caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
05727d94de75e2e98e6ae37c36aeb4f6ca6b2aed
clang-p2996/llvm/test/CodeGen/PowerPC/vselect-constants.ll
Quinn Pham 335e8bf100 [PowerPC] emit VSX instructions instead of VMX instructions for vector loads and stores 
This patch changes the PowerPC backend to generate VSX load/store instructions
for all vector loads/stores on Power8 and earlier  (LE) instead of VMX
load/store instructions. The reason for this change is because VMX instructions
require the vector to be 16-byte aligned. So, a vector load/store will fail with
VMX instructions if the vector is misaligned. Also, `gcc` generates VSX
instructions in this situation which allow for unaligned access but require a
swap instruction after loading/before storing. This is not an issue for BE
because we already emit VSX instructions since no swap is required. And this is
not an issue on Power9 and up since we have access to `lxv[x]`/`stxv[x]` which
allow for unaligned access and do not require swaps.

This patch also delays the VSX load/store for LE combines until after
LegalizeOps to prioritize other load/store combines.

Reviewed By: #powerpc, stefanp

Differential Revision: https://reviews.llvm.org/D127309
2022-06-15 12:06:04 -05:00

205 lines
7.2 KiB
LLVM
Raw Blame History

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -verify-machineinstrs < %s -mtriple=powerpc64le-unknown-unknown | FileCheck %s
; First, check the generic pattern for any 2 vector constants. Then, check special cases where
; the constants are all off-by-one. Finally, check the extra special cases where the constants
; include 0 or -1.
; Each minimal select test is repeated with a more typical pattern that includes a compare to
; generate the condition value.
define <4 x i32> @sel_C1_or_C2_vec(<4 x i1> %cond) {
; CHECK-LABEL: sel_C1_or_C2_vec:
; CHECK: # %bb.0:
; CHECK-NEXT: vspltisw 3, -16
; CHECK-NEXT: vspltisw 4, 15
; CHECK-NEXT: addis 3, 2, .LCPI0_0@toc@ha
; CHECK-NEXT: addis 4, 2, .LCPI0_1@toc@ha
; CHECK-NEXT: addi 3, 3, .LCPI0_0@toc@l
; CHECK-NEXT: addi 4, 4, .LCPI0_1@toc@l
; CHECK-NEXT: lxvd2x 0, 0, 3
; CHECK-NEXT: lxvd2x 1, 0, 4
; CHECK-NEXT: vsubuwm 3, 4, 3
; CHECK-NEXT: vslw 2, 2, 3
; CHECK-NEXT: xxswapd 36, 1
; CHECK-NEXT: vsraw 2, 2, 3
; CHECK-NEXT: xxswapd 35, 0
; CHECK-NEXT: xxsel 34, 36, 35, 34
; CHECK-NEXT: blr
%add = select <4 x i1> %cond, <4 x i32> <i32 3000, i32 1, i32 -1, i32 0>, <4 x i32> <i32 42, i32 0, i32 -2, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_C1_or_C2_vec(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: cmp_sel_C1_or_C2_vec:
; CHECK: # %bb.0:
; CHECK-NEXT: addis 3, 2, .LCPI1_0@toc@ha
; CHECK-NEXT: addis 4, 2, .LCPI1_1@toc@ha
; CHECK-NEXT: vcmpequw 2, 2, 3
; CHECK-NEXT: addi 3, 3, .LCPI1_0@toc@l
; CHECK-NEXT: addi 4, 4, .LCPI1_1@toc@l
; CHECK-NEXT: lxvd2x 0, 0, 3
; CHECK-NEXT: lxvd2x 1, 0, 4
; CHECK-NEXT: xxswapd 35, 0
; CHECK-NEXT: xxswapd 36, 1
; CHECK-NEXT: xxsel 34, 36, 35, 34
; CHECK-NEXT: blr
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 3000, i32 1, i32 -1, i32 0>, <4 x i32> <i32 42, i32 0, i32 -2, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @sel_Cplus1_or_C_vec(<4 x i1> %cond) {
; CHECK-LABEL: sel_Cplus1_or_C_vec:
; CHECK: # %bb.0:
; CHECK-NEXT: addis 3, 2, .LCPI2_0@toc@ha
; CHECK-NEXT: vspltisw 3, 1
; CHECK-NEXT: addi 3, 3, .LCPI2_0@toc@l
; CHECK-NEXT: lxvd2x 0, 0, 3
; CHECK-NEXT: xxland 34, 34, 35
; CHECK-NEXT: xxswapd 36, 0
; CHECK-NEXT: vadduwm 2, 2, 4
; CHECK-NEXT: blr
%add = select <4 x i1> %cond, <4 x i32> <i32 43, i32 1, i32 -1, i32 0>, <4 x i32> <i32 42, i32 0, i32 -2, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_Cplus1_or_C_vec(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: cmp_sel_Cplus1_or_C_vec:
; CHECK: # %bb.0:
; CHECK-NEXT: addis 3, 2, .LCPI3_0@toc@ha
; CHECK-NEXT: vcmpequw 2, 2, 3
; CHECK-NEXT: addi 3, 3, .LCPI3_0@toc@l
; CHECK-NEXT: lxvd2x 0, 0, 3
; CHECK-NEXT: xxswapd 35, 0
; CHECK-NEXT: vsubuwm 2, 3, 2
; CHECK-NEXT: blr
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 43, i32 1, i32 -1, i32 0>, <4 x i32> <i32 42, i32 0, i32 -2, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @sel_Cminus1_or_C_vec(<4 x i1> %cond) {
; CHECK-LABEL: sel_Cminus1_or_C_vec:
; CHECK: # %bb.0:
; CHECK-NEXT: vspltisw 3, -16
; CHECK-NEXT: vspltisw 4, 15
; CHECK-NEXT: addis 3, 2, .LCPI4_0@toc@ha
; CHECK-NEXT: addi 3, 3, .LCPI4_0@toc@l
; CHECK-NEXT: lxvd2x 0, 0, 3
; CHECK-NEXT: vsubuwm 3, 4, 3
; CHECK-NEXT: vslw 2, 2, 3
; CHECK-NEXT: vsraw 2, 2, 3
; CHECK-NEXT: xxswapd 35, 0
; CHECK-NEXT: vadduwm 2, 2, 3
; CHECK-NEXT: blr
%add = select <4 x i1> %cond, <4 x i32> <i32 43, i32 1, i32 -1, i32 0>, <4 x i32> <i32 44, i32 2, i32 0, i32 1>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_Cminus1_or_C_vec(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: cmp_sel_Cminus1_or_C_vec:
; CHECK: # %bb.0:
; CHECK-NEXT: addis 3, 2, .LCPI5_0@toc@ha
; CHECK-NEXT: vcmpequw 2, 2, 3
; CHECK-NEXT: addi 3, 3, .LCPI5_0@toc@l
; CHECK-NEXT: lxvd2x 0, 0, 3
; CHECK-NEXT: xxswapd 35, 0
; CHECK-NEXT: vadduwm 2, 2, 3
; CHECK-NEXT: blr
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 43, i32 1, i32 -1, i32 0>, <4 x i32> <i32 44, i32 2, i32 0, i32 1>
ret <4 x i32> %add
}
define <4 x i32> @sel_minus1_or_0_vec(<4 x i1> %cond) {
; CHECK-LABEL: sel_minus1_or_0_vec:
; CHECK: # %bb.0:
; CHECK-NEXT: vspltisw 3, -16
; CHECK-NEXT: vspltisw 4, 15
; CHECK-NEXT: vsubuwm 3, 4, 3
; CHECK-NEXT: vslw 2, 2, 3
; CHECK-NEXT: vsraw 2, 2, 3
; CHECK-NEXT: blr
%add = select <4 x i1> %cond, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_minus1_or_0_vec(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: cmp_sel_minus1_or_0_vec:
; CHECK: # %bb.0:
; CHECK-NEXT: vcmpequw 2, 2, 3
; CHECK-NEXT: blr
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
ret <4 x i32> %add
}
define <4 x i32> @sel_0_or_minus1_vec(<4 x i1> %cond) {
; CHECK-LABEL: sel_0_or_minus1_vec:
; CHECK: # %bb.0:
; CHECK-NEXT: vspltisw 3, 1
; CHECK-NEXT: xxland 34, 34, 35
; CHECK-NEXT: xxleqv 35, 35, 35
; CHECK-NEXT: vadduwm 2, 2, 3
; CHECK-NEXT: blr
%add = select <4 x i1> %cond, <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_0_or_minus1_vec(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: cmp_sel_0_or_minus1_vec:
; CHECK: # %bb.0:
; CHECK-NEXT: vcmpequw 2, 2, 3
; CHECK-NEXT: xxlnor 34, 34, 34
; CHECK-NEXT: blr
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @sel_1_or_0_vec(<4 x i1> %cond) {
; CHECK-LABEL: sel_1_or_0_vec:
; CHECK: # %bb.0:
; CHECK-NEXT: vspltisw 3, 1
; CHECK-NEXT: xxland 34, 34, 35
; CHECK-NEXT: blr
%add = select <4 x i1> %cond, <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_1_or_0_vec(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: cmp_sel_1_or_0_vec:
; CHECK: # %bb.0:
; CHECK-NEXT: vcmpequw 2, 2, 3
; CHECK-NEXT: vspltisw 3, 1
; CHECK-NEXT: xxland 34, 34, 35
; CHECK-NEXT: blr
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
ret <4 x i32> %add
}
define <4 x i32> @sel_0_or_1_vec(<4 x i1> %cond) {
; CHECK-LABEL: sel_0_or_1_vec:
; CHECK: # %bb.0:
; CHECK-NEXT: vspltisw 3, 1
; CHECK-NEXT: xxlandc 34, 35, 34
; CHECK-NEXT: blr
%add = select <4 x i1> %cond, <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_0_or_1_vec(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: cmp_sel_0_or_1_vec:
; CHECK: # %bb.0:
; CHECK-NEXT: vcmpequw 2, 2, 3
; CHECK-NEXT: vspltisw 3, 1
; CHECK-NEXT: xxlnor 0, 34, 34
; CHECK-NEXT: xxland 34, 0, 35
; CHECK-NEXT: blr
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
ret <4 x i32> %add
}
Reference in New Issue View Git Blame Copy Permalink