[llvm] [AMDGPU] Remove verification failing cases due to bundle (PR #139868)
via llvm-commits
llvm-commits at lists.llvm.org
Wed May 14 02:39:55 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: None (Shoreshen)
<details>
<summary>Changes</summary>
This is a fix up PR for https://github.com/llvm/llvm-project/pull/136112
There are test cases failing machine instruction verifier due to bundle (see this issue:https://github.com/llvm/llvm-project/issues/139102#issuecomment-2863620759)
---
Patch is 1.29 MiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/139868.diff
1 Files Affected:
- (modified) llvm/test/CodeGen/AMDGPU/amdgcn.bitcast.1024bit.ll (+225-23539)
``````````diff
diff --git a/llvm/test/CodeGen/AMDGPU/amdgcn.bitcast.1024bit.ll b/llvm/test/CodeGen/AMDGPU/amdgcn.bitcast.1024bit.ll
index 8d491f6bafbbc..a67679c1293bb 100644
--- a/llvm/test/CodeGen/AMDGPU/amdgcn.bitcast.1024bit.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdgcn.bitcast.1024bit.ll
@@ -1,10 +1,10 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
-; RUN: llc -mtriple=amdgcn -mcpu=tahiti < %s | FileCheck -check-prefix=SI %s
-; RUN: llc -mtriple=amdgcn -mcpu=tonga < %s | FileCheck -check-prefix=VI %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefix=GFX9 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck -check-prefixes=GFX11,GFX11-TRUE16 %s
-; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GFX11,GFX11-FAKE16 %s
+; RUN: llc -mtriple=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
+; RUN: llc -mtriple=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=VI %s
+; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX9 %s
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX11,GFX11-TRUE16 %s
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX11,GFX11-FAKE16 %s
define <32 x float> @bitcast_v32i32_to_v32f32(<32 x i32> %a, i32 %b) {
; SI-LABEL: bitcast_v32i32_to_v32f32:
@@ -203181,23320 +203181,6 @@ end:
ret <128 x i8> %phi
}
-define <64 x i16> @bitcast_v128i8_to_v64i16(<128 x i8> %a, i32 %b) {
-; SI-LABEL: bitcast_v128i8_to_v64i16:
-; SI: ; %bb.0:
-; SI-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; SI-NEXT: buffer_store_dword v40, off, s[0:3], s32 offset:456 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v41, off, s[0:3], s32 offset:452 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v42, off, s[0:3], s32 offset:448 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v43, off, s[0:3], s32 offset:444 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v44, off, s[0:3], s32 offset:440 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v45, off, s[0:3], s32 offset:436 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v46, off, s[0:3], s32 offset:432 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v47, off, s[0:3], s32 offset:428 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v56, off, s[0:3], s32 offset:424 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v57, off, s[0:3], s32 offset:420 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v58, off, s[0:3], s32 offset:416 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v59, off, s[0:3], s32 offset:412 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v60, off, s[0:3], s32 offset:408 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v61, off, s[0:3], s32 offset:404 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v62, off, s[0:3], s32 offset:400 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v63, off, s[0:3], s32 offset:396 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v29, off, s[0:3], s32 offset:492 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v27, off, s[0:3], s32 offset:496 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v25, off, s[0:3], s32 offset:940 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v23, off, s[0:3], s32 offset:472 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v21, off, s[0:3], s32 offset:488 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v19, off, s[0:3], s32 offset:484 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v17, off, s[0:3], s32 offset:640 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v15, off, s[0:3], s32 offset:460 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:480 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:476 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:632 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:648 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:468 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:464 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:620 ; 4-byte Folded Spill
-; SI-NEXT: buffer_load_dword v25, off, s[0:3], s32 offset:392
-; SI-NEXT: s_waitcnt expcnt(1)
-; SI-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:4
-; SI-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:28
-; SI-NEXT: buffer_load_dword v9, off, s[0:3], s32 offset:36
-; SI-NEXT: buffer_load_dword v5, off, s[0:3], s32 offset:20
-; SI-NEXT: buffer_load_dword v13, off, s[0:3], s32 offset:60
-; SI-NEXT: buffer_load_dword v15, off, s[0:3], s32 offset:68
-; SI-NEXT: buffer_load_dword v11, off, s[0:3], s32 offset:52
-; SI-NEXT: buffer_load_dword v19, off, s[0:3], s32 offset:92
-; SI-NEXT: buffer_load_dword v21, off, s[0:3], s32 offset:100
-; SI-NEXT: buffer_load_dword v17, off, s[0:3], s32 offset:84
-; SI-NEXT: buffer_load_dword v23, off, s[0:3], s32 offset:124
-; SI-NEXT: buffer_load_dword v27, off, s[0:3], s32 offset:132
-; SI-NEXT: buffer_load_dword v29, off, s[0:3], s32 offset:116
-; SI-NEXT: buffer_load_dword v31, off, s[0:3], s32 offset:156
-; SI-NEXT: buffer_load_dword v32, off, s[0:3], s32 offset:164
-; SI-NEXT: buffer_load_dword v33, off, s[0:3], s32 offset:148
-; SI-NEXT: buffer_load_dword v34, off, s[0:3], s32 offset:188
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v1, off, s[0:3], s32 offset:128
-; SI-NEXT: v_lshlrev_b32_e32 v4, 24, v4
-; SI-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:508 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v4, 8, v14
-; SI-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:516 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v4, 24, v16
-; SI-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:512 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v4, 24, v12
-; SI-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:520 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v4, 8, v22
-; SI-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:524 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v4, 24, v20
-; SI-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:528 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v4, 8, v30
-; SI-NEXT: v_lshlrev_b32_e32 v6, 8, v6
-; SI-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:504 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v6, 24, v8
-; SI-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:532 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v4, 24, v28
-; SI-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:500 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:536 ; 4-byte Folded Spill
-; SI-NEXT: v_lshlrev_b32_e32 v24, 24, v24
-; SI-NEXT: ; implicit-def: $vgpr43
-; SI-NEXT: ; implicit-def: $vgpr40
-; SI-NEXT: ; implicit-def: $vgpr22
-; SI-NEXT: ; implicit-def: $vgpr20
-; SI-NEXT: ; implicit-def: $vgpr56
-; SI-NEXT: ; implicit-def: $vgpr41
-; SI-NEXT: ; implicit-def: $vgpr39
-; SI-NEXT: ; implicit-def: $vgpr53
-; SI-NEXT: ; implicit-def: $vgpr50
-; SI-NEXT: ; implicit-def: $vgpr49
-; SI-NEXT: ; implicit-def: $vgpr48
-; SI-NEXT: ; implicit-def: $vgpr35
-; SI-NEXT: ; implicit-def: $vgpr55
-; SI-NEXT: ; implicit-def: $vgpr63
-; SI-NEXT: ; implicit-def: $vgpr58
-; SI-NEXT: ; implicit-def: $vgpr61
-; SI-NEXT: ; implicit-def: $vgpr52
-; SI-NEXT: ; implicit-def: $vgpr57
-; SI-NEXT: ; implicit-def: $vgpr28
-; SI-NEXT: ; implicit-def: $vgpr38
-; SI-NEXT: ; implicit-def: $vgpr46
-; SI-NEXT: ; implicit-def: $vgpr36
-; SI-NEXT: ; implicit-def: $vgpr44
-; SI-NEXT: ; kill: killed $vgpr43
-; SI-NEXT: ; implicit-def: $vgpr43
-; SI-NEXT: ; kill: killed $vgpr40
-; SI-NEXT: ; implicit-def: $vgpr40
-; SI-NEXT: buffer_load_dword v45, off, s[0:3], s32 offset:360
-; SI-NEXT: s_waitcnt vmcnt(14)
-; SI-NEXT: v_cmp_ne_u32_e32 vcc, 0, v25
-; SI-NEXT: v_lshlrev_b32_e32 v30, 24, v3
-; SI-NEXT: v_lshlrev_b32_e32 v3, 8, v7
-; SI-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:552 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v3, 24, v9
-; SI-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:544 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v3, 24, v5
-; SI-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:584 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v3, 8, v13
-; SI-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:596 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v3, 24, v15
-; SI-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:592 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v3, 24, v11
-; SI-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:600 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v3, 8, v19
-; SI-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:612 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v3, 24, v21
-; SI-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:608 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt vmcnt(14)
-; SI-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:564 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v1, off, s[0:3], s32 offset:152
-; SI-NEXT: v_lshlrev_b32_e32 v3, 24, v17
-; SI-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:616 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v3, 8, v23
-; SI-NEXT: buffer_store_dword v3, off, s[0:3], s32 offset:644 ; 4-byte Folded Spill
-; SI-NEXT: v_lshlrev_b32_e32 v4, 24, v27
-; SI-NEXT: v_lshlrev_b32_e32 v5, 24, v32
-; SI-NEXT: buffer_load_dword v15, off, s[0:3], s32 offset:332
-; SI-NEXT: ; implicit-def: $vgpr23
-; SI-NEXT: ; implicit-def: $vgpr25
-; SI-NEXT: ; implicit-def: $vgpr32
-; SI-NEXT: ; implicit-def: $vgpr27
-; SI-NEXT: ; implicit-def: $vgpr21
-; SI-NEXT: ; kill: killed $vgpr23
-; SI-NEXT: ; implicit-def: $vgpr23
-; SI-NEXT: s_waitcnt vmcnt(3)
-; SI-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:580 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v1, off, s[0:3], s32 offset:160
-; SI-NEXT: s_waitcnt vmcnt(0)
-; SI-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:576 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v1, off, s[0:3], s32 offset:96
-; SI-NEXT: s_waitcnt vmcnt(0)
-; SI-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:556 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v1, off, s[0:3], s32 offset:88
-; SI-NEXT: s_waitcnt vmcnt(0)
-; SI-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:560 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v1, off, s[0:3], s32 offset:64
-; SI-NEXT: s_waitcnt vmcnt(0)
-; SI-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:540 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v1, off, s[0:3], s32 offset:56
-; SI-NEXT: s_waitcnt vmcnt(0)
-; SI-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:548 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v1, off, s[0:3], s32 offset:112
-; SI-NEXT: s_waitcnt vmcnt(0)
-; SI-NEXT: buffer_store_dword v1, off, s[0:3], s32 offset:572 ; 4-byte Folded Spill
-; SI-NEXT: buffer_load_dword v17, off, s[0:3], s32 offset:144
-; SI-NEXT: buffer_load_dword v3, off, s[0:3], s32 offset:140
-; SI-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:628 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v4, 24, v29
-; SI-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:664 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v4, 8, v31
-; SI-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:696 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v4, off, s[0:3], s32 offset:184
-; SI-NEXT: v_lshlrev_b32_e32 v29, 8, v2
-; SI-NEXT: v_lshlrev_b32_e32 v2, 8, v18
-; SI-NEXT: buffer_load_dword v1, off, s[0:3], s32 offset:108
-; SI-NEXT: ; implicit-def: $vgpr18
-; SI-NEXT: ; implicit-def: $vgpr31
-; SI-NEXT: s_waitcnt vmcnt(1)
-; SI-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:624 ; 4-byte Folded Spill
-; SI-NEXT: buffer_load_dword v6, off, s[0:3], s32 offset:180
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v4, off, s[0:3], s32 offset:176
-; SI-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:692 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v5, 24, v33
-; SI-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:700 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v5, 8, v34
-; SI-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:716 ; 4-byte Folded Spill
-; SI-NEXT: v_lshlrev_b32_e32 v33, 8, v10
-; SI-NEXT: ; implicit-def: $vgpr10
-; SI-NEXT: s_waitcnt vmcnt(4)
-; SI-NEXT: v_lshlrev_b32_e32 v6, 24, v6
-; SI-NEXT: s_waitcnt vmcnt(3)
-; SI-NEXT: buffer_store_dword v4, off, s[0:3], s32 offset:636 ; 4-byte Folded Spill
-; SI-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:196
-; SI-NEXT: buffer_load_dword v8, off, s[0:3], s32 offset:220
-; SI-NEXT: s_waitcnt expcnt(1)
-; SI-NEXT: buffer_load_dword v5, off, s[0:3], s32 offset:192
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v4, off, s[0:3], s32 offset:172
-; SI-NEXT: s_waitcnt vmcnt(3)
-; SI-NEXT: v_lshlrev_b32_e32 v7, 24, v7
-; SI-NEXT: s_waitcnt vmcnt(1)
-; SI-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:668 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v5, off, s[0:3], s32 offset:216
-; SI-NEXT: s_waitcnt vmcnt(0)
-; SI-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:704 ; 4-byte Folded Spill
-; SI-NEXT: buffer_load_dword v9, off, s[0:3], s32 offset:212
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v5, off, s[0:3], s32 offset:208
-; SI-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:736 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v6, 8, v8
-; SI-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:728 ; 4-byte Folded Spill
-; SI-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:752 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt vmcnt(3)
-; SI-NEXT: buffer_store_dword v5, off, s[0:3], s32 offset:708 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(1)
-; SI-NEXT: buffer_load_dword v6, off, s[0:3], s32 offset:228
-; SI-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:252
-; SI-NEXT: buffer_load_dword v8, off, s[0:3], s32 offset:224
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v5, off, s[0:3], s32 offset:204
-; SI-NEXT: s_waitcnt vmcnt(3)
-; SI-NEXT: v_lshlrev_b32_e32 v6, 24, v6
-; SI-NEXT: s_waitcnt vmcnt(1)
-; SI-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:744 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v8, off, s[0:3], s32 offset:248
-; SI-NEXT: s_waitcnt vmcnt(0)
-; SI-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:760 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v8, off, s[0:3], s32 offset:244
-; SI-NEXT: buffer_load_dword v11, off, s[0:3], s32 offset:240
-; SI-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:788 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v6, 24, v9
-; SI-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:800 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v6, 8, v7
-; SI-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:828 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt vmcnt(3)
-; SI-NEXT: buffer_store_dword v11, off, s[0:3], s32 offset:764 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v11, off, s[0:3], s32 offset:236
-; SI-NEXT: buffer_load_dword v6, off, s[0:3], s32 offset:260
-; SI-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:284
-; SI-NEXT: buffer_load_dword v9, off, s[0:3], s32 offset:256
-; SI-NEXT: s_waitcnt vmcnt(2)
-; SI-NEXT: v_lshlrev_b32_e32 v6, 24, v6
-; SI-NEXT: s_waitcnt vmcnt(0)
-; SI-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:780 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v9, off, s[0:3], s32 offset:280
-; SI-NEXT: s_waitcnt vmcnt(0)
-; SI-NEXT: buffer_store_dword v9, off, s[0:3], s32 offset:804 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v9, off, s[0:3], s32 offset:276
-; SI-NEXT: buffer_load_dword v12, off, s[0:3], s32 offset:272
-; SI-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:832 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v6, 24, v8
-; SI-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:840 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v6, 8, v7
-; SI-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:928 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt vmcnt(3)
-; SI-NEXT: buffer_store_dword v12, off, s[0:3], s32 offset:808 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v12, off, s[0:3], s32 offset:268
-; SI-NEXT: buffer_load_dword v6, off, s[0:3], s32 offset:292
-; SI-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:316
-; SI-NEXT: buffer_load_dword v8, off, s[0:3], s32 offset:288
-; SI-NEXT: s_waitcnt vmcnt(2)
-; SI-NEXT: v_lshlrev_b32_e32 v6, 24, v6
-; SI-NEXT: s_waitcnt vmcnt(1)
-; SI-NEXT: v_lshlrev_b32_e32 v34, 8, v7
-; SI-NEXT: s_waitcnt vmcnt(0)
-; SI-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:820 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v8, off, s[0:3], s32 offset:312
-; SI-NEXT: s_waitcnt vmcnt(0)
-; SI-NEXT: buffer_store_dword v8, off, s[0:3], s32 offset:844 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v8, off, s[0:3], s32 offset:308
-; SI-NEXT: buffer_load_dword v13, off, s[0:3], s32 offset:304
-; SI-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:932 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: v_lshlrev_b32_e32 v6, 24, v9
-; SI-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:948 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt vmcnt(3)
-; SI-NEXT: v_lshlrev_b32_e32 v51, 24, v8
-; SI-NEXT: s_waitcnt vmcnt(2)
-; SI-NEXT: buffer_store_dword v13, off, s[0:3], s32 offset:912 ; 4-byte Folded Spill
-; SI-NEXT: s_waitcnt expcnt(1)
-; SI-NEXT: buffer_load_dword v6, off, s[0:3], s32 offset:324
-; SI-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:348
-; SI-NEXT: buffer_load_dword v9, off, s[0:3], s32 offset:320
-; SI-NEXT: s_waitcnt expcnt(0)
-; SI-NEXT: buffer_load_dword v13, off, s[0:3], s32 offset:300
-; SI-NEXT: s_waitcnt vmcnt(3)
-; SI-NEXT: v_lshlrev_b32_e32 v37, 24, v6
-; SI-NEXT: s_waitcnt vmcnt(2)
-; SI-...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/139868
More information about the llvm-commits
mailing list