[llvm] [AMDGPU] Skip non-wwm reg implicit-def from bb prolog (PR #115834)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Nov 12 04:02:54 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Christudasan Devadasan (cdevadas)
<details>
<summary>Changes</summary>
Currently all implicit-def instructions are part of
bb prolog. We should only include the wwm-register's
implicit definitions into the BB prolog. The other
vector class registers' implicit defs when exist at
the bb top might cause interference when pushed the
LR_split copy insertion downwards. The SplitKit is
very strict on altering the insertion points and will
assert such instances.
---
Patch is 37.39 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/115834.diff
10 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/SIInstrInfo.cpp (+5-2)
- (modified) llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h (+4)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/divergence-divergent-i1-used-outside-loop.mir (+3-3)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/image-waterfall-loop-O0.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/collapse-endcf.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/indirect-addressing-si.ll (+9-9)
- (modified) llvm/test/CodeGen/AMDGPU/infloop-subrange-spill-inspect-subrange.mir (+14-13)
- (modified) llvm/test/CodeGen/AMDGPU/infloop-subrange-spill.mir (+14-12)
- (modified) llvm/test/CodeGen/AMDGPU/kernel-vgpr-spill-mubuf-with-voffset.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/merge-m0.mir (+23-23)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
index ad45af00f2bd75..c864f03f1f0f9e 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -8909,16 +8909,19 @@ bool SIInstrInfo::isBasicBlockPrologue(const MachineInstr &MI,
// needed by the prolog. However, the insertions for scalar registers can
// always be placed at the BB top as they are independent of the exec mask
// value.
+ const MachineFunction *MF = MI.getParent()->getParent();
bool IsNullOrVectorRegister = true;
if (Reg) {
- const MachineRegisterInfo &MRI = MI.getParent()->getParent()->getRegInfo();
+ const MachineRegisterInfo &MRI = MF->getRegInfo();
IsNullOrVectorRegister = !RI.isSGPRClass(RI.getRegClassForReg(MRI, Reg));
}
uint16_t Opcode = MI.getOpcode();
+ const SIMachineFunctionInfo *MFI = MF->getInfo<SIMachineFunctionInfo>();
return IsNullOrVectorRegister &&
(isSGPRSpill(Opcode) || isWWMRegSpillOpcode(Opcode) ||
- Opcode == AMDGPU::IMPLICIT_DEF ||
+ (Opcode == AMDGPU::IMPLICIT_DEF &&
+ MFI->isWWMReg(MI.getOperand(0).getReg())) ||
(!MI.isTerminator() && Opcode != AMDGPU::COPY &&
MI.modifiesRegister(AMDGPU::EXEC, &RI)));
}
diff --git a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h
index 018322eaa18665..2a754680fdc8ca 100644
--- a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h
+++ b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.h
@@ -596,6 +596,10 @@ class SIMachineFunctionInfo final : public AMDGPUMachineFunction,
SMDiagnostic &Error, SMRange &SourceRange);
void reserveWWMRegister(Register Reg) { WWMReservedRegs.insert(Reg); }
+ bool isWWMReg(Register Reg) const {
+ return Reg.isVirtual() ? checkFlag(Reg, AMDGPU::VirtRegFlag::WWM_REG)
+ : WWMReservedRegs.contains(Reg);
+ }
void updateNonWWMRegMask(BitVector &RegMask) { NonWWMRegMask = RegMask; }
BitVector getNonWWMRegMask() const { return NonWWMRegMask; }
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/divergence-divergent-i1-used-outside-loop.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/divergence-divergent-i1-used-outside-loop.mir
index 46573113027964..5bbe3e48868998 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/divergence-divergent-i1-used-outside-loop.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/divergence-divergent-i1-used-outside-loop.mir
@@ -19,8 +19,8 @@ body: |
; GFX10-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
; GFX10-NEXT: [[C1:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
; GFX10-NEXT: [[FCMP:%[0-9]+]]:_(s1) = G_FCMP floatpred(ogt), [[COPY1]](s32), [[C1]]
- ; GFX10-NEXT: [[DEF:%[0-9]+]]:sreg_32(s1) = IMPLICIT_DEF
; GFX10-NEXT: [[COPY4:%[0-9]+]]:sreg_32(s1) = COPY [[FCMP]](s1)
+ ; GFX10-NEXT: [[DEF:%[0-9]+]]:sreg_32(s1) = IMPLICIT_DEF
; GFX10-NEXT: [[COPY5:%[0-9]+]]:sreg_32(s1) = COPY [[DEF]](s1)
; GFX10-NEXT: [[S_ANDN2_B32_:%[0-9]+]]:sreg_32(s1) = S_ANDN2_B32 [[COPY5]](s1), $exec_lo, implicit-def $scc
; GFX10-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32(s1) = S_AND_B32 $exec_lo, [[COPY4]](s1), implicit-def $scc
@@ -122,8 +122,8 @@ body: |
; GFX10-NEXT: [[MV1:%[0-9]+]]:_(p0) = G_MERGE_VALUES [[COPY2]](s32), [[COPY3]](s32)
; GFX10-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 -1
; GFX10-NEXT: [[C1:%[0-9]+]]:_(s1) = G_CONSTANT i1 true
- ; GFX10-NEXT: [[DEF:%[0-9]+]]:sreg_32_xm0_xexec(s1) = IMPLICIT_DEF
; GFX10-NEXT: [[COPY4:%[0-9]+]]:sreg_32_xm0_xexec(s1) = COPY [[C1]](s1)
+ ; GFX10-NEXT: [[DEF:%[0-9]+]]:sreg_32_xm0_xexec(s1) = IMPLICIT_DEF
; GFX10-NEXT: [[COPY5:%[0-9]+]]:sreg_32_xm0_xexec(s1) = COPY [[DEF]](s1)
; GFX10-NEXT: [[S_ANDN2_B32_:%[0-9]+]]:sreg_32_xm0_xexec(s1) = S_ANDN2_B32 [[COPY5]](s1), $exec_lo, implicit-def $scc
; GFX10-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32_xm0_xexec(s1) = S_AND_B32 $exec_lo, [[COPY4]](s1), implicit-def $scc
@@ -790,8 +790,8 @@ body: |
; GFX10-NEXT: [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[PTR_ADD]](p1) :: (load (s32), addrspace 1)
; GFX10-NEXT: [[C3:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
; GFX10-NEXT: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[LOAD]](s32), [[C3]]
- ; GFX10-NEXT: [[DEF2:%[0-9]+]]:sreg_32_xm0_xexec(s1) = IMPLICIT_DEF
; GFX10-NEXT: [[COPY11:%[0-9]+]]:sreg_32(s1) = COPY [[ICMP]](s1)
+ ; GFX10-NEXT: [[DEF2:%[0-9]+]]:sreg_32_xm0_xexec(s1) = IMPLICIT_DEF
; GFX10-NEXT: [[S_ANDN2_B32_1:%[0-9]+]]:sreg_32(s1) = S_ANDN2_B32 [[COPY10]](s1), $exec_lo, implicit-def $scc
; GFX10-NEXT: [[S_AND_B32_1:%[0-9]+]]:sreg_32(s1) = S_AND_B32 $exec_lo, [[COPY11]](s1), implicit-def $scc
; GFX10-NEXT: [[S_OR_B32_1:%[0-9]+]]:sreg_32(s1) = S_OR_B32 [[S_ANDN2_B32_1]](s1), [[S_AND_B32_1]](s1), implicit-def $scc
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/image-waterfall-loop-O0.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/image-waterfall-loop-O0.ll
index 88fd7dcce35f68..c9426106af5dad 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/image-waterfall-loop-O0.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/image-waterfall-loop-O0.ll
@@ -170,8 +170,8 @@ define <4 x float> @waterfall_loop(<8 x i32> %vgpr_srd) {
; CHECK-NEXT: v_readlane_b32 s4, v16, 4
; CHECK-NEXT: s_mov_b32 exec_lo, s4
; CHECK-NEXT: ; %bb.4:
-; CHECK-NEXT: ; implicit-def: $sgpr4
; CHECK-NEXT: buffer_load_dword v0, off, s[0:3], s32 offset:76 ; 4-byte Folded Reload
+; CHECK-NEXT: ; implicit-def: $sgpr4
; CHECK-NEXT: v_mov_b32_e32 v1, s4
; CHECK-NEXT: v_mov_b32_e32 v2, s4
; CHECK-NEXT: v_mov_b32_e32 v3, s4
diff --git a/llvm/test/CodeGen/AMDGPU/collapse-endcf.ll b/llvm/test/CodeGen/AMDGPU/collapse-endcf.ll
index b3b26df49910a9..50c9c0cb64ccd6 100644
--- a/llvm/test/CodeGen/AMDGPU/collapse-endcf.ll
+++ b/llvm/test/CodeGen/AMDGPU/collapse-endcf.ll
@@ -1135,11 +1135,11 @@ define void @scc_liveness(i32 %arg) local_unnamed_addr #0 {
; GCN-O0-NEXT: s_cbranch_execz .LBB5_5
; GCN-O0-NEXT: ; %bb.3: ; %bb4
; GCN-O0-NEXT: ; in Loop: Header=BB5_1 Depth=1
-; GCN-O0-NEXT: ; implicit-def: $sgpr4
; GCN-O0-NEXT: s_or_saveexec_b64 s[14:15], -1
; GCN-O0-NEXT: s_waitcnt expcnt(0)
; GCN-O0-NEXT: buffer_load_dword v6, off, s[0:3], s32 ; 4-byte Folded Reload
; GCN-O0-NEXT: s_mov_b64 exec, s[14:15]
+; GCN-O0-NEXT: ; implicit-def: $sgpr4
; GCN-O0-NEXT: v_mov_b32_e32 v0, s4
; GCN-O0-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen
; GCN-O0-NEXT: s_mov_b32 s4, 0
diff --git a/llvm/test/CodeGen/AMDGPU/indirect-addressing-si.ll b/llvm/test/CodeGen/AMDGPU/indirect-addressing-si.ll
index 6fed9889838cd8..e71c6cf71c8823 100644
--- a/llvm/test/CodeGen/AMDGPU/indirect-addressing-si.ll
+++ b/llvm/test/CodeGen/AMDGPU/indirect-addressing-si.ll
@@ -5370,9 +5370,9 @@ define amdgpu_kernel void @extract_vgpr_offset_multiple_in_block(ptr addrspace(1
; NOOPT-NEXT: s_waitcnt expcnt(0)
; NOOPT-NEXT: buffer_load_dword v18, off, s[36:39], 0 ; 4-byte Folded Reload
; NOOPT-NEXT: s_mov_b64 exec, s[28:29]
-; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: v_readlane_b32 s4, v18, 25
+; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: s_mov_b32 s7, s1
; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: ; kill: def $sgpr0 killed $sgpr0 killed $sgpr0_sgpr1
@@ -6223,8 +6223,8 @@ define amdgpu_kernel void @insert_vgpr_offset_multiple_in_block(ptr addrspace(1)
; NOOPT-NEXT: s_mov_b64 exec, s[0:1]
; NOOPT-NEXT: s_cbranch_execz .LBB17_8
; NOOPT-NEXT: ; %bb.7: ; %bb1
-; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: buffer_load_dword v0, off, s[28:31], 0 offset:68 ; 4-byte Folded Reload
+; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: s_mov_b32 s6, s1
; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: ; kill: def $sgpr0 killed $sgpr0 killed $sgpr0_sgpr1
@@ -7286,10 +7286,10 @@ define amdgpu_kernel void @extract_adjacent_blocks(i32 %arg) {
; NOOPT-NEXT: s_waitcnt expcnt(0)
; NOOPT-NEXT: buffer_load_dword v4, off, s[12:15], 0 ; 4-byte Folded Reload
; NOOPT-NEXT: s_mov_b64 exec, s[8:9]
-; NOOPT-NEXT: ; implicit-def: $sgpr2
; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: v_readlane_b32 s0, v4, 0
; NOOPT-NEXT: v_readlane_b32 s1, v4, 1
+; NOOPT-NEXT: ; implicit-def: $sgpr2
; NOOPT-NEXT: v_cndmask_b32_e64 v0, 0, 1, s[0:1]
; NOOPT-NEXT: s_mov_b32 s0, 1
; NOOPT-NEXT: ; implicit-def: $sgpr1
@@ -7316,11 +7316,11 @@ define amdgpu_kernel void @extract_adjacent_blocks(i32 %arg) {
; NOOPT-NEXT: ;;#ASMEND
; NOOPT-NEXT: s_branch .LBB19_4
; NOOPT-NEXT: .LBB19_3: ; %bb4
-; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: s_or_saveexec_b64 s[8:9], -1
; NOOPT-NEXT: s_waitcnt expcnt(0)
; NOOPT-NEXT: buffer_load_dword v4, off, s[12:15], 0 ; 4-byte Folded Reload
; NOOPT-NEXT: s_mov_b64 exec, s[8:9]
+; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: s_mov_b32 s6, s1
; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: ; kill: def $sgpr0 killed $sgpr0 killed $sgpr0_sgpr1
@@ -7345,8 +7345,8 @@ define amdgpu_kernel void @extract_adjacent_blocks(i32 %arg) {
; NOOPT-NEXT: s_mov_b64 exec, s[8:9]
; NOOPT-NEXT: s_branch .LBB19_1
; NOOPT-NEXT: .LBB19_4: ; %bb7
-; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: ; implicit-def: $sgpr4
+; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: s_mov_b32 s7, s1
; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: ; kill: def $sgpr0 killed $sgpr0 killed $sgpr0_sgpr1
@@ -7529,10 +7529,10 @@ define amdgpu_kernel void @insert_adjacent_blocks(i32 %arg, float %val0) {
; NOOPT-NEXT: s_waitcnt expcnt(0)
; NOOPT-NEXT: buffer_load_dword v4, off, s[16:19], 0 ; 4-byte Folded Reload
; NOOPT-NEXT: s_mov_b64 exec, s[12:13]
-; NOOPT-NEXT: ; implicit-def: $sgpr4_sgpr5_sgpr6_sgpr7
; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: v_readlane_b32 s0, v4, 0
; NOOPT-NEXT: v_readlane_b32 s1, v4, 1
+; NOOPT-NEXT: ; implicit-def: $sgpr4_sgpr5_sgpr6_sgpr7
; NOOPT-NEXT: v_cndmask_b32_e64 v0, 0, 1, s[0:1]
; NOOPT-NEXT: s_mov_b32 s0, 1
; NOOPT-NEXT: ; implicit-def: $sgpr1
@@ -7560,11 +7560,11 @@ define amdgpu_kernel void @insert_adjacent_blocks(i32 %arg, float %val0) {
; NOOPT-NEXT: ;;#ASMEND
; NOOPT-NEXT: s_branch .LBB20_4
; NOOPT-NEXT: .LBB20_3: ; %bb4
-; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: s_or_saveexec_b64 s[12:13], -1
; NOOPT-NEXT: s_waitcnt expcnt(0)
; NOOPT-NEXT: buffer_load_dword v4, off, s[16:19], 0 ; 4-byte Folded Reload
; NOOPT-NEXT: s_mov_b64 exec, s[12:13]
+; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: s_mov_b32 s6, s1
; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: ; kill: def $sgpr0 killed $sgpr0 killed $sgpr0_sgpr1
@@ -7590,8 +7590,8 @@ define amdgpu_kernel void @insert_adjacent_blocks(i32 %arg, float %val0) {
; NOOPT-NEXT: s_mov_b64 exec, s[12:13]
; NOOPT-NEXT: s_branch .LBB20_1
; NOOPT-NEXT: .LBB20_4: ; %bb7
-; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: ; implicit-def: $sgpr4_sgpr5_sgpr6_sgpr7
+; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: s_mov_b32 s10, s1
; NOOPT-NEXT: ; implicit-def: $sgpr0_sgpr1
; NOOPT-NEXT: ; kill: def $sgpr0 killed $sgpr0 killed $sgpr0_sgpr1
@@ -9105,9 +9105,9 @@ define amdgpu_kernel void @broken_phi_bb(i32 %arg, i32 %arg1) {
; NOOPT-NEXT: s_waitcnt expcnt(0)
; NOOPT-NEXT: buffer_load_dword v18, off, s[24:27], 0 ; 4-byte Folded Reload
; NOOPT-NEXT: s_mov_b64 exec, s[20:21]
-; NOOPT-NEXT: ; implicit-def: $sgpr2_sgpr3
; NOOPT-NEXT: s_waitcnt vmcnt(0)
; NOOPT-NEXT: v_readlane_b32 s0, v18, 1
+; NOOPT-NEXT: ; implicit-def: $sgpr2_sgpr3
; NOOPT-NEXT: ; kill: def $sgpr3 killed $sgpr3 killed $sgpr2_sgpr3
; NOOPT-NEXT: ; implicit-def: $sgpr4_sgpr5
; NOOPT-NEXT: ; kill: def $sgpr4 killed $sgpr4 killed $sgpr4_sgpr5
diff --git a/llvm/test/CodeGen/AMDGPU/infloop-subrange-spill-inspect-subrange.mir b/llvm/test/CodeGen/AMDGPU/infloop-subrange-spill-inspect-subrange.mir
index 7421a2e10c3b57..215200c770245d 100644
--- a/llvm/test/CodeGen/AMDGPU/infloop-subrange-spill-inspect-subrange.mir
+++ b/llvm/test/CodeGen/AMDGPU/infloop-subrange-spill-inspect-subrange.mir
@@ -27,11 +27,9 @@ body: |
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: renamable $sgpr5 = IMPLICIT_DEF
; CHECK-NEXT: dead undef [[DEF:%[0-9]+]].sub0:vreg_64 = IMPLICIT_DEF
- ; CHECK-NEXT: renamable $sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27 = IMPLICIT_DEF
; CHECK-NEXT: dead [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
; CHECK-NEXT: dead undef [[DEF2:%[0-9]+]].sub0:vreg_64 = IMPLICIT_DEF
- ; CHECK-NEXT: renamable $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19 = S_LOAD_DWORDX16_IMM renamable $sgpr4_sgpr5, 0, 0 :: (invariant load (s512), align 32, addrspace 4)
- ; CHECK-NEXT: SI_SPILL_S512_SAVE killed renamable $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19, %stack.0, implicit $exec, implicit $sgpr32 :: (store (s512) into %stack.0, align 4, addrspace 5)
+ ; CHECK-NEXT: renamable $sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51 = S_LOAD_DWORDX16_IMM renamable $sgpr4_sgpr5, 0, 0 :: (invariant load (s512), align 32, addrspace 4)
; CHECK-NEXT: renamable $sgpr24 = IMPLICIT_DEF implicit-def $sgpr25
; CHECK-NEXT: renamable $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19 = S_LOAD_DWORDX16_IMM undef renamable $sgpr4_sgpr5, 0, 0 :: (invariant load (s512), align 32, addrspace 4)
; CHECK-NEXT: $exec = S_MOV_B64_term undef renamable $sgpr4_sgpr5
@@ -39,15 +37,14 @@ body: |
; CHECK-NEXT: S_BRANCH %bb.5
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.1:
- ; CHECK-NEXT: liveins: $sgpr24_sgpr25_sgpr26_sgpr27:0x000000000000000F, $sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27:0x00000000000000FF, $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19:0x000000000000FFFF
+ ; CHECK-NEXT: liveins: $sgpr24_sgpr25_sgpr26_sgpr27:0x000000000000000F, $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19:0x000000000000FFFF, $sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51:0x000000000000FFFF
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: $exec = S_MOV_B64_term undef renamable $sgpr4_sgpr5
; CHECK-NEXT: S_CBRANCH_EXECNZ %bb.4, implicit $exec
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.2:
- ; CHECK-NEXT: liveins: $sgpr24_sgpr25_sgpr26_sgpr27:0x000000000000000F, $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19:0x000000000000FFFF
+ ; CHECK-NEXT: liveins: $sgpr24_sgpr25_sgpr26_sgpr27:0x000000000000000F, $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19:0x000000000000FFFF, $sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51:0x000000000000FFFF
; CHECK-NEXT: {{ $}}
- ; CHECK-NEXT: renamable $sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51 = SI_SPILL_S512_RESTORE %stack.0, implicit $exec, implicit $sgpr32 :: (load (s512) from %stack.0, align 4, addrspace 5)
; CHECK-NEXT: dead [[IMAGE_SAMPLE_LZ_V1_V2_:%[0-9]+]]:vgpr_32 = IMAGE_SAMPLE_LZ_V1_V2 undef [[DEF2]], killed renamable $sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43, undef renamable $sgpr24_sgpr25_sgpr26_sgpr27, 1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 8)
; CHECK-NEXT: dead [[IMAGE_SAMPLE_LZ_V1_V2_1:%[0-9]+]]:vgpr_32 = IMAGE_SAMPLE_LZ_V1_V2 undef [[DEF2]], killed renamable $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11, renamable $sgpr24_sgpr25_sgpr26_sgpr27, 1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 8)
; CHECK-NEXT: {{ $}}
@@ -55,33 +52,37 @@ body: |
; CHECK-NEXT: SI_RETURN
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.4:
- ; CHECK-NEXT: liveins: $sgpr24_sgpr25_sgpr26_sgpr27:0x000000000000000F, $sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27:0x00000000000000FF, $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19:0x000000000000FFFF
+ ; CHECK-NEXT: liveins: $sgpr24_sgpr25_sgpr26_sgpr27:0x000000000000000F, $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19:0x000000000000FFFF, $sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51:0x000000000000FFFF
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: renamable $sgpr12 = IMPLICIT_DEF
+ ; CHECK-NEXT: SI_SPILL_S512_SAVE renamable $sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51, %stack.0, implicit $exec, implicit $sgpr32 :: (store (s512) into %stack.0, align 4, addrspace 5)
; CHECK-NEXT: renamable $sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51 = IMPLICIT_DEF
; CHECK-NEXT: dead undef [[IMAGE_SAMPLE_LZ_V1_V2_2:%[0-9]+]].sub0:vreg_96 = IMAGE_SAMPLE_LZ_V1_V2 undef [[DEF2]], killed renamable $sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43, renamable $sgpr12_sgpr13_sgpr14_sgpr15, 1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 8)
- ; CHECK-NEXT: dead undef [[IMAGE_SAMPLE_LZ_V1_V2_3:%[0-9]+]].sub0:vreg_128 = IMAGE_SAMPLE_LZ_V1_V2 undef [[DEF2]], undef renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19, killed renamable $sgpr20_sgpr21_sgpr22_sgpr23, 1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 8)
+ ; CHECK-NEXT: renamable $sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51 = SI_SPILL_S512_RESTORE %stack.0, implicit $exec, implicit $sgpr32 :: (load (s512) from %stack.0, align 4, addrspace 5)
+ ; CHECK-NEXT: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19 = IMPLICIT_DEF
+ ; CHECK-NEXT: dead undef [[IMAGE_SAMPLE_LZ_V1_V2_3:%[0-9]+]].sub0:vreg_128 = IMAGE_SAMPLE_LZ_V1_V2 undef [[DEF2]], undef renamable $sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51, killed renamable $sgpr12_sgpr13_sgpr14_sgpr15, 1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 8)
; CHECK-NEXT: S_BRANCH %bb.2
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.5:
- ; CHECK-NEXT: liveins: $sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27:0x00000000000000FF, $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19:0x000000000000FFFF
+ ; CHECK-NEXT: liveins: $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19:0x000000000000FFFF, $sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51:0x00000000FFFFFFFF
; CHECK-NEXT: {{ $}}
+ ; CHECK-NEXT: renamable $sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27 = COPY killed renamable $sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51
; CHECK-NEXT: renamable $sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51 = IMPLICIT_DEF
; CHECK-NEXT: dead [[IMAGE_SAMPLE_LZ_V1_V2_4:%[0-9]+]]:vgpr_32 = IMAGE_SAMPLE_LZ_V1_V2 undef [[DEF]], killed renamable $sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51, undef renamable $sgpr24_sgpr25_sgpr26_sgpr27, 1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 8)
+ ; CHECK-NEXT: renamable $sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51 = COPY kill...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/115834
More information about the llvm-commits
mailing list