[llvm] ab46273 - [MachineLICM] testcase for hoisting rematerializable instruction, nfc
Chen Zheng via llvm-commits
llvm-commits at lists.llvm.org
Sun Jun 28 00:19:11 PDT 2020
Author: Chen Zheng
Date: 2020-06-28T03:16:57-04:00
New Revision: ab4627364aefcaac751e757b721b7d07b48a545a
URL: https://github.com/llvm/llvm-project/commit/ab4627364aefcaac751e757b721b7d07b48a545a
DIFF: https://github.com/llvm/llvm-project/commit/ab4627364aefcaac751e757b721b7d07b48a545a.diff
LOG: [MachineLICM] testcase for hoisting rematerializable instruction, nfc
Added:
llvm/test/CodeGen/PowerPC/rematerializable-instruction-machine-licm.ll
Modified:
Removed:
################################################################################
diff --git a/llvm/test/CodeGen/PowerPC/rematerializable-instruction-machine-licm.ll b/llvm/test/CodeGen/PowerPC/rematerializable-instruction-machine-licm.ll
new file mode 100644
index 000000000000..9ad5cb886472
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/rematerializable-instruction-machine-licm.ll
@@ -0,0 +1,618 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -verify-machineinstrs -mcpu=pwr9 < %s | FileCheck %s
+target datalayout = "e-m:e-i64:64-n32:64"
+target triple = "powerpc64le-unknown-linux-gnu"
+
+define zeroext i32 @test1(i64 %0, i64* %1) {
+; CHECK-LABEL: test1:
+; CHECK: # %bb.0:
+; CHECK-NEXT: stdu 1, -720(1)
+; CHECK-NEXT: .cfi_def_cfa_offset 720
+; CHECK-NEXT: .cfi_offset r14, -144
+; CHECK-NEXT: .cfi_offset r15, -136
+; CHECK-NEXT: .cfi_offset r16, -128
+; CHECK-NEXT: .cfi_offset r17, -120
+; CHECK-NEXT: .cfi_offset r18, -112
+; CHECK-NEXT: .cfi_offset r19, -104
+; CHECK-NEXT: .cfi_offset r20, -96
+; CHECK-NEXT: .cfi_offset r21, -88
+; CHECK-NEXT: .cfi_offset r22, -80
+; CHECK-NEXT: .cfi_offset r23, -72
+; CHECK-NEXT: .cfi_offset r24, -64
+; CHECK-NEXT: .cfi_offset r25, -56
+; CHECK-NEXT: .cfi_offset r26, -48
+; CHECK-NEXT: .cfi_offset r27, -40
+; CHECK-NEXT: .cfi_offset r28, -32
+; CHECK-NEXT: .cfi_offset r29, -24
+; CHECK-NEXT: .cfi_offset r30, -16
+; CHECK-NEXT: .cfi_offset r31, -8
+; CHECK-NEXT: .cfi_offset r2, -152
+; CHECK-NEXT: lis 5, 4
+; CHECK-NEXT: ori 6, 5, 6292
+; CHECK-NEXT: ori 5, 5, 6291
+; CHECK-NEXT: sldi 6, 6, 32
+; CHECK-NEXT: oris 7, 6, 13030
+; CHECK-NEXT: oris 8, 6, 13066
+; CHECK-NEXT: ori 7, 7, 3704
+; CHECK-NEXT: oris 9, 6, 13054
+; CHECK-NEXT: ori 8, 8, 44408
+; CHECK-NEXT: ori 9, 9, 30840
+; CHECK-NEXT: add 7, 4, 7
+; CHECK-NEXT: oris 10, 6, 13042
+; CHECK-NEXT: ori 10, 10, 17272
+; CHECK-NEXT: std 7, 384(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 7, 4, 8
+; CHECK-NEXT: oris 11, 6, 13078
+; CHECK-NEXT: ori 11, 11, 57976
+; CHECK-NEXT: std 7, 376(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 7, 4, 9
+; CHECK-NEXT: oris 12, 6, 13115
+; CHECK-NEXT: ori 12, 12, 33144
+; CHECK-NEXT: std 7, 368(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 7, 4, 10
+; CHECK-NEXT: oris 0, 6, 13103
+; CHECK-NEXT: ori 0, 0, 19576
+; CHECK-NEXT: std 7, 360(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 7, 4, 11
+; CHECK-NEXT: std 30, 704(1) # 8-byte Folded Spill
+; CHECK-NEXT: oris 30, 6, 13091
+; CHECK-NEXT: ori 30, 30, 6008
+; CHECK-NEXT: std 7, 352(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 7, 4, 12
+; CHECK-NEXT: std 29, 696(1) # 8-byte Folded Spill
+; CHECK-NEXT: oris 29, 6, 13127
+; CHECK-NEXT: ori 29, 29, 46712
+; CHECK-NEXT: sldi 5, 5, 32
+; CHECK-NEXT: oris 5, 5, 29347
+; CHECK-NEXT: ori 5, 5, 20088
+; CHECK-NEXT: lis 8, 402
+; CHECK-NEXT: lis 9, 451
+; CHECK-NEXT: lis 10, 500
+; CHECK-NEXT: lis 11, 549
+; CHECK-NEXT: std 31, 712(1) # 8-byte Folded Spill
+; CHECK-NEXT: std 2, 568(1) # 8-byte Folded Spill
+; CHECK-NEXT: std 7, 344(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 7, 4, 0
+; CHECK-NEXT: std 28, 688(1) # 8-byte Folded Spill
+; CHECK-NEXT: oris 28, 6, 13164
+; CHECK-NEXT: ori 28, 28, 21880
+; CHECK-NEXT: std 7, 336(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 7, 4, 30
+; CHECK-NEXT: std 27, 680(1) # 8-byte Folded Spill
+; CHECK-NEXT: oris 27, 6, 13152
+; CHECK-NEXT: ori 27, 27, 8312
+; CHECK-NEXT: std 7, 328(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 7, 4, 29
+; CHECK-NEXT: std 26, 672(1) # 8-byte Folded Spill
+; CHECK-NEXT: oris 26, 6, 13139
+; CHECK-NEXT: ori 26, 26, 60280
+; CHECK-NEXT: std 7, 320(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 7, 4, 28
+; CHECK-NEXT: std 25, 664(1) # 8-byte Folded Spill
+; CHECK-NEXT: oris 25, 6, 13176
+; CHECK-NEXT: ori 25, 25, 35448
+; CHECK-NEXT: std 7, 312(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 7, 4, 27
+; CHECK-NEXT: std 7, 304(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 7, 4, 26
+; CHECK-NEXT: std 7, 296(1) # 8-byte Folded Spill
+; CHECK-NEXT: add 7, 4, 25
+; CHECK-NEXT: std 7, 288(1) # 8-byte Folded Spill
+; CHECK-NEXT: oris 7, 6, 13213
+; CHECK-NEXT: ori 7, 7, 10616
+; CHECK-NEXT: add 7, 4, 7
+; CHECK-NEXT: std 7, 280(1) # 8-byte Folded Spill
+; CHECK-NEXT: oris 7, 6, 13200
+; CHECK-NEXT: oris 6, 6, 13188
+; CHECK-NEXT: ori 7, 7, 62584
+; CHECK-NEXT: ori 6, 6, 49016
+; CHECK-NEXT: add 7, 4, 7
+; CHECK-NEXT: add 6, 4, 6
+; CHECK-NEXT: add 4, 4, 5
+; CHECK-NEXT: lis 5, 268
+; CHECK-NEXT: std 4, 256(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 585
+; CHECK-NEXT: ori 4, 4, 61440
+; CHECK-NEXT: std 4, 560(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 48
+; CHECK-NEXT: ori 4, 4, 54272
+; CHECK-NEXT: std 4, 552(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 97
+; CHECK-NEXT: ori 4, 4, 43008
+; CHECK-NEXT: std 4, 544(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 146
+; CHECK-NEXT: ori 4, 4, 31744
+; CHECK-NEXT: std 4, 536(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 195
+; CHECK-NEXT: ori 4, 4, 20480
+; CHECK-NEXT: std 4, 528(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 244
+; CHECK-NEXT: ori 4, 4, 9216
+; CHECK-NEXT: std 4, 520(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 292
+; CHECK-NEXT: ori 4, 4, 63488
+; CHECK-NEXT: std 4, 512(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 341
+; CHECK-NEXT: ori 4, 4, 52224
+; CHECK-NEXT: std 4, 504(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 390
+; CHECK-NEXT: ori 4, 4, 40960
+; CHECK-NEXT: std 4, 496(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 439
+; CHECK-NEXT: ori 4, 4, 29696
+; CHECK-NEXT: std 4, 488(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 488
+; CHECK-NEXT: ori 4, 4, 18432
+; CHECK-NEXT: std 4, 480(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 537
+; CHECK-NEXT: ori 4, 4, 7168
+; CHECK-NEXT: std 4, 472(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 36
+; CHECK-NEXT: ori 4, 4, 40704
+; CHECK-NEXT: std 4, 464(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 85
+; CHECK-NEXT: ori 4, 4, 29440
+; CHECK-NEXT: std 4, 456(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 134
+; CHECK-NEXT: ori 4, 4, 18176
+; CHECK-NEXT: std 4, 448(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 183
+; CHECK-NEXT: ori 4, 4, 6912
+; CHECK-NEXT: std 4, 440(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 231
+; CHECK-NEXT: ori 4, 4, 61184
+; CHECK-NEXT: std 4, 432(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 280
+; CHECK-NEXT: ori 4, 4, 49920
+; CHECK-NEXT: std 4, 424(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 329
+; CHECK-NEXT: ori 4, 4, 38656
+; CHECK-NEXT: std 4, 416(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 378
+; CHECK-NEXT: ori 4, 4, 27392
+; CHECK-NEXT: std 4, 408(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 427
+; CHECK-NEXT: ori 4, 4, 16128
+; CHECK-NEXT: std 4, 400(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 476
+; CHECK-NEXT: ori 4, 4, 4864
+; CHECK-NEXT: std 4, 248(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 524
+; CHECK-NEXT: ori 4, 4, 59136
+; CHECK-NEXT: std 4, 240(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 573
+; CHECK-NEXT: ori 4, 4, 47872
+; CHECK-NEXT: std 4, 232(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 24
+; CHECK-NEXT: ori 4, 4, 27136
+; CHECK-NEXT: std 4, 224(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 73
+; CHECK-NEXT: ori 4, 4, 15872
+; CHECK-NEXT: std 4, 216(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 122
+; CHECK-NEXT: ori 4, 4, 4608
+; CHECK-NEXT: std 4, 208(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 170
+; CHECK-NEXT: ori 4, 4, 58880
+; CHECK-NEXT: std 4, 200(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 4, 219
+; CHECK-NEXT: ori 4, 4, 47616
+; CHECK-NEXT: std 4, 192(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 5, 36352
+; CHECK-NEXT: lis 5, 317
+; CHECK-NEXT: std 4, 184(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 5, 25088
+; CHECK-NEXT: lis 5, 366
+; CHECK-NEXT: std 4, 176(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 5, 13824
+; CHECK-NEXT: lis 5, 415
+; CHECK-NEXT: std 4, 168(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 5, 2560
+; CHECK-NEXT: lis 5, 463
+; CHECK-NEXT: std 4, 160(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 5, 56832
+; CHECK-NEXT: lis 5, 512
+; CHECK-NEXT: std 4, 152(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 5, 45568
+; CHECK-NEXT: lis 5, 561
+; CHECK-NEXT: std 4, 144(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 5, 34304
+; CHECK-NEXT: lis 5, 12
+; CHECK-NEXT: std 4, 136(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 5, 13568
+; CHECK-NEXT: lis 5, 61
+; CHECK-NEXT: std 4, 128(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 5, 2304
+; CHECK-NEXT: lis 5, 109
+; CHECK-NEXT: std 4, 120(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 5, 56576
+; CHECK-NEXT: lis 5, 158
+; CHECK-NEXT: std 4, 112(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 5, 45312
+; CHECK-NEXT: lis 5, 207
+; CHECK-NEXT: std 4, 104(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 5, 34048
+; CHECK-NEXT: lis 5, 256
+; CHECK-NEXT: std 6, 264(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 6, 305
+; CHECK-NEXT: ld 30, 192(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 29, 184(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 28, 176(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 27, 168(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 26, 160(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 25, 152(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 0, 120(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 4, 96(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 5, 22784
+; CHECK-NEXT: std 7, 272(1) # 8-byte Folded Spill
+; CHECK-NEXT: lis 7, 354
+; CHECK-NEXT: std 4, 88(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 6, 11520
+; CHECK-NEXT: ld 6, 240(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 4, 80(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 7, 256
+; CHECK-NEXT: ld 7, 232(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 4, 72(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 8, 54528
+; CHECK-NEXT: ld 8, 224(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 4, 64(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 9, 43264
+; CHECK-NEXT: ld 9, 216(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 4, 56(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 10, 32000
+; CHECK-NEXT: ld 10, 208(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 4, 48(1) # 8-byte Folded Spill
+; CHECK-NEXT: ori 4, 11, 20736
+; CHECK-NEXT: ld 11, 200(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 4, 40(1) # 8-byte Folded Spill
+; CHECK-NEXT: std 14, 576(1) # 8-byte Folded Spill
+; CHECK-NEXT: std 15, 584(1) # 8-byte Folded Spill
+; CHECK-NEXT: std 16, 592(1) # 8-byte Folded Spill
+; CHECK-NEXT: std 17, 600(1) # 8-byte Folded Spill
+; CHECK-NEXT: std 18, 608(1) # 8-byte Folded Spill
+; CHECK-NEXT: std 19, 616(1) # 8-byte Folded Spill
+; CHECK-NEXT: std 20, 624(1) # 8-byte Folded Spill
+; CHECK-NEXT: std 21, 632(1) # 8-byte Folded Spill
+; CHECK-NEXT: std 22, 640(1) # 8-byte Folded Spill
+; CHECK-NEXT: std 23, 648(1) # 8-byte Folded Spill
+; CHECK-NEXT: std 24, 656(1) # 8-byte Folded Spill
+; CHECK-NEXT: ld 5, 248(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 24, 144(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 23, 136(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 22, 112(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 21, 104(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 20, 96(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 19, 88(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 18, 80(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 17, 72(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 16, 64(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 15, 56(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 14, 48(1) # 8-byte Folded Reload
+; CHECK-NEXT: li 4, 0
+; CHECK-NEXT: ld 31, 40(1) # 8-byte Folded Reload
+; CHECK-NEXT: .p2align 4
+; CHECK-NEXT: .LBB0_1: # =>This Loop Header: Depth=1
+; CHECK-NEXT: # Child Loop BB0_2 Depth 2
+; CHECK-NEXT: stw 4, 396(1) # 4-byte Folded Spill
+; CHECK-NEXT: li 4, 83
+; CHECK-NEXT: mtctr 4
+; CHECK-NEXT: ld 12, 256(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 4, 128(1) # 8-byte Folded Reload
+; CHECK-NEXT: .p2align 5
+; CHECK-NEXT: .LBB0_2: # Parent Loop BB0_1 Depth=1
+; CHECK-NEXT: # => This Inner Loop Header: Depth=2
+; CHECK-NEXT: ld 2, 560(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdux 3, 12, 2
+; CHECK-NEXT: ld 2, 552(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 5
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 544(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 536(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 528(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 520(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 512(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 504(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 496(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 488(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 480(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 472(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 464(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 456(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 448(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 440(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 432(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 424(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 416(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 408(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: ld 2, 400(1) # 8-byte Folded Reload
+; CHECK-NEXT: stdx 3, 12, 2
+; CHECK-NEXT: stdx 3, 12, 6
+; CHECK-NEXT: stdx 3, 12, 7
+; CHECK-NEXT: stdx 3, 12, 8
+; CHECK-NEXT: stdx 3, 12, 9
+; CHECK-NEXT: stdx 3, 12, 10
+; CHECK-NEXT: stdx 3, 12, 11
+; CHECK-NEXT: stdx 3, 12, 30
+; CHECK-NEXT: stdx 3, 12, 29
+; CHECK-NEXT: stdx 3, 12, 28
+; CHECK-NEXT: stdx 3, 12, 27
+; CHECK-NEXT: stdx 3, 12, 26
+; CHECK-NEXT: stdx 3, 12, 25
+; CHECK-NEXT: stdx 3, 12, 24
+; CHECK-NEXT: stdx 3, 12, 23
+; CHECK-NEXT: stdx 3, 12, 4
+; CHECK-NEXT: stdx 3, 12, 0
+; CHECK-NEXT: stdx 3, 12, 22
+; CHECK-NEXT: stdx 3, 12, 21
+; CHECK-NEXT: stdx 3, 12, 20
+; CHECK-NEXT: stdx 3, 12, 19
+; CHECK-NEXT: stdx 3, 12, 18
+; CHECK-NEXT: stdx 3, 12, 17
+; CHECK-NEXT: stdx 3, 12, 16
+; CHECK-NEXT: stdx 3, 12, 15
+; CHECK-NEXT: stdx 3, 12, 14
+; CHECK-NEXT: stdx 3, 12, 31
+; CHECK-NEXT: bdnz .LBB0_2
+; CHECK-NEXT: # %bb.3:
+; CHECK-NEXT: ld 12, 384(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 3, 0(12)
+; CHECK-NEXT: ld 12, 376(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 3, 0(12)
+; CHECK-NEXT: ld 12, 368(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 3, 0(12)
+; CHECK-NEXT: ld 12, 360(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 3, 0(12)
+; CHECK-NEXT: ld 12, 352(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 3, 0(12)
+; CHECK-NEXT: ld 12, 344(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 3, 0(12)
+; CHECK-NEXT: ld 12, 336(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 3, 0(12)
+; CHECK-NEXT: ld 12, 328(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 3, 0(12)
+; CHECK-NEXT: ld 12, 320(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 3, 0(12)
+; CHECK-NEXT: ld 12, 312(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 3, 0(12)
+; CHECK-NEXT: ld 12, 304(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 3, 0(12)
+; CHECK-NEXT: ld 12, 296(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 3, 0(12)
+; CHECK-NEXT: ld 12, 288(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 3, 0(12)
+; CHECK-NEXT: ld 12, 280(1) # 8-byte Folded Reload
+; CHECK-NEXT: lwz 4, 396(1) # 4-byte Folded Reload
+; CHECK-NEXT: addi 4, 4, 1
+; CHECK-NEXT: std 3, 0(12)
+; CHECK-NEXT: ld 12, 272(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 3, 0(12)
+; CHECK-NEXT: xoris 12, 4, 6
+; CHECK-NEXT: cmplwi 12, 6784
+; CHECK-NEXT: ld 12, 264(1) # 8-byte Folded Reload
+; CHECK-NEXT: std 3, 0(12)
+; CHECK-NEXT: bne 0, .LBB0_1
+; CHECK-NEXT: # %bb.4:
+; CHECK-NEXT: ld 2, 568(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 31, 712(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 30, 704(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 29, 696(1) # 8-byte Folded Reload
+; CHECK-NEXT: li 3, 0
+; CHECK-NEXT: ld 28, 688(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 27, 680(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 26, 672(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 25, 664(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 24, 656(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 23, 648(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 22, 640(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 21, 632(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 20, 624(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 19, 616(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 18, 608(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 17, 600(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 16, 592(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 15, 584(1) # 8-byte Folded Reload
+; CHECK-NEXT: ld 14, 576(1) # 8-byte Folded Reload
+; CHECK-NEXT: addi 1, 1, 720
+; CHECK-NEXT: blr
+ %3 = getelementptr inbounds i64, i64* %1, i64 144115188075855
+ %4 = getelementptr i64, i64* %1, i64 144115586875855
+ %5 = getelementptr i64, i64* %1, i64 144115587175855
+ %6 = getelementptr i64, i64* %1, i64 144115587075855
+ %7 = getelementptr i64, i64* %1, i64 144115586975855
+ %8 = getelementptr i64, i64* %1, i64 144115587275855
+ %9 = getelementptr i64, i64* %1, i64 144115587575855
+ %10 = getelementptr i64, i64* %1, i64 144115587475855
+ %11 = getelementptr i64, i64* %1, i64 144115587375855
+ %12 = getelementptr i64, i64* %1, i64 144115587675855
+ %13 = getelementptr i64, i64* %1, i64 144115587975855
+ %14 = getelementptr i64, i64* %1, i64 144115587875855
+ %15 = getelementptr i64, i64* %1, i64 144115587775855
+ %16 = getelementptr i64, i64* %1, i64 144115588075855
+ %17 = getelementptr i64, i64* %1, i64 144115588375855
+ %18 = getelementptr i64, i64* %1, i64 144115588275855
+ %19 = getelementptr i64, i64* %1, i64 144115588175855
+ br label %20
+
+20: ; preds = %2, %109
+ %21 = phi i32 [ 0, %2 ], [ %110, %109 ]
+ br label %22
+
+22: ; preds = %22, %20
+ %23 = phi i64 [ 0, %20 ], [ %107, %22 ]
+ %24 = mul i64 %23, 400000
+ %25 = getelementptr i64, i64* %3, i64 %24
+ %26 = or i64 %23, 1
+ %27 = mul i64 %26, 400000
+ %28 = getelementptr i64, i64* %3, i64 %27
+ %29 = or i64 %23, 2
+ %30 = mul i64 %29, 400000
+ %31 = getelementptr i64, i64* %3, i64 %30
+ %32 = or i64 %23, 3
+ %33 = mul i64 %32, 400000
+ %34 = getelementptr i64, i64* %3, i64 %33
+ %35 = mul i64 %23, 400000
+ %36 = add i64 %35, 1600000
+ %37 = getelementptr i64, i64* %3, i64 %36
+ %38 = mul i64 %23, 400000
+ %39 = add i64 %38, 2000000
+ %40 = getelementptr i64, i64* %3, i64 %39
+ %41 = mul i64 %23, 400000
+ %42 = add i64 %41, 2400000
+ %43 = getelementptr i64, i64* %3, i64 %42
+ %44 = mul i64 %23, 400000
+ %45 = add i64 %44, 2800000
+ %46 = getelementptr i64, i64* %3, i64 %45
+ %47 = mul i64 %23, 400000
+ %48 = add i64 %47, 3200000
+ %49 = getelementptr i64, i64* %3, i64 %48
+ %50 = mul i64 %23, 400000
+ %51 = add i64 %50, 3600000
+ %52 = getelementptr i64, i64* %3, i64 %51
+ %53 = mul i64 %23, 400000
+ %54 = add i64 %53, 4000000
+ %55 = getelementptr i64, i64* %3, i64 %54
+ %56 = mul i64 %23, 400000
+ %57 = add i64 %56, 4400000
+ %58 = getelementptr i64, i64* %3, i64 %57
+ %59 = getelementptr inbounds i64, i64* %25, i64 400000
+ %60 = getelementptr inbounds i64, i64* %28, i64 400000
+ %61 = getelementptr inbounds i64, i64* %31, i64 400000
+ %62 = getelementptr inbounds i64, i64* %34, i64 400000
+ %63 = getelementptr inbounds i64, i64* %37, i64 400000
+ %64 = getelementptr inbounds i64, i64* %40, i64 400000
+ %65 = getelementptr inbounds i64, i64* %43, i64 400000
+ %66 = getelementptr inbounds i64, i64* %46, i64 400000
+ %67 = getelementptr inbounds i64, i64* %49, i64 400000
+ %68 = getelementptr inbounds i64, i64* %52, i64 400000
+ %69 = getelementptr inbounds i64, i64* %55, i64 400000
+ %70 = getelementptr inbounds i64, i64* %58, i64 400000
+ store i64 %0, i64* %59, align 8
+ store i64 %0, i64* %60, align 8
+ store i64 %0, i64* %61, align 8
+ store i64 %0, i64* %62, align 8
+ store i64 %0, i64* %63, align 8
+ store i64 %0, i64* %64, align 8
+ store i64 %0, i64* %65, align 8
+ store i64 %0, i64* %66, align 8
+ store i64 %0, i64* %67, align 8
+ store i64 %0, i64* %68, align 8
+ store i64 %0, i64* %69, align 8
+ store i64 %0, i64* %70, align 8
+ %71 = getelementptr inbounds i64, i64* %25, i64 700000
+ %72 = getelementptr inbounds i64, i64* %28, i64 700000
+ %73 = getelementptr inbounds i64, i64* %31, i64 700000
+ %74 = getelementptr inbounds i64, i64* %34, i64 700000
+ %75 = getelementptr inbounds i64, i64* %37, i64 700000
+ %76 = getelementptr inbounds i64, i64* %40, i64 700000
+ %77 = getelementptr inbounds i64, i64* %43, i64 700000
+ %78 = getelementptr inbounds i64, i64* %46, i64 700000
+ %79 = getelementptr inbounds i64, i64* %49, i64 700000
+ %80 = getelementptr inbounds i64, i64* %52, i64 700000
+ %81 = getelementptr inbounds i64, i64* %55, i64 700000
+ %82 = getelementptr inbounds i64, i64* %58, i64 700000
+ store i64 %0, i64* %71, align 8
+ store i64 %0, i64* %72, align 8
+ store i64 %0, i64* %73, align 8
+ store i64 %0, i64* %74, align 8
+ store i64 %0, i64* %75, align 8
+ store i64 %0, i64* %76, align 8
+ store i64 %0, i64* %77, align 8
+ store i64 %0, i64* %78, align 8
+ store i64 %0, i64* %79, align 8
+ store i64 %0, i64* %80, align 8
+ store i64 %0, i64* %81, align 8
+ store i64 %0, i64* %82, align 8
+ %83 = getelementptr inbounds i64, i64* %25, i64 600000
+ %84 = getelementptr inbounds i64, i64* %28, i64 600000
+ %85 = getelementptr inbounds i64, i64* %31, i64 600000
+ %86 = getelementptr inbounds i64, i64* %34, i64 600000
+ %87 = getelementptr inbounds i64, i64* %37, i64 600000
+ %88 = getelementptr inbounds i64, i64* %40, i64 600000
+ %89 = getelementptr inbounds i64, i64* %43, i64 600000
+ %90 = getelementptr inbounds i64, i64* %46, i64 600000
+ %91 = getelementptr inbounds i64, i64* %49, i64 600000
+ %92 = getelementptr inbounds i64, i64* %52, i64 600000
+ %93 = getelementptr inbounds i64, i64* %55, i64 600000
+ %94 = getelementptr inbounds i64, i64* %58, i64 600000
+ store i64 %0, i64* %83, align 8
+ store i64 %0, i64* %84, align 8
+ store i64 %0, i64* %85, align 8
+ store i64 %0, i64* %86, align 8
+ store i64 %0, i64* %87, align 8
+ store i64 %0, i64* %88, align 8
+ store i64 %0, i64* %89, align 8
+ store i64 %0, i64* %90, align 8
+ store i64 %0, i64* %91, align 8
+ store i64 %0, i64* %92, align 8
+ store i64 %0, i64* %93, align 8
+ store i64 %0, i64* %94, align 8
+ %95 = getelementptr inbounds i64, i64* %25, i64 500000
+ %96 = getelementptr inbounds i64, i64* %28, i64 500000
+ %97 = getelementptr inbounds i64, i64* %31, i64 500000
+ %98 = getelementptr inbounds i64, i64* %34, i64 500000
+ %99 = getelementptr inbounds i64, i64* %37, i64 500000
+ %100 = getelementptr inbounds i64, i64* %40, i64 500000
+ %101 = getelementptr inbounds i64, i64* %43, i64 500000
+ %102 = getelementptr inbounds i64, i64* %46, i64 500000
+ %103 = getelementptr inbounds i64, i64* %49, i64 500000
+ %104 = getelementptr inbounds i64, i64* %52, i64 500000
+ %105 = getelementptr inbounds i64, i64* %55, i64 500000
+ %106 = getelementptr inbounds i64, i64* %58, i64 500000
+ store i64 %0, i64* %95, align 8
+ store i64 %0, i64* %96, align 8
+ store i64 %0, i64* %97, align 8
+ store i64 %0, i64* %98, align 8
+ store i64 %0, i64* %99, align 8
+ store i64 %0, i64* %100, align 8
+ store i64 %0, i64* %101, align 8
+ store i64 %0, i64* %102, align 8
+ store i64 %0, i64* %103, align 8
+ store i64 %0, i64* %104, align 8
+ store i64 %0, i64* %105, align 8
+ store i64 %0, i64* %106, align 8
+ %107 = add i64 %23, 12
+ %108 = icmp eq i64 %107, 996
+ br i1 %108, label %109, label %22
+
+109: ; preds = %22
+ store i64 %0, i64* %4, align 8
+ store i64 %0, i64* %5, align 8
+ store i64 %0, i64* %6, align 8
+ store i64 %0, i64* %7, align 8
+ store i64 %0, i64* %8, align 8
+ store i64 %0, i64* %9, align 8
+ store i64 %0, i64* %10, align 8
+ store i64 %0, i64* %11, align 8
+ store i64 %0, i64* %12, align 8
+ store i64 %0, i64* %13, align 8
+ store i64 %0, i64* %14, align 8
+ store i64 %0, i64* %15, align 8
+ store i64 %0, i64* %16, align 8
+ store i64 %0, i64* %17, align 8
+ store i64 %0, i64* %18, align 8
+ store i64 %0, i64* %19, align 8
+ %110 = add nuw nsw i32 %21, 1
+ %111 = icmp eq i32 %110, 400000
+ br i1 %111, label %112, label %20
+
+112: ; preds = %109
+ ret i32 0
+}
More information about the llvm-commits
mailing list