[llvm] [AMDGPU] Convert flat scratch SS->SV in FI elimination (PR #166979)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Nov 7 10:29:18 PST 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Anshil Gandhi (gandhi56)
<details>
<summary>Changes</summary>
- Fix O0 crash on gfx950 by remapping SS to SV and materializing the offset in a VGPR when FrameReg is unavailable and no SGPR can be scavenged. Resolves issue #<!-- -->155902
- Reuse existing VGPR temp if available; otherwise scavenge one.
- Add regression: llvm/test/CodeGen/AMDGPU/flat-scratch-ss-to-sv-scavenge.ll.
Co-authored by Matt Arsenault
---
Patch is 34.61 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/166979.diff
2 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp (+36-2)
- (added) llvm/test/CodeGen/AMDGPU/flat-scratch-ss-to-sv-scavenge.ll (+630)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
index a6c1af24e13e9..0c7bb95432fe4 100644
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
@@ -2981,8 +2981,42 @@ bool SIRegisterInfo::eliminateFrameIndex(MachineBasicBlock::iterator MI,
: RS->scavengeRegisterBackwards(AMDGPU::SReg_32_XM0RegClass,
MI, false, 0, !UseSGPR);
- // TODO: for flat scratch another attempt can be made with a VGPR index
- // if no SGPRs can be scavenged.
+ // Fallback: If we need an SGPR but cannot scavenge one and there is no
+ // frame register, try to convert the flat-scratch instruction to use a
+ // VGPR index (SS -> SV) and materialize the offset in a VGPR.
+ if (!TmpSReg && !FrameReg && TII->isFLATScratch(*MI)) {
+ // Reuse an existing VGPR temp if available, otherwise scavenge one.
+ Register VTmp = (!UseSGPR && TmpReg)
+ ? TmpReg
+ : RS->scavengeRegisterBackwards(
+ AMDGPU::VGPR_32RegClass, MI, false, 0);
+ if (VTmp) {
+ // Put the large offset into a VGPR and zero the immediate offset.
+ BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_MOV_B32_e32), VTmp)
+ .addImm(Offset);
+
+ unsigned Opc = MI->getOpcode();
+ int NewOpc = AMDGPU::getFlatScratchInstSVfromSS(Opc);
+ if (NewOpc != -1) {
+ int OldSAddrIdx =
+ AMDGPU::getNamedOperandIdx(Opc, AMDGPU::OpName::saddr);
+ int NewVAddrIdx =
+ AMDGPU::getNamedOperandIdx(NewOpc, AMDGPU::OpName::vaddr);
+ if (OldSAddrIdx == NewVAddrIdx && OldSAddrIdx >= 0) {
+ MI->setDesc(TII->get(NewOpc));
+ // Replace former saddr (now vaddr) with the VGPR index.
+ MI->getOperand(NewVAddrIdx).ChangeToRegister(VTmp, false);
+ // Reset the immediate offset to 0 as it is now in vaddr.
+ MachineOperand *OffOp =
+ TII->getNamedOperand(*MI, AMDGPU::OpName::offset);
+ assert(OffOp && "Flat scratch SV form must have offset operand");
+ OffOp->setImm(0);
+ return false;
+ }
+ }
+ }
+ }
+
if ((!TmpSReg && !FrameReg) || (!TmpReg && !UseSGPR))
report_fatal_error("Cannot scavenge register in FI elimination!");
diff --git a/llvm/test/CodeGen/AMDGPU/flat-scratch-ss-to-sv-scavenge.ll b/llvm/test/CodeGen/AMDGPU/flat-scratch-ss-to-sv-scavenge.ll
new file mode 100644
index 0000000000000..9d8bbc198afa0
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/flat-scratch-ss-to-sv-scavenge.ll
@@ -0,0 +1,630 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
+; REQUIRES: amdgpu-registered-target
+; Ensure we don't crash with: "Cannot scavenge register in FI elimination!"
+; RUN: llc < %s -verify-machineinstrs -O0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a | FileCheck %s --check-prefix=GFX90A
+; RUN: llc < %s -verify-machineinstrs -O0 -mtriple=amdgcn-amd-amdhsa -mcpu=gfx950 | FileCheck %s --check-prefix=GFX950
+
+target datalayout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32-p7:160:256:256:32-p8:128:128-p9:192:256:256:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5-G1-ni:7:8:9"
+target triple = "amdgcn-amd-amdhsa"
+
+define amdgpu_kernel void @issue155902(i64 %arg2, i64 %arg3, i64 %arg4, i64 %arg5, i64 %arg6, i64 %arg7, i64 %arg8, i64 %arg9, i64 %arg10, i64 %arg11, i64 %arg12, i64 %arg13, i64 %arg14, i64 %arg15, i64 %arg16, i64 %arg17, i64 %arg18, i64 %arg19, i64 %arg20, i64 %arg21, i64 %arg22, i64 %arg23, i64 %arg24, i64 %arg25, i64 %arg26, i64 %arg27, i64 %arg28, i64 %arg29, i64 %arg30, i64 %arg31, i64 %arg32, i64 %arg33, i64 %arg1, i64 %arg35, i64 %arg34, i64 %arg, i64 %arg38, i64 %arg39, i64 %arg40, i64 %arg41, i64 %arg42, i64 %arg43, i64 %arg44, i64 %arg37, i64 %arg46, i64 %arg47, i64 %arg48, i64 %arg49, i64 %arg45, i64 %arg36) {
+; GFX90A-LABEL: issue155902:
+; GFX90A: ; %bb.0: ; %bb
+; GFX90A-NEXT: s_add_u32 s0, s0, s17
+; GFX90A-NEXT: s_addc_u32 s1, s1, 0
+; GFX90A-NEXT: v_mov_b32_e32 v1, 0x4008
+; GFX90A-NEXT: s_mov_b64 s[4:5], s[8:9]
+; GFX90A-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x0
+; GFX90A-NEXT: ; implicit-def: $vgpr2 : SGPR spill to VGPR lane
+; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
+; GFX90A-NEXT: v_writelane_b32 v2, s6, 0
+; GFX90A-NEXT: v_writelane_b32 v2, s7, 1
+; GFX90A-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x8
+; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
+; GFX90A-NEXT: v_writelane_b32 v2, s6, 2
+; GFX90A-NEXT: v_writelane_b32 v2, s7, 3
+; GFX90A-NEXT: s_load_dwordx2 vcc, s[4:5], 0x10
+; GFX90A-NEXT: s_load_dwordx2 s[98:99], s[4:5], 0x18
+; GFX90A-NEXT: s_load_dwordx2 s[96:97], s[4:5], 0x20
+; GFX90A-NEXT: s_load_dwordx2 s[94:95], s[4:5], 0x28
+; GFX90A-NEXT: s_load_dwordx2 s[92:93], s[4:5], 0x30
+; GFX90A-NEXT: s_load_dwordx2 s[90:91], s[4:5], 0x38
+; GFX90A-NEXT: s_load_dwordx2 s[88:89], s[4:5], 0x40
+; GFX90A-NEXT: s_load_dwordx2 s[86:87], s[4:5], 0x48
+; GFX90A-NEXT: s_load_dwordx2 s[84:85], s[4:5], 0x50
+; GFX90A-NEXT: s_load_dwordx2 s[82:83], s[4:5], 0x58
+; GFX90A-NEXT: s_load_dwordx2 s[80:81], s[4:5], 0x60
+; GFX90A-NEXT: s_load_dwordx2 s[78:79], s[4:5], 0x68
+; GFX90A-NEXT: s_load_dwordx2 s[76:77], s[4:5], 0x70
+; GFX90A-NEXT: s_load_dwordx2 s[74:75], s[4:5], 0x78
+; GFX90A-NEXT: s_load_dwordx2 s[72:73], s[4:5], 0x80
+; GFX90A-NEXT: s_load_dwordx2 s[70:71], s[4:5], 0x88
+; GFX90A-NEXT: s_load_dwordx2 s[68:69], s[4:5], 0x90
+; GFX90A-NEXT: s_load_dwordx2 s[66:67], s[4:5], 0x98
+; GFX90A-NEXT: s_load_dwordx2 s[64:65], s[4:5], 0xa0
+; GFX90A-NEXT: s_load_dwordx2 s[62:63], s[4:5], 0xa8
+; GFX90A-NEXT: s_load_dwordx2 s[60:61], s[4:5], 0xb0
+; GFX90A-NEXT: s_load_dwordx2 s[58:59], s[4:5], 0xb8
+; GFX90A-NEXT: s_load_dwordx2 s[56:57], s[4:5], 0xc0
+; GFX90A-NEXT: s_load_dwordx2 s[54:55], s[4:5], 0xc8
+; GFX90A-NEXT: s_load_dwordx2 s[52:53], s[4:5], 0xd0
+; GFX90A-NEXT: s_load_dwordx2 s[50:51], s[4:5], 0xd8
+; GFX90A-NEXT: s_load_dwordx2 s[48:49], s[4:5], 0xe0
+; GFX90A-NEXT: s_load_dwordx2 s[46:47], s[4:5], 0xe8
+; GFX90A-NEXT: s_load_dwordx2 s[44:45], s[4:5], 0xf0
+; GFX90A-NEXT: s_load_dwordx2 s[42:43], s[4:5], 0xf8
+; GFX90A-NEXT: s_load_dwordx2 s[40:41], s[4:5], 0x100
+; GFX90A-NEXT: s_load_dwordx2 s[38:39], s[4:5], 0x108
+; GFX90A-NEXT: s_load_dwordx2 s[36:37], s[4:5], 0x110
+; GFX90A-NEXT: s_load_dwordx2 s[34:35], s[4:5], 0x118
+; GFX90A-NEXT: s_load_dwordx2 s[30:31], s[4:5], 0x120
+; GFX90A-NEXT: s_load_dwordx2 s[28:29], s[4:5], 0x128
+; GFX90A-NEXT: s_load_dwordx2 s[26:27], s[4:5], 0x130
+; GFX90A-NEXT: s_load_dwordx2 s[24:25], s[4:5], 0x138
+; GFX90A-NEXT: s_load_dwordx2 s[22:23], s[4:5], 0x140
+; GFX90A-NEXT: s_load_dwordx2 s[20:21], s[4:5], 0x148
+; GFX90A-NEXT: s_load_dwordx2 s[18:19], s[4:5], 0x150
+; GFX90A-NEXT: s_load_dwordx2 s[16:17], s[4:5], 0x158
+; GFX90A-NEXT: s_load_dwordx2 s[14:15], s[4:5], 0x160
+; GFX90A-NEXT: s_load_dwordx2 s[12:13], s[4:5], 0x168
+; GFX90A-NEXT: s_load_dwordx2 s[10:11], s[4:5], 0x170
+; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[4:5], 0x178
+; GFX90A-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x180
+; GFX90A-NEXT: s_nop 0
+; GFX90A-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x188
+; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
+; GFX90A-NEXT: v_writelane_b32 v2, s4, 4
+; GFX90A-NEXT: v_writelane_b32 v2, s5, 5
+; GFX90A-NEXT: s_mov_b64 s[4:5], 0
+; GFX90A-NEXT: s_mov_b32 s33, s5
+; GFX90A-NEXT: v_writelane_b32 v2, s33, 6
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: v_mov_b32_e32 v3, 0x4008
+; GFX90A-NEXT: buffer_store_dword v0, v3, s[0:3], 0 offen offset:12
+; GFX90A-NEXT: s_mov_b32 s33, s4
+; GFX90A-NEXT: v_readlane_b32 s4, v2, 6
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: v_mov_b32_e32 v3, 0x4008
+; GFX90A-NEXT: buffer_store_dword v0, v3, s[0:3], 0 offen offset:8
+; GFX90A-NEXT: v_mov_b32_e32 v0, s4
+; GFX90A-NEXT: v_mov_b32_e32 v3, 0x4008
+; GFX90A-NEXT: buffer_store_dword v0, v3, s[0:3], 0 offen offset:4
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen
+; GFX90A-NEXT: v_mov_b32_e32 v0, s4
+; GFX90A-NEXT: v_readlane_b32 s4, v2, 0
+; GFX90A-NEXT: v_readlane_b32 s5, v2, 1
+; GFX90A-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen offset:20
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen offset:16
+; GFX90A-NEXT: s_mov_b32 s33, s5
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s4
+; GFX90A-NEXT: v_readlane_b32 s4, v2, 2
+; GFX90A-NEXT: v_readlane_b32 s5, v2, 3
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s5
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s4
+; GFX90A-NEXT: v_readlane_b32 s4, v2, 4
+; GFX90A-NEXT: v_readlane_b32 s5, v2, 5
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, vcc_hi
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, vcc_lo
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s99
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s98
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s97
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s96
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s95
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s94
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s93
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s92
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s91
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s90
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s89
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s88
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s87
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s86
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s85
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s84
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s83
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s82
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s81
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s80
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s79
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s78
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s77
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s76
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s75
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s74
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s73
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s72
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s71
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s70
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s69
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s68
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s67
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s66
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s65
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s64
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s63
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s62
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s61
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s60
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s59
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s58
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s57
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s56
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s55
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s54
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s53
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s52
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s51
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s50
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s49
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s48
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s47
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s46
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s45
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s44
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s43
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s42
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s41
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s40
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s39
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s38
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s37
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s36
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s35
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: s_mov_b32 s33, s34
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s33, s31
+; GFX90A-NEXT: v_mov_b32_e32 v0, s33
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: ; kill: def $sgpr30 killed $sgpr30 killed $sgpr30_sgpr31
+; GFX90A-NEXT: v_mov_b32_e32 v0, s30
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s30, s29
+; GFX90A-NEXT: v_mov_b32_e32 v0, s30
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: ; kill: def $sgpr28 killed $sgpr28 killed $sgpr28_sgpr29
+; GFX90A-NEXT: v_mov_b32_e32 v0, s28
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s28, s27
+; GFX90A-NEXT: v_mov_b32_e32 v0, s28
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: ; kill: def $sgpr26 killed $sgpr26 killed $sgpr26_sgpr27
+; GFX90A-NEXT: v_mov_b32_e32 v0, s26
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s26, s25
+; GFX90A-NEXT: v_mov_b32_e32 v0, s26
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0 offset:4
+; GFX90A-NEXT: ; kill: def $sgpr24 killed $sgpr24 killed $sgpr24_sgpr25
+; GFX90A-NEXT: v_mov_b32_e32 v0, s24
+; GFX90A-NEXT: buffer_store_dword v0, off, s[0:3], 0
+; GFX90A-NEXT: s_mov_b32 s24, s23
+; GFX90A-NEXT: ...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/166979
More information about the llvm-commits
mailing list