[llvm] [AMDGPU] Fold constant offset into SV form addressing in SVS frame index fallback (PR #208629)
Anshil Gandhi via llvm-commits
llvm-commits at lists.llvm.org
Thu Jul 16 08:23:08 PDT 2026
https://github.com/gandhi56 updated https://github.com/llvm/llvm-project/pull/208629
>From eee37bafa0b6a39d24a883deb90c26c603434755 Mon Sep 17 00:00:00 2001
From: Anshil Gandhi <Anshil.Gandhi at amd.com>
Date: Fri, 10 Jul 2026 01:13:04 -0500
Subject: [PATCH] [AMDGPU] Fold constant offset into SV form addressing in SVS
frame index fallback
---
llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp | 15 +++++++--
...eliminate-frame-index-flat-scratch-svs.mir | 32 +++++++++----------
2 files changed, 29 insertions(+), 18 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
index 619db2f61e0e9..358aa054b3a3f 100644
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
@@ -3245,12 +3245,23 @@ bool SIRegisterInfo::eliminateFrameIndex(MachineBasicBlock::iterator MI,
if (ST.hasFlatScratchSVSMode() && SVOpcode != -1) {
Register TmpVGPR = RS->scavengeRegisterBackwards(
AMDGPU::VGPR_32RegClass, MI, false, 0, /*AllowSpill=*/true);
+
+ // Fold as much of the constant offset as possible into the SV form
+ // instruction's immediate offset field, and materialize the
+ // remainder (plus the frame register, if any) into the scavenged
+ // VGPR used as the vaddr.
+ int64_t FullOffset =
+ Offset +
+ TII->getNamedOperand(*MI, AMDGPU::OpName::offset)->getImm();
+ auto [ImmOffset, RemainderOffset] =
+ TII->splitFlatOffset(FullOffset, AMDGPUAS::PRIVATE_ADDRESS,
+ AMDGPU::FlatAddrSpace::FlatScratch);
BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_MOV_B32_e32), TmpVGPR)
- .addImm(Offset);
+ .addImm(RemainderOffset);
BuildMI(*MBB, MI, DL, TII->get(SVOpcode))
.add(MI->getOperand(0)) // $vdata
.addReg(TmpVGPR) // $vaddr
- .addImm(0) // Offset
+ .addImm(ImmOffset) // $offset
.add(*TII->getNamedOperand(*MI, AMDGPU::OpName::cpol));
MI->eraseFromParent();
return true;
diff --git a/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-flat-scratch-svs.mir b/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-flat-scratch-svs.mir
index 1d377af057377..b00f7a6762620 100644
--- a/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-flat-scratch-svs.mir
+++ b/llvm/test/CodeGen/AMDGPU/eliminate-frame-index-flat-scratch-svs.mir
@@ -42,15 +42,15 @@ body: |
; GFX950-LABEL: name: scratch_store_svs_fallback
; GFX950: liveins: $vgpr0, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $sgpr16, $sgpr17, $sgpr18, $sgpr19, $sgpr20, $sgpr21, $sgpr22, $sgpr23, $sgpr24, $sgpr25, $sgpr26, $sgpr27, $sgpr28, $sgpr29, $sgpr30, $sgpr31, $sgpr33, $sgpr34, $sgpr35, $sgpr36, $sgpr37, $sgpr38, $sgpr39, $sgpr40, $sgpr41, $sgpr42, $sgpr43, $sgpr44, $sgpr45, $sgpr46, $sgpr47, $sgpr48, $sgpr49, $sgpr50, $sgpr51, $sgpr52, $sgpr53, $sgpr54, $sgpr55, $sgpr56, $sgpr57, $sgpr58, $sgpr59, $sgpr60, $sgpr61, $sgpr62, $sgpr63, $sgpr64, $sgpr65, $sgpr66, $sgpr67, $sgpr68, $sgpr69, $sgpr70, $sgpr71, $sgpr72, $sgpr73, $sgpr74, $sgpr75, $sgpr76, $sgpr77, $sgpr78, $sgpr79, $sgpr80, $sgpr81, $sgpr82, $sgpr83, $sgpr84, $sgpr85, $sgpr86, $sgpr87, $sgpr88, $sgpr89, $sgpr90, $sgpr91, $sgpr92, $sgpr93, $sgpr94, $sgpr95, $sgpr96, $sgpr97, $sgpr98, $sgpr99, $sgpr100, $sgpr101, $sgpr102, $sgpr103, $sgpr104, $sgpr105, $vcc_lo, $vcc_hi
; GFX950-NEXT: {{ $}}
- ; GFX950-NEXT: $vgpr1 = V_MOV_B32_e32 16388, implicit $exec
- ; GFX950-NEXT: SCRATCH_STORE_DWORD $vgpr0, $vgpr1, 0, 0, implicit $exec, implicit $flat_scr
+ ; GFX950-NEXT: $vgpr1 = V_MOV_B32_e32 16384, implicit $exec
+ ; GFX950-NEXT: SCRATCH_STORE_DWORD $vgpr0, $vgpr1, 4, 0, implicit $exec, implicit $flat_scr
; GFX950-NEXT: S_ENDPGM 0, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr28, implicit $sgpr29, implicit $sgpr30, implicit $sgpr31, implicit $sgpr33, implicit $sgpr34, implicit $sgpr35, implicit $sgpr36, implicit $sgpr37, implicit $sgpr38, implicit $sgpr39, implicit $sgpr40, implicit $sgpr41, implicit $sgpr42, implicit $sgpr43, implicit $sgpr44, implicit $sgpr45, implicit $sgpr46, implicit $sgpr47, implicit $sgpr48, implicit $sgpr49, implicit $sgpr50, implicit $sgpr51, implicit $sgpr52, implicit $sgpr53, implicit $sgpr54, implicit $sgpr55, implicit $sgpr56, implicit $sgpr57, implicit $sgpr58, implicit $sgpr59, implicit $sgpr60, implicit $sgpr61, implicit $sgpr62, implicit $sgpr63, implicit $sgpr64, implicit $sgpr65, implicit $sgpr66, implicit $sgpr67, implicit $sgpr68, implicit $sgpr69, implicit $sgpr70, implicit $sgpr71, implicit $sgpr72, implicit $sgpr73, implicit $sgpr74, implicit $sgpr75, implicit $sgpr76, implicit $sgpr77, implicit $sgpr78, implicit $sgpr79, implicit $sgpr80, implicit $sgpr81, implicit $sgpr82, implicit $sgpr83, implicit $sgpr84, implicit $sgpr85, implicit $sgpr86, implicit $sgpr87, implicit $sgpr88, implicit $sgpr89, implicit $sgpr90, implicit $sgpr91, implicit $sgpr92, implicit $sgpr93, implicit $sgpr94, implicit $sgpr95, implicit $sgpr96, implicit $sgpr97, implicit $sgpr98, implicit $sgpr99, implicit $sgpr100, implicit $sgpr101, implicit $sgpr102, implicit $sgpr103, implicit $sgpr104, implicit $sgpr105, implicit $vcc_lo, implicit $vcc_hi
;
; GFX11-LABEL: name: scratch_store_svs_fallback
; GFX11: liveins: $vgpr0, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $sgpr16, $sgpr17, $sgpr18, $sgpr19, $sgpr20, $sgpr21, $sgpr22, $sgpr23, $sgpr24, $sgpr25, $sgpr26, $sgpr27, $sgpr28, $sgpr29, $sgpr30, $sgpr31, $sgpr33, $sgpr34, $sgpr35, $sgpr36, $sgpr37, $sgpr38, $sgpr39, $sgpr40, $sgpr41, $sgpr42, $sgpr43, $sgpr44, $sgpr45, $sgpr46, $sgpr47, $sgpr48, $sgpr49, $sgpr50, $sgpr51, $sgpr52, $sgpr53, $sgpr54, $sgpr55, $sgpr56, $sgpr57, $sgpr58, $sgpr59, $sgpr60, $sgpr61, $sgpr62, $sgpr63, $sgpr64, $sgpr65, $sgpr66, $sgpr67, $sgpr68, $sgpr69, $sgpr70, $sgpr71, $sgpr72, $sgpr73, $sgpr74, $sgpr75, $sgpr76, $sgpr77, $sgpr78, $sgpr79, $sgpr80, $sgpr81, $sgpr82, $sgpr83, $sgpr84, $sgpr85, $sgpr86, $sgpr87, $sgpr88, $sgpr89, $sgpr90, $sgpr91, $sgpr92, $sgpr93, $sgpr94, $sgpr95, $sgpr96, $sgpr97, $sgpr98, $sgpr99, $sgpr100, $sgpr101, $sgpr102, $sgpr103, $sgpr104, $sgpr105, $vcc_lo, $vcc_hi
; GFX11-NEXT: {{ $}}
- ; GFX11-NEXT: $vgpr1 = V_MOV_B32_e32 16388, implicit $exec
- ; GFX11-NEXT: SCRATCH_STORE_DWORD $vgpr0, $vgpr1, 0, 0, implicit $exec, implicit $flat_scr
+ ; GFX11-NEXT: $vgpr1 = V_MOV_B32_e32 16384, implicit $exec
+ ; GFX11-NEXT: SCRATCH_STORE_DWORD $vgpr0, $vgpr1, 4, 0, implicit $exec, implicit $flat_scr
; GFX11-NEXT: S_ENDPGM 0, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr28, implicit $sgpr29, implicit $sgpr30, implicit $sgpr31, implicit $sgpr33, implicit $sgpr34, implicit $sgpr35, implicit $sgpr36, implicit $sgpr37, implicit $sgpr38, implicit $sgpr39, implicit $sgpr40, implicit $sgpr41, implicit $sgpr42, implicit $sgpr43, implicit $sgpr44, implicit $sgpr45, implicit $sgpr46, implicit $sgpr47, implicit $sgpr48, implicit $sgpr49, implicit $sgpr50, implicit $sgpr51, implicit $sgpr52, implicit $sgpr53, implicit $sgpr54, implicit $sgpr55, implicit $sgpr56, implicit $sgpr57, implicit $sgpr58, implicit $sgpr59, implicit $sgpr60, implicit $sgpr61, implicit $sgpr62, implicit $sgpr63, implicit $sgpr64, implicit $sgpr65, implicit $sgpr66, implicit $sgpr67, implicit $sgpr68, implicit $sgpr69, implicit $sgpr70, implicit $sgpr71, implicit $sgpr72, implicit $sgpr73, implicit $sgpr74, implicit $sgpr75, implicit $sgpr76, implicit $sgpr77, implicit $sgpr78, implicit $sgpr79, implicit $sgpr80, implicit $sgpr81, implicit $sgpr82, implicit $sgpr83, implicit $sgpr84, implicit $sgpr85, implicit $sgpr86, implicit $sgpr87, implicit $sgpr88, implicit $sgpr89, implicit $sgpr90, implicit $sgpr91, implicit $sgpr92, implicit $sgpr93, implicit $sgpr94, implicit $sgpr95, implicit $sgpr96, implicit $sgpr97, implicit $sgpr98, implicit $sgpr99, implicit $sgpr100, implicit $sgpr101, implicit $sgpr102, implicit $sgpr103, implicit $sgpr104, implicit $sgpr105, implicit $vcc_lo, implicit $vcc_hi
SCRATCH_STORE_DWORD_SADDR $vgpr0, %stack.1, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32) into %stack.1, addrspace 5)
S_ENDPGM 0, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr28, implicit $sgpr29, implicit $sgpr30, implicit $sgpr31, implicit $sgpr33, implicit $sgpr34, implicit $sgpr35, implicit $sgpr36, implicit $sgpr37, implicit $sgpr38, implicit $sgpr39, implicit $sgpr40, implicit $sgpr41, implicit $sgpr42, implicit $sgpr43, implicit $sgpr44, implicit $sgpr45, implicit $sgpr46, implicit $sgpr47, implicit $sgpr48, implicit $sgpr49, implicit $sgpr50, implicit $sgpr51, implicit $sgpr52, implicit $sgpr53, implicit $sgpr54, implicit $sgpr55, implicit $sgpr56, implicit $sgpr57, implicit $sgpr58, implicit $sgpr59, implicit $sgpr60, implicit $sgpr61, implicit $sgpr62, implicit $sgpr63, implicit $sgpr64, implicit $sgpr65, implicit $sgpr66, implicit $sgpr67, implicit $sgpr68, implicit $sgpr69, implicit $sgpr70, implicit $sgpr71, implicit $sgpr72, implicit $sgpr73, implicit $sgpr74, implicit $sgpr75, implicit $sgpr76, implicit $sgpr77, implicit $sgpr78, implicit $sgpr79, implicit $sgpr80, implicit $sgpr81, implicit $sgpr82, implicit $sgpr83, implicit $sgpr84, implicit $sgpr85, implicit $sgpr86, implicit $sgpr87, implicit $sgpr88, implicit $sgpr89, implicit $sgpr90, implicit $sgpr91, implicit $sgpr92, implicit $sgpr93, implicit $sgpr94, implicit $sgpr95, implicit $sgpr96, implicit $sgpr97, implicit $sgpr98, implicit $sgpr99, implicit $sgpr100, implicit $sgpr101, implicit $sgpr102, implicit $sgpr103, implicit $sgpr104, implicit $sgpr105, implicit $vcc_lo, implicit $vcc_hi
@@ -74,15 +74,15 @@ body: |
; GFX950-LABEL: name: scratch_load_svs_fallback
; GFX950: liveins: $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $sgpr16, $sgpr17, $sgpr18, $sgpr19, $sgpr20, $sgpr21, $sgpr22, $sgpr23, $sgpr24, $sgpr25, $sgpr26, $sgpr27, $sgpr28, $sgpr29, $sgpr30, $sgpr31, $sgpr33, $sgpr34, $sgpr35, $sgpr36, $sgpr37, $sgpr38, $sgpr39, $sgpr40, $sgpr41, $sgpr42, $sgpr43, $sgpr44, $sgpr45, $sgpr46, $sgpr47, $sgpr48, $sgpr49, $sgpr50, $sgpr51, $sgpr52, $sgpr53, $sgpr54, $sgpr55, $sgpr56, $sgpr57, $sgpr58, $sgpr59, $sgpr60, $sgpr61, $sgpr62, $sgpr63, $sgpr64, $sgpr65, $sgpr66, $sgpr67, $sgpr68, $sgpr69, $sgpr70, $sgpr71, $sgpr72, $sgpr73, $sgpr74, $sgpr75, $sgpr76, $sgpr77, $sgpr78, $sgpr79, $sgpr80, $sgpr81, $sgpr82, $sgpr83, $sgpr84, $sgpr85, $sgpr86, $sgpr87, $sgpr88, $sgpr89, $sgpr90, $sgpr91, $sgpr92, $sgpr93, $sgpr94, $sgpr95, $sgpr96, $sgpr97, $sgpr98, $sgpr99, $sgpr100, $sgpr101, $sgpr102, $sgpr103, $sgpr104, $sgpr105, $vcc_lo, $vcc_hi
; GFX950-NEXT: {{ $}}
- ; GFX950-NEXT: $vgpr1 = V_MOV_B32_e32 16388, implicit $exec
- ; GFX950-NEXT: renamable $vgpr0 = SCRATCH_LOAD_DWORD $vgpr1, 0, 0, implicit $exec, implicit $flat_scr
+ ; GFX950-NEXT: $vgpr1 = V_MOV_B32_e32 16384, implicit $exec
+ ; GFX950-NEXT: renamable $vgpr0 = SCRATCH_LOAD_DWORD $vgpr1, 4, 0, implicit $exec, implicit $flat_scr
; GFX950-NEXT: S_ENDPGM 0, implicit $vgpr0, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr28, implicit $sgpr29, implicit $sgpr30, implicit $sgpr31, implicit $sgpr33, implicit $sgpr34, implicit $sgpr35, implicit $sgpr36, implicit $sgpr37, implicit $sgpr38, implicit $sgpr39, implicit $sgpr40, implicit $sgpr41, implicit $sgpr42, implicit $sgpr43, implicit $sgpr44, implicit $sgpr45, implicit $sgpr46, implicit $sgpr47, implicit $sgpr48, implicit $sgpr49, implicit $sgpr50, implicit $sgpr51, implicit $sgpr52, implicit $sgpr53, implicit $sgpr54, implicit $sgpr55, implicit $sgpr56, implicit $sgpr57, implicit $sgpr58, implicit $sgpr59, implicit $sgpr60, implicit $sgpr61, implicit $sgpr62, implicit $sgpr63, implicit $sgpr64, implicit $sgpr65, implicit $sgpr66, implicit $sgpr67, implicit $sgpr68, implicit $sgpr69, implicit $sgpr70, implicit $sgpr71, implicit $sgpr72, implicit $sgpr73, implicit $sgpr74, implicit $sgpr75, implicit $sgpr76, implicit $sgpr77, implicit $sgpr78, implicit $sgpr79, implicit $sgpr80, implicit $sgpr81, implicit $sgpr82, implicit $sgpr83, implicit $sgpr84, implicit $sgpr85, implicit $sgpr86, implicit $sgpr87, implicit $sgpr88, implicit $sgpr89, implicit $sgpr90, implicit $sgpr91, implicit $sgpr92, implicit $sgpr93, implicit $sgpr94, implicit $sgpr95, implicit $sgpr96, implicit $sgpr97, implicit $sgpr98, implicit $sgpr99, implicit $sgpr100, implicit $sgpr101, implicit $sgpr102, implicit $sgpr103, implicit $sgpr104, implicit $sgpr105, implicit $vcc_lo, implicit $vcc_hi
;
; GFX11-LABEL: name: scratch_load_svs_fallback
; GFX11: liveins: $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $sgpr16, $sgpr17, $sgpr18, $sgpr19, $sgpr20, $sgpr21, $sgpr22, $sgpr23, $sgpr24, $sgpr25, $sgpr26, $sgpr27, $sgpr28, $sgpr29, $sgpr30, $sgpr31, $sgpr33, $sgpr34, $sgpr35, $sgpr36, $sgpr37, $sgpr38, $sgpr39, $sgpr40, $sgpr41, $sgpr42, $sgpr43, $sgpr44, $sgpr45, $sgpr46, $sgpr47, $sgpr48, $sgpr49, $sgpr50, $sgpr51, $sgpr52, $sgpr53, $sgpr54, $sgpr55, $sgpr56, $sgpr57, $sgpr58, $sgpr59, $sgpr60, $sgpr61, $sgpr62, $sgpr63, $sgpr64, $sgpr65, $sgpr66, $sgpr67, $sgpr68, $sgpr69, $sgpr70, $sgpr71, $sgpr72, $sgpr73, $sgpr74, $sgpr75, $sgpr76, $sgpr77, $sgpr78, $sgpr79, $sgpr80, $sgpr81, $sgpr82, $sgpr83, $sgpr84, $sgpr85, $sgpr86, $sgpr87, $sgpr88, $sgpr89, $sgpr90, $sgpr91, $sgpr92, $sgpr93, $sgpr94, $sgpr95, $sgpr96, $sgpr97, $sgpr98, $sgpr99, $sgpr100, $sgpr101, $sgpr102, $sgpr103, $sgpr104, $sgpr105, $vcc_lo, $vcc_hi
; GFX11-NEXT: {{ $}}
- ; GFX11-NEXT: $vgpr1 = V_MOV_B32_e32 16388, implicit $exec
- ; GFX11-NEXT: renamable $vgpr0 = SCRATCH_LOAD_DWORD $vgpr1, 0, 0, implicit $exec, implicit $flat_scr
+ ; GFX11-NEXT: $vgpr1 = V_MOV_B32_e32 16384, implicit $exec
+ ; GFX11-NEXT: renamable $vgpr0 = SCRATCH_LOAD_DWORD $vgpr1, 4, 0, implicit $exec, implicit $flat_scr
; GFX11-NEXT: S_ENDPGM 0, implicit $vgpr0, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr28, implicit $sgpr29, implicit $sgpr30, implicit $sgpr31, implicit $sgpr33, implicit $sgpr34, implicit $sgpr35, implicit $sgpr36, implicit $sgpr37, implicit $sgpr38, implicit $sgpr39, implicit $sgpr40, implicit $sgpr41, implicit $sgpr42, implicit $sgpr43, implicit $sgpr44, implicit $sgpr45, implicit $sgpr46, implicit $sgpr47, implicit $sgpr48, implicit $sgpr49, implicit $sgpr50, implicit $sgpr51, implicit $sgpr52, implicit $sgpr53, implicit $sgpr54, implicit $sgpr55, implicit $sgpr56, implicit $sgpr57, implicit $sgpr58, implicit $sgpr59, implicit $sgpr60, implicit $sgpr61, implicit $sgpr62, implicit $sgpr63, implicit $sgpr64, implicit $sgpr65, implicit $sgpr66, implicit $sgpr67, implicit $sgpr68, implicit $sgpr69, implicit $sgpr70, implicit $sgpr71, implicit $sgpr72, implicit $sgpr73, implicit $sgpr74, implicit $sgpr75, implicit $sgpr76, implicit $sgpr77, implicit $sgpr78, implicit $sgpr79, implicit $sgpr80, implicit $sgpr81, implicit $sgpr82, implicit $sgpr83, implicit $sgpr84, implicit $sgpr85, implicit $sgpr86, implicit $sgpr87, implicit $sgpr88, implicit $sgpr89, implicit $sgpr90, implicit $sgpr91, implicit $sgpr92, implicit $sgpr93, implicit $sgpr94, implicit $sgpr95, implicit $sgpr96, implicit $sgpr97, implicit $sgpr98, implicit $sgpr99, implicit $sgpr100, implicit $sgpr101, implicit $sgpr102, implicit $sgpr103, implicit $sgpr104, implicit $sgpr105, implicit $vcc_lo, implicit $vcc_hi
renamable $vgpr0 = SCRATCH_LOAD_DWORD_SADDR %stack.1, 0, 0, implicit $exec, implicit $flat_scr :: (load (s32) from %stack.1, addrspace 5)
S_ENDPGM 0, implicit $vgpr0, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr28, implicit $sgpr29, implicit $sgpr30, implicit $sgpr31, implicit $sgpr33, implicit $sgpr34, implicit $sgpr35, implicit $sgpr36, implicit $sgpr37, implicit $sgpr38, implicit $sgpr39, implicit $sgpr40, implicit $sgpr41, implicit $sgpr42, implicit $sgpr43, implicit $sgpr44, implicit $sgpr45, implicit $sgpr46, implicit $sgpr47, implicit $sgpr48, implicit $sgpr49, implicit $sgpr50, implicit $sgpr51, implicit $sgpr52, implicit $sgpr53, implicit $sgpr54, implicit $sgpr55, implicit $sgpr56, implicit $sgpr57, implicit $sgpr58, implicit $sgpr59, implicit $sgpr60, implicit $sgpr61, implicit $sgpr62, implicit $sgpr63, implicit $sgpr64, implicit $sgpr65, implicit $sgpr66, implicit $sgpr67, implicit $sgpr68, implicit $sgpr69, implicit $sgpr70, implicit $sgpr71, implicit $sgpr72, implicit $sgpr73, implicit $sgpr74, implicit $sgpr75, implicit $sgpr76, implicit $sgpr77, implicit $sgpr78, implicit $sgpr79, implicit $sgpr80, implicit $sgpr81, implicit $sgpr82, implicit $sgpr83, implicit $sgpr84, implicit $sgpr85, implicit $sgpr86, implicit $sgpr87, implicit $sgpr88, implicit $sgpr89, implicit $sgpr90, implicit $sgpr91, implicit $sgpr92, implicit $sgpr93, implicit $sgpr94, implicit $sgpr95, implicit $sgpr96, implicit $sgpr97, implicit $sgpr98, implicit $sgpr99, implicit $sgpr100, implicit $sgpr101, implicit $sgpr102, implicit $sgpr103, implicit $sgpr104, implicit $sgpr105, implicit $vcc_lo, implicit $vcc_hi
@@ -107,8 +107,8 @@ body: |
; GFX950: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $vgpr8, $vgpr9, $vgpr10, $vgpr11, $vgpr12, $vgpr13, $vgpr14, $vgpr15, $vgpr16, $vgpr17, $vgpr18, $vgpr19, $vgpr20, $vgpr21, $vgpr22, $vgpr23, $vgpr24, $vgpr25, $vgpr26, $vgpr27, $vgpr28, $vgpr29, $vgpr30, $vgpr31, $vgpr32, $vgpr33, $vgpr34, $vgpr35, $vgpr36, $vgpr37, $vgpr38, $vgpr39, $vgpr40, $vgpr41, $vgpr42, $vgpr43, $vgpr44, $vgpr45, $vgpr46, $vgpr47, $vgpr48, $vgpr49, $vgpr50, $vgpr51, $vgpr52, $vgpr53, $vgpr54, $vgpr55, $vgpr56, $vgpr57, $vgpr58, $vgpr59, $vgpr60, $vgpr61, $vgpr62, $vgpr63, $vgpr64, $vgpr65, $vgpr66, $vgpr67, $vgpr68, $vgpr69, $vgpr70, $vgpr71, $vgpr72, $vgpr73, $vgpr74, $vgpr75, $vgpr76, $vgpr77, $vgpr78, $vgpr79, $vgpr80, $vgpr81, $vgpr82, $vgpr83, $vgpr84, $vgpr85, $vgpr86, $vgpr87, $vgpr88, $vgpr89, $vgpr90, $vgpr91, $vgpr92, $vgpr93, $vgpr94, $vgpr95, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $sgpr16, $sgpr17, $sgpr18, $sgpr19, $sgpr20, $sgpr21, $sgpr22, $sgpr23, $sgpr24, $sgpr25, $sgpr26, $sgpr27, $sgpr28, $sgpr29, $sgpr30, $sgpr31, $sgpr33, $sgpr34, $sgpr35, $sgpr36, $sgpr37, $sgpr38, $sgpr39, $sgpr40, $sgpr41, $sgpr42, $sgpr43, $sgpr44, $sgpr45, $sgpr46, $sgpr47, $sgpr48, $sgpr49, $sgpr50, $sgpr51, $sgpr52, $sgpr53, $sgpr54, $sgpr55, $sgpr56, $sgpr57, $sgpr58, $sgpr59, $sgpr60, $sgpr61, $sgpr62, $sgpr63, $sgpr64, $sgpr65, $sgpr66, $sgpr67, $sgpr68, $sgpr69, $sgpr70, $sgpr71, $sgpr72, $sgpr73, $sgpr74, $sgpr75, $sgpr76, $sgpr77, $sgpr78, $sgpr79, $sgpr80, $sgpr81, $sgpr82, $sgpr83, $sgpr84, $sgpr85, $sgpr86, $sgpr87, $sgpr88, $sgpr89, $sgpr90, $sgpr91, $sgpr92, $sgpr93, $sgpr94, $sgpr95, $sgpr96, $sgpr97, $sgpr98, $sgpr99, $sgpr100, $sgpr101, $sgpr102, $sgpr103, $sgpr104, $sgpr105, $vcc_lo, $vcc_hi
; GFX950-NEXT: {{ $}}
; GFX950-NEXT: SCRATCH_STORE_DWORD_ST killed $vgpr1, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.2, addrspace 5)
- ; GFX950-NEXT: $vgpr1 = V_MOV_B32_e32 16388, implicit $exec
- ; GFX950-NEXT: SCRATCH_STORE_DWORD $vgpr0, $vgpr1, 0, 0, implicit $exec, implicit $flat_scr
+ ; GFX950-NEXT: $vgpr1 = V_MOV_B32_e32 16384, implicit $exec
+ ; GFX950-NEXT: SCRATCH_STORE_DWORD $vgpr0, $vgpr1, 4, 0, implicit $exec, implicit $flat_scr
; GFX950-NEXT: $vgpr1 = SCRATCH_LOAD_DWORD_ST 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.2, addrspace 5)
; GFX950-NEXT: S_ENDPGM 0, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $vgpr31, implicit $vgpr32, implicit $vgpr33, implicit $vgpr34, implicit $vgpr35, implicit $vgpr36, implicit $vgpr37, implicit $vgpr38, implicit $vgpr39, implicit $vgpr40, implicit $vgpr41, implicit $vgpr42, implicit $vgpr43, implicit $vgpr44, implicit $vgpr45, implicit $vgpr46, implicit $vgpr47, implicit $vgpr48, implicit $vgpr49, implicit $vgpr50, implicit $vgpr51, implicit $vgpr52, implicit $vgpr53, implicit $vgpr54, implicit $vgpr55, implicit $vgpr56, implicit $vgpr57, implicit $vgpr58, implicit $vgpr59, implicit $vgpr60, implicit $vgpr61, implicit $vgpr62, implicit $vgpr63, implicit $vgpr64, implicit $vgpr65, implicit $vgpr66, implicit $vgpr67, implicit $vgpr68, implicit $vgpr69, implicit $vgpr70, implicit $vgpr71, implicit $vgpr72, implicit $vgpr73, implicit $vgpr74, implicit $vgpr75, implicit $vgpr76, implicit $vgpr77, implicit $vgpr78, implicit $vgpr79, implicit $vgpr80, implicit $vgpr81, implicit $vgpr82, implicit $vgpr83, implicit $vgpr84, implicit $vgpr85, implicit $vgpr86, implicit $vgpr87, implicit $vgpr88, implicit $vgpr89, implicit $vgpr90, implicit $vgpr91, implicit $vgpr92, implicit $vgpr93, implicit $vgpr94, implicit $vgpr95, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr28, implicit $sgpr29, implicit $sgpr30, implicit $sgpr31, implicit $sgpr33, implicit $sgpr34, implicit $sgpr35, implicit $sgpr36, implicit $sgpr37, implicit $sgpr38, implicit $sgpr39, implicit $sgpr40, implicit $sgpr41, implicit $sgpr42, implicit $sgpr43, implicit $sgpr44, implicit $sgpr45, implicit $sgpr46, implicit $sgpr47, implicit $sgpr48, implicit $sgpr49, implicit $sgpr50, implicit $sgpr51, implicit $sgpr52, implicit $sgpr53, implicit $sgpr54, implicit $sgpr55, implicit $sgpr56, implicit $sgpr57, implicit $sgpr58, implicit $sgpr59, implicit $sgpr60, implicit $sgpr61, implicit $sgpr62, implicit $sgpr63, implicit $sgpr64, implicit $sgpr65, implicit $sgpr66, implicit $sgpr67, implicit $sgpr68, implicit $sgpr69, implicit $sgpr70, implicit $sgpr71, implicit $sgpr72, implicit $sgpr73, implicit $sgpr74, implicit $sgpr75, implicit $sgpr76, implicit $sgpr77, implicit $sgpr78, implicit $sgpr79, implicit $sgpr80, implicit $sgpr81, implicit $sgpr82, implicit $sgpr83, implicit $sgpr84, implicit $sgpr85, implicit $sgpr86, implicit $sgpr87, implicit $sgpr88, implicit $sgpr89, implicit $sgpr90, implicit $sgpr91, implicit $sgpr92, implicit $sgpr93, implicit $sgpr94, implicit $sgpr95, implicit $sgpr96, implicit $sgpr97, implicit $sgpr98, implicit $sgpr99, implicit $sgpr100, implicit $sgpr101, implicit $sgpr102, implicit $sgpr103, implicit $sgpr104, implicit $sgpr105, implicit $vcc_lo, implicit $vcc_hi
;
@@ -116,8 +116,8 @@ body: |
; GFX11: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $vgpr8, $vgpr9, $vgpr10, $vgpr11, $vgpr12, $vgpr13, $vgpr14, $vgpr15, $vgpr16, $vgpr17, $vgpr18, $vgpr19, $vgpr20, $vgpr21, $vgpr22, $vgpr23, $vgpr24, $vgpr25, $vgpr26, $vgpr27, $vgpr28, $vgpr29, $vgpr30, $vgpr31, $vgpr32, $vgpr33, $vgpr34, $vgpr35, $vgpr36, $vgpr37, $vgpr38, $vgpr39, $vgpr40, $vgpr41, $vgpr42, $vgpr43, $vgpr44, $vgpr45, $vgpr46, $vgpr47, $vgpr48, $vgpr49, $vgpr50, $vgpr51, $vgpr52, $vgpr53, $vgpr54, $vgpr55, $vgpr56, $vgpr57, $vgpr58, $vgpr59, $vgpr60, $vgpr61, $vgpr62, $vgpr63, $vgpr64, $vgpr65, $vgpr66, $vgpr67, $vgpr68, $vgpr69, $vgpr70, $vgpr71, $vgpr72, $vgpr73, $vgpr74, $vgpr75, $vgpr76, $vgpr77, $vgpr78, $vgpr79, $vgpr80, $vgpr81, $vgpr82, $vgpr83, $vgpr84, $vgpr85, $vgpr86, $vgpr87, $vgpr88, $vgpr89, $vgpr90, $vgpr91, $vgpr92, $vgpr93, $vgpr94, $vgpr95, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $sgpr16, $sgpr17, $sgpr18, $sgpr19, $sgpr20, $sgpr21, $sgpr22, $sgpr23, $sgpr24, $sgpr25, $sgpr26, $sgpr27, $sgpr28, $sgpr29, $sgpr30, $sgpr31, $sgpr33, $sgpr34, $sgpr35, $sgpr36, $sgpr37, $sgpr38, $sgpr39, $sgpr40, $sgpr41, $sgpr42, $sgpr43, $sgpr44, $sgpr45, $sgpr46, $sgpr47, $sgpr48, $sgpr49, $sgpr50, $sgpr51, $sgpr52, $sgpr53, $sgpr54, $sgpr55, $sgpr56, $sgpr57, $sgpr58, $sgpr59, $sgpr60, $sgpr61, $sgpr62, $sgpr63, $sgpr64, $sgpr65, $sgpr66, $sgpr67, $sgpr68, $sgpr69, $sgpr70, $sgpr71, $sgpr72, $sgpr73, $sgpr74, $sgpr75, $sgpr76, $sgpr77, $sgpr78, $sgpr79, $sgpr80, $sgpr81, $sgpr82, $sgpr83, $sgpr84, $sgpr85, $sgpr86, $sgpr87, $sgpr88, $sgpr89, $sgpr90, $sgpr91, $sgpr92, $sgpr93, $sgpr94, $sgpr95, $sgpr96, $sgpr97, $sgpr98, $sgpr99, $sgpr100, $sgpr101, $sgpr102, $sgpr103, $sgpr104, $sgpr105, $vcc_lo, $vcc_hi
; GFX11-NEXT: {{ $}}
; GFX11-NEXT: SCRATCH_STORE_DWORD_ST killed $vgpr1, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.2, addrspace 5)
- ; GFX11-NEXT: $vgpr1 = V_MOV_B32_e32 16388, implicit $exec
- ; GFX11-NEXT: SCRATCH_STORE_DWORD $vgpr0, $vgpr1, 0, 0, implicit $exec, implicit $flat_scr
+ ; GFX11-NEXT: $vgpr1 = V_MOV_B32_e32 16384, implicit $exec
+ ; GFX11-NEXT: SCRATCH_STORE_DWORD $vgpr0, $vgpr1, 4, 0, implicit $exec, implicit $flat_scr
; GFX11-NEXT: $vgpr1 = SCRATCH_LOAD_DWORD_ST 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.2, addrspace 5)
; GFX11-NEXT: S_ENDPGM 0, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $vgpr31, implicit $vgpr32, implicit $vgpr33, implicit $vgpr34, implicit $vgpr35, implicit $vgpr36, implicit $vgpr37, implicit $vgpr38, implicit $vgpr39, implicit $vgpr40, implicit $vgpr41, implicit $vgpr42, implicit $vgpr43, implicit $vgpr44, implicit $vgpr45, implicit $vgpr46, implicit $vgpr47, implicit $vgpr48, implicit $vgpr49, implicit $vgpr50, implicit $vgpr51, implicit $vgpr52, implicit $vgpr53, implicit $vgpr54, implicit $vgpr55, implicit $vgpr56, implicit $vgpr57, implicit $vgpr58, implicit $vgpr59, implicit $vgpr60, implicit $vgpr61, implicit $vgpr62, implicit $vgpr63, implicit $vgpr64, implicit $vgpr65, implicit $vgpr66, implicit $vgpr67, implicit $vgpr68, implicit $vgpr69, implicit $vgpr70, implicit $vgpr71, implicit $vgpr72, implicit $vgpr73, implicit $vgpr74, implicit $vgpr75, implicit $vgpr76, implicit $vgpr77, implicit $vgpr78, implicit $vgpr79, implicit $vgpr80, implicit $vgpr81, implicit $vgpr82, implicit $vgpr83, implicit $vgpr84, implicit $vgpr85, implicit $vgpr86, implicit $vgpr87, implicit $vgpr88, implicit $vgpr89, implicit $vgpr90, implicit $vgpr91, implicit $vgpr92, implicit $vgpr93, implicit $vgpr94, implicit $vgpr95, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr28, implicit $sgpr29, implicit $sgpr30, implicit $sgpr31, implicit $sgpr33, implicit $sgpr34, implicit $sgpr35, implicit $sgpr36, implicit $sgpr37, implicit $sgpr38, implicit $sgpr39, implicit $sgpr40, implicit $sgpr41, implicit $sgpr42, implicit $sgpr43, implicit $sgpr44, implicit $sgpr45, implicit $sgpr46, implicit $sgpr47, implicit $sgpr48, implicit $sgpr49, implicit $sgpr50, implicit $sgpr51, implicit $sgpr52, implicit $sgpr53, implicit $sgpr54, implicit $sgpr55, implicit $sgpr56, implicit $sgpr57, implicit $sgpr58, implicit $sgpr59, implicit $sgpr60, implicit $sgpr61, implicit $sgpr62, implicit $sgpr63, implicit $sgpr64, implicit $sgpr65, implicit $sgpr66, implicit $sgpr67, implicit $sgpr68, implicit $sgpr69, implicit $sgpr70, implicit $sgpr71, implicit $sgpr72, implicit $sgpr73, implicit $sgpr74, implicit $sgpr75, implicit $sgpr76, implicit $sgpr77, implicit $sgpr78, implicit $sgpr79, implicit $sgpr80, implicit $sgpr81, implicit $sgpr82, implicit $sgpr83, implicit $sgpr84, implicit $sgpr85, implicit $sgpr86, implicit $sgpr87, implicit $sgpr88, implicit $sgpr89, implicit $sgpr90, implicit $sgpr91, implicit $sgpr92, implicit $sgpr93, implicit $sgpr94, implicit $sgpr95, implicit $sgpr96, implicit $sgpr97, implicit $sgpr98, implicit $sgpr99, implicit $sgpr100, implicit $sgpr101, implicit $sgpr102, implicit $sgpr103, implicit $sgpr104, implicit $sgpr105, implicit $vcc_lo, implicit $vcc_hi
SCRATCH_STORE_DWORD_SADDR $vgpr0, %stack.1, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32) into %stack.1, addrspace 5)
@@ -143,8 +143,8 @@ body: |
; GFX950: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $vgpr8, $vgpr9, $vgpr10, $vgpr11, $vgpr12, $vgpr13, $vgpr14, $vgpr15, $vgpr16, $vgpr17, $vgpr18, $vgpr19, $vgpr20, $vgpr21, $vgpr22, $vgpr23, $vgpr24, $vgpr25, $vgpr26, $vgpr27, $vgpr28, $vgpr29, $vgpr30, $vgpr31, $vgpr32, $vgpr33, $vgpr34, $vgpr35, $vgpr36, $vgpr37, $vgpr38, $vgpr39, $vgpr40, $vgpr41, $vgpr42, $vgpr43, $vgpr44, $vgpr45, $vgpr46, $vgpr47, $vgpr48, $vgpr49, $vgpr50, $vgpr51, $vgpr52, $vgpr53, $vgpr54, $vgpr55, $vgpr56, $vgpr57, $vgpr58, $vgpr59, $vgpr60, $vgpr61, $vgpr62, $vgpr63, $vgpr64, $vgpr65, $vgpr66, $vgpr67, $vgpr68, $vgpr69, $vgpr70, $vgpr71, $vgpr72, $vgpr73, $vgpr74, $vgpr75, $vgpr76, $vgpr77, $vgpr78, $vgpr79, $vgpr80, $vgpr81, $vgpr82, $vgpr83, $vgpr84, $vgpr85, $vgpr86, $vgpr87, $vgpr88, $vgpr89, $vgpr90, $vgpr91, $vgpr92, $vgpr93, $vgpr94, $vgpr95, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $sgpr16, $sgpr17, $sgpr18, $sgpr19, $sgpr20, $sgpr21, $sgpr22, $sgpr23, $sgpr24, $sgpr25, $sgpr26, $sgpr27, $sgpr28, $sgpr29, $sgpr30, $sgpr31, $sgpr33, $sgpr34, $sgpr35, $sgpr36, $sgpr37, $sgpr38, $sgpr39, $sgpr40, $sgpr41, $sgpr42, $sgpr43, $sgpr44, $sgpr45, $sgpr46, $sgpr47, $sgpr48, $sgpr49, $sgpr50, $sgpr51, $sgpr52, $sgpr53, $sgpr54, $sgpr55, $sgpr56, $sgpr57, $sgpr58, $sgpr59, $sgpr60, $sgpr61, $sgpr62, $sgpr63, $sgpr64, $sgpr65, $sgpr66, $sgpr67, $sgpr68, $sgpr69, $sgpr70, $sgpr71, $sgpr72, $sgpr73, $sgpr74, $sgpr75, $sgpr76, $sgpr77, $sgpr78, $sgpr79, $sgpr80, $sgpr81, $sgpr82, $sgpr83, $sgpr84, $sgpr85, $sgpr86, $sgpr87, $sgpr88, $sgpr89, $sgpr90, $sgpr91, $sgpr92, $sgpr93, $sgpr94, $sgpr95, $sgpr96, $sgpr97, $sgpr98, $sgpr99, $sgpr100, $sgpr101, $sgpr102, $sgpr103, $sgpr104, $sgpr105, $vcc_lo, $vcc_hi
; GFX950-NEXT: {{ $}}
; GFX950-NEXT: SCRATCH_STORE_DWORD_ST killed $vgpr1, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.2, addrspace 5)
- ; GFX950-NEXT: $vgpr1 = V_MOV_B32_e32 16388, implicit $exec
- ; GFX950-NEXT: renamable $vgpr0 = SCRATCH_LOAD_DWORD $vgpr1, 0, 0, implicit $exec, implicit $flat_scr
+ ; GFX950-NEXT: $vgpr1 = V_MOV_B32_e32 16384, implicit $exec
+ ; GFX950-NEXT: renamable $vgpr0 = SCRATCH_LOAD_DWORD $vgpr1, 4, 0, implicit $exec, implicit $flat_scr
; GFX950-NEXT: $vgpr1 = SCRATCH_LOAD_DWORD_ST 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.2, addrspace 5)
; GFX950-NEXT: S_ENDPGM 0, implicit $vgpr0, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $vgpr31, implicit $vgpr32, implicit $vgpr33, implicit $vgpr34, implicit $vgpr35, implicit $vgpr36, implicit $vgpr37, implicit $vgpr38, implicit $vgpr39, implicit $vgpr40, implicit $vgpr41, implicit $vgpr42, implicit $vgpr43, implicit $vgpr44, implicit $vgpr45, implicit $vgpr46, implicit $vgpr47, implicit $vgpr48, implicit $vgpr49, implicit $vgpr50, implicit $vgpr51, implicit $vgpr52, implicit $vgpr53, implicit $vgpr54, implicit $vgpr55, implicit $vgpr56, implicit $vgpr57, implicit $vgpr58, implicit $vgpr59, implicit $vgpr60, implicit $vgpr61, implicit $vgpr62, implicit $vgpr63, implicit $vgpr64, implicit $vgpr65, implicit $vgpr66, implicit $vgpr67, implicit $vgpr68, implicit $vgpr69, implicit $vgpr70, implicit $vgpr71, implicit $vgpr72, implicit $vgpr73, implicit $vgpr74, implicit $vgpr75, implicit $vgpr76, implicit $vgpr77, implicit $vgpr78, implicit $vgpr79, implicit $vgpr80, implicit $vgpr81, implicit $vgpr82, implicit $vgpr83, implicit $vgpr84, implicit $vgpr85, implicit $vgpr86, implicit $vgpr87, implicit $vgpr88, implicit $vgpr89, implicit $vgpr90, implicit $vgpr91, implicit $vgpr92, implicit $vgpr93, implicit $vgpr94, implicit $vgpr95, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr28, implicit $sgpr29, implicit $sgpr30, implicit $sgpr31, implicit $sgpr33, implicit $sgpr34, implicit $sgpr35, implicit $sgpr36, implicit $sgpr37, implicit $sgpr38, implicit $sgpr39, implicit $sgpr40, implicit $sgpr41, implicit $sgpr42, implicit $sgpr43, implicit $sgpr44, implicit $sgpr45, implicit $sgpr46, implicit $sgpr47, implicit $sgpr48, implicit $sgpr49, implicit $sgpr50, implicit $sgpr51, implicit $sgpr52, implicit $sgpr53, implicit $sgpr54, implicit $sgpr55, implicit $sgpr56, implicit $sgpr57, implicit $sgpr58, implicit $sgpr59, implicit $sgpr60, implicit $sgpr61, implicit $sgpr62, implicit $sgpr63, implicit $sgpr64, implicit $sgpr65, implicit $sgpr66, implicit $sgpr67, implicit $sgpr68, implicit $sgpr69, implicit $sgpr70, implicit $sgpr71, implicit $sgpr72, implicit $sgpr73, implicit $sgpr74, implicit $sgpr75, implicit $sgpr76, implicit $sgpr77, implicit $sgpr78, implicit $sgpr79, implicit $sgpr80, implicit $sgpr81, implicit $sgpr82, implicit $sgpr83, implicit $sgpr84, implicit $sgpr85, implicit $sgpr86, implicit $sgpr87, implicit $sgpr88, implicit $sgpr89, implicit $sgpr90, implicit $sgpr91, implicit $sgpr92, implicit $sgpr93, implicit $sgpr94, implicit $sgpr95, implicit $sgpr96, implicit $sgpr97, implicit $sgpr98, implicit $sgpr99, implicit $sgpr100, implicit $sgpr101, implicit $sgpr102, implicit $sgpr103, implicit $sgpr104, implicit $sgpr105, implicit $vcc_lo, implicit $vcc_hi
;
@@ -152,8 +152,8 @@ body: |
; GFX11: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $vgpr8, $vgpr9, $vgpr10, $vgpr11, $vgpr12, $vgpr13, $vgpr14, $vgpr15, $vgpr16, $vgpr17, $vgpr18, $vgpr19, $vgpr20, $vgpr21, $vgpr22, $vgpr23, $vgpr24, $vgpr25, $vgpr26, $vgpr27, $vgpr28, $vgpr29, $vgpr30, $vgpr31, $vgpr32, $vgpr33, $vgpr34, $vgpr35, $vgpr36, $vgpr37, $vgpr38, $vgpr39, $vgpr40, $vgpr41, $vgpr42, $vgpr43, $vgpr44, $vgpr45, $vgpr46, $vgpr47, $vgpr48, $vgpr49, $vgpr50, $vgpr51, $vgpr52, $vgpr53, $vgpr54, $vgpr55, $vgpr56, $vgpr57, $vgpr58, $vgpr59, $vgpr60, $vgpr61, $vgpr62, $vgpr63, $vgpr64, $vgpr65, $vgpr66, $vgpr67, $vgpr68, $vgpr69, $vgpr70, $vgpr71, $vgpr72, $vgpr73, $vgpr74, $vgpr75, $vgpr76, $vgpr77, $vgpr78, $vgpr79, $vgpr80, $vgpr81, $vgpr82, $vgpr83, $vgpr84, $vgpr85, $vgpr86, $vgpr87, $vgpr88, $vgpr89, $vgpr90, $vgpr91, $vgpr92, $vgpr93, $vgpr94, $vgpr95, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $sgpr8, $sgpr9, $sgpr10, $sgpr11, $sgpr12, $sgpr13, $sgpr14, $sgpr15, $sgpr16, $sgpr17, $sgpr18, $sgpr19, $sgpr20, $sgpr21, $sgpr22, $sgpr23, $sgpr24, $sgpr25, $sgpr26, $sgpr27, $sgpr28, $sgpr29, $sgpr30, $sgpr31, $sgpr33, $sgpr34, $sgpr35, $sgpr36, $sgpr37, $sgpr38, $sgpr39, $sgpr40, $sgpr41, $sgpr42, $sgpr43, $sgpr44, $sgpr45, $sgpr46, $sgpr47, $sgpr48, $sgpr49, $sgpr50, $sgpr51, $sgpr52, $sgpr53, $sgpr54, $sgpr55, $sgpr56, $sgpr57, $sgpr58, $sgpr59, $sgpr60, $sgpr61, $sgpr62, $sgpr63, $sgpr64, $sgpr65, $sgpr66, $sgpr67, $sgpr68, $sgpr69, $sgpr70, $sgpr71, $sgpr72, $sgpr73, $sgpr74, $sgpr75, $sgpr76, $sgpr77, $sgpr78, $sgpr79, $sgpr80, $sgpr81, $sgpr82, $sgpr83, $sgpr84, $sgpr85, $sgpr86, $sgpr87, $sgpr88, $sgpr89, $sgpr90, $sgpr91, $sgpr92, $sgpr93, $sgpr94, $sgpr95, $sgpr96, $sgpr97, $sgpr98, $sgpr99, $sgpr100, $sgpr101, $sgpr102, $sgpr103, $sgpr104, $sgpr105, $vcc_lo, $vcc_hi
; GFX11-NEXT: {{ $}}
; GFX11-NEXT: SCRATCH_STORE_DWORD_ST killed $vgpr1, 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" store (s32) into %stack.2, addrspace 5)
- ; GFX11-NEXT: $vgpr1 = V_MOV_B32_e32 16388, implicit $exec
- ; GFX11-NEXT: renamable $vgpr0 = SCRATCH_LOAD_DWORD $vgpr1, 0, 0, implicit $exec, implicit $flat_scr
+ ; GFX11-NEXT: $vgpr1 = V_MOV_B32_e32 16384, implicit $exec
+ ; GFX11-NEXT: renamable $vgpr0 = SCRATCH_LOAD_DWORD $vgpr1, 4, 0, implicit $exec, implicit $flat_scr
; GFX11-NEXT: $vgpr1 = SCRATCH_LOAD_DWORD_ST 0, 0, implicit $exec, implicit $flat_scr :: ("amdgpu-thread-private" load (s32) from %stack.2, addrspace 5)
; GFX11-NEXT: S_ENDPGM 0, implicit $vgpr0, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $vgpr31, implicit $vgpr32, implicit $vgpr33, implicit $vgpr34, implicit $vgpr35, implicit $vgpr36, implicit $vgpr37, implicit $vgpr38, implicit $vgpr39, implicit $vgpr40, implicit $vgpr41, implicit $vgpr42, implicit $vgpr43, implicit $vgpr44, implicit $vgpr45, implicit $vgpr46, implicit $vgpr47, implicit $vgpr48, implicit $vgpr49, implicit $vgpr50, implicit $vgpr51, implicit $vgpr52, implicit $vgpr53, implicit $vgpr54, implicit $vgpr55, implicit $vgpr56, implicit $vgpr57, implicit $vgpr58, implicit $vgpr59, implicit $vgpr60, implicit $vgpr61, implicit $vgpr62, implicit $vgpr63, implicit $vgpr64, implicit $vgpr65, implicit $vgpr66, implicit $vgpr67, implicit $vgpr68, implicit $vgpr69, implicit $vgpr70, implicit $vgpr71, implicit $vgpr72, implicit $vgpr73, implicit $vgpr74, implicit $vgpr75, implicit $vgpr76, implicit $vgpr77, implicit $vgpr78, implicit $vgpr79, implicit $vgpr80, implicit $vgpr81, implicit $vgpr82, implicit $vgpr83, implicit $vgpr84, implicit $vgpr85, implicit $vgpr86, implicit $vgpr87, implicit $vgpr88, implicit $vgpr89, implicit $vgpr90, implicit $vgpr91, implicit $vgpr92, implicit $vgpr93, implicit $vgpr94, implicit $vgpr95, implicit $sgpr4, implicit $sgpr5, implicit $sgpr6, implicit $sgpr7, implicit $sgpr8, implicit $sgpr9, implicit $sgpr10, implicit $sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $sgpr16, implicit $sgpr17, implicit $sgpr18, implicit $sgpr19, implicit $sgpr20, implicit $sgpr21, implicit $sgpr22, implicit $sgpr23, implicit $sgpr24, implicit $sgpr25, implicit $sgpr26, implicit $sgpr27, implicit $sgpr28, implicit $sgpr29, implicit $sgpr30, implicit $sgpr31, implicit $sgpr33, implicit $sgpr34, implicit $sgpr35, implicit $sgpr36, implicit $sgpr37, implicit $sgpr38, implicit $sgpr39, implicit $sgpr40, implicit $sgpr41, implicit $sgpr42, implicit $sgpr43, implicit $sgpr44, implicit $sgpr45, implicit $sgpr46, implicit $sgpr47, implicit $sgpr48, implicit $sgpr49, implicit $sgpr50, implicit $sgpr51, implicit $sgpr52, implicit $sgpr53, implicit $sgpr54, implicit $sgpr55, implicit $sgpr56, implicit $sgpr57, implicit $sgpr58, implicit $sgpr59, implicit $sgpr60, implicit $sgpr61, implicit $sgpr62, implicit $sgpr63, implicit $sgpr64, implicit $sgpr65, implicit $sgpr66, implicit $sgpr67, implicit $sgpr68, implicit $sgpr69, implicit $sgpr70, implicit $sgpr71, implicit $sgpr72, implicit $sgpr73, implicit $sgpr74, implicit $sgpr75, implicit $sgpr76, implicit $sgpr77, implicit $sgpr78, implicit $sgpr79, implicit $sgpr80, implicit $sgpr81, implicit $sgpr82, implicit $sgpr83, implicit $sgpr84, implicit $sgpr85, implicit $sgpr86, implicit $sgpr87, implicit $sgpr88, implicit $sgpr89, implicit $sgpr90, implicit $sgpr91, implicit $sgpr92, implicit $sgpr93, implicit $sgpr94, implicit $sgpr95, implicit $sgpr96, implicit $sgpr97, implicit $sgpr98, implicit $sgpr99, implicit $sgpr100, implicit $sgpr101, implicit $sgpr102, implicit $sgpr103, implicit $sgpr104, implicit $sgpr105, implicit $vcc_lo, implicit $vcc_hi
renamable $vgpr0 = SCRATCH_LOAD_DWORD_SADDR %stack.1, 0, 0, implicit $exec, implicit $flat_scr :: (load (s32) from %stack.1, addrspace 5)
More information about the llvm-commits
mailing list