;
|
|
; CHECK-BE-P9-LABEL: test3:
|
|
; CHECK-BE-P9: # %bb.0: # %entry
|
|
; CHECK-BE-P9-NEXT: xscvdpuxws f0, f1
|
|
; CHECK-BE-P9-NEXT: xxinsertw v2, vs0, 12
|
|
; CHECK-BE-P9-NEXT: blr
|
|
entry:
|
|
%conv = fptoui double %b to i32
|
|
%vecins = insertelement <4 x i32> %a, i32 %conv, i32 3
|
|
ret <4 x i32> %vecins
|
|
}
|
|
|
|
define dso_local <4 x i32> @test4(<4 x i32> %a, float %b) {
|
|
; CHECK-LE-P7-LABEL: test4:
|
|
; CHECK-LE-P7: # %bb.0: # %entry
|
|
; CHECK-LE-P7-NEXT: xscvdpuxws f0, f1
|
|
; CHECK-LE-P7-NEXT: addi r3, r1, -4
|
|
; CHECK-LE-P7-NEXT: addis r4, r2, .LCPI3_0@toc@ha
|
|
; CHECK-LE-P7-NEXT: addi r4, r4, .LCPI3_0@toc@l
|
|
; CHECK-LE-P7-NEXT: lvx v3, 0, r4
|
|
; CHECK-LE-P7-NEXT: stfiwx f0, 0, r3
|
|
; CHECK-LE-P7-NEXT: lwz r3, -4(r1)
|
|
; CHECK-LE-P7-NEXT: stw r3, -32(r1)
|
|
; CHECK-LE-P7-NEXT: addi r3, r1, -32
|
|
; CHECK-LE-P7-NEXT: lvx v4, 0, r3
|
|
; CHECK-LE-P7-NEXT: vperm v2, v4, v2, v3
|
|
; CHECK-LE-P7-NEXT: blr
|
|
;
|
|
; CHECK-LE-P8-LABEL: test4:
|
|
; CHECK-LE-P8: # %bb.0: # %entry
|
|
; CHECK-LE-P8-NEXT: xscvdpuxws v3, f1
|
|
; CHECK-LE-P8-NEXT: addis r3, r2, .LCPI3_0@toc@ha
|
|
; CHECK-LE-P8-NEXT: addi r3, r3, .LCPI3_0@toc@l
|
|
; CHECK-LE-P8-NEXT: lvx v4, 0, r3
|
|
; CHECK-LE-P8-NEXT: vperm v2, v3, v2, v4
|
|
; CHECK-LE-P8-NEXT: blr
|
|
;
|
|
; CHECK-LE-P9-LABEL: test4:
|
|
; CHECK-LE-P9: # %bb.0: # %entry
|
|
; CHECK-LE-P9-NEXT: xscvdpuxws f0, f1
|
|
; CHECK-LE-P9-NEXT: xxinsertw v2, vs0, 0
|
|
; CHECK-LE-P9-NEXT: blr
|
|
;
|
|
; CHECK-BE-P7-LABEL: test4:
|
|
; CHECK-BE-P7: # %bb.0: # %entry
|
|
; CHECK-BE-P7-NEXT: xscvdpuxws f0, f1
|
|
; CHECK-BE-P7-NEXT: addi r3, r1, -4
|
|
; CHECK-BE-P7-NEXT: addis r4, r2, .LCPI3_0@toc@ha
|
|
; CHECK-BE-P7-NEXT: stfiwx f0, 0, r3
|
|
; CHECK-BE-P7-NEXT: lwz r3, -4(r1)
|
|
; CHECK-BE-P7-NEXT: stw r3, -32(r1)
|
|
; CHECK-BE-P7-NEXT: addi r3, r4, .LCPI3_0@toc@l
|
|
; CHECK-BE-P7-NEXT: addi r4, r1, -32
|
|
; CHECK-BE-P7-NEXT: lxvw4x v3, 0, r3
|
|
; CHECK-BE-P7-NEXT: lxvw4x v4, 0, r4
|
|
; CHECK-BE-P7-NEXT: vperm v2, v2, v4, v3
|
|
; CHECK-BE-P7-NEXT: blr
|
|
;
|
|
; CHECK-BE-P8-LABEL: test4:
|
|
; CHECK-BE-P8: # %bb.0: # %entry
|
|
; CHECK-BE-P8-NEXT: xscvdpuxws v3, f1
|
|
; CHECK-BE-P8-NEXT: addis r3, r2, .LCPI3_0@toc@ha
|
|
; CHECK-BE-P8-NEXT: addi r3, r3, .LCPI3_0@toc@l
|
|
; CHECK-BE-P8-NEXT: lxvw4x v4, 0, r3
|
|
; CHECK-BE-P8-NEXT: vperm v2, v2, v3, v4
|
|
; CHECK-BE-P8-NEXT: blr
|
|
;
|
|
; CHECK-BE-P9-LABEL: test4:
|
|
; CHECK-BE-P9: # %bb.0: # %entry
|
|
; CHECK-BE-P9-NEXT: xscvdpuxws f0, f1
|
|
; CHECK-BE-P9-NEXT: xxinsertw v2, vs0, 12
|
|
; CHECK-BE-P9-NEXT: blr
|
|
entry:
|
|
%conv = fptoui float %b to i32
|
|
%vecins = insertelement <4 x i32> %a, i32 %conv, i32 3
|
|
ret <4 x i32> %vecins
|
|
}
|