[llvm] [MachineSink] Fix typo in loop sinking (PR #127133)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Feb 13 14:11:21 PST 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Jeffrey Byrnes (jrbyrnes)
<details>
<summary>Changes</summary>
Failure to sink a candidate should not block us from attempting to sink other candidates. There are mechanisms in place to handle the case where the failed to be sunk instruction uses an instruction that gets sunk (we do not delete the sunk instruction if it still has uses).
---
Full diff: https://github.com/llvm/llvm-project/pull/127133.diff
2 Files Affected:
- (modified) llvm/lib/CodeGen/MachineSink.cpp (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/machine-sink-cycle.mir (+82-28)
``````````diff
diff --git a/llvm/lib/CodeGen/MachineSink.cpp b/llvm/lib/CodeGen/MachineSink.cpp
index 82acb780cfb72..b20668fe3ea46 100644
--- a/llvm/lib/CodeGen/MachineSink.cpp
+++ b/llvm/lib/CodeGen/MachineSink.cpp
@@ -836,7 +836,7 @@ bool MachineSinking::runOnMachineFunction(MachineFunction &MF) {
continue;
if (!aggressivelySinkIntoCycle(Cycle, *I, SunkInstrs))
- break;
+ continue;
EverMadeChange = true;
++NumCycleSunk;
}
diff --git a/llvm/test/CodeGen/AMDGPU/machine-sink-cycle.mir b/llvm/test/CodeGen/AMDGPU/machine-sink-cycle.mir
index bca1517ed183a..f718749bff3d3 100644
--- a/llvm/test/CodeGen/AMDGPU/machine-sink-cycle.mir
+++ b/llvm/test/CodeGen/AMDGPU/machine-sink-cycle.mir
@@ -1078,6 +1078,19 @@ body: |
; GFX9-SUNK-NEXT: [[DEF2:%[0-9]+]]:vreg_256_align2 = IMPLICIT_DEF
; GFX9-SUNK-NEXT: [[DEF3:%[0-9]+]]:vreg_256_align2 = IMPLICIT_DEF
; GFX9-SUNK-NEXT: [[DEF4:%[0-9]+]]:vreg_256_align2 = IMPLICIT_DEF
+ ; GFX9-SUNK-NEXT: [[V_ADD_CO_U32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_CO_U32_e64 [[DEF]].sub2, [[DEF1]].sub4, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: S_BRANCH %bb.1
+ ; GFX9-SUNK-NEXT: {{ $}}
+ ; GFX9-SUNK-NEXT: bb.1:
+ ; GFX9-SUNK-NEXT: successors: %bb.2(0x40000000), %bb.3(0x40000000)
+ ; GFX9-SUNK-NEXT: {{ $}}
+ ; GFX9-SUNK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, implicit [[V_ADD_CO_U32_e64_]], implicit [[V_ADD_CO_U32_e64_1]]
+ ; GFX9-SUNK-NEXT: S_CBRANCH_EXECZ %bb.2, implicit $exec
+ ; GFX9-SUNK-NEXT: S_BRANCH %bb.3
+ ; GFX9-SUNK-NEXT: {{ $}}
+ ; GFX9-SUNK-NEXT: bb.2:
+ ; GFX9-SUNK-NEXT: successors: %bb.4(0x80000000)
+ ; GFX9-SUNK-NEXT: {{ $}}
; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub0, [[DEF1]].sub0, 0, implicit $exec
; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub1, [[DEF1]].sub0, 0, implicit $exec
; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_2:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub2, [[DEF1]].sub0, 0, implicit $exec
@@ -1105,19 +1118,6 @@ body: |
; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_24:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub0, [[DEF1]].sub3, 0, implicit $exec
; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_25:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub1, [[DEF1]].sub3, 0, implicit $exec
; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_26:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub2, [[DEF1]].sub3, 0, implicit $exec
- ; GFX9-SUNK-NEXT: [[V_ADD_CO_U32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_CO_U32_e64 [[DEF]].sub2, [[DEF1]].sub4, 0, implicit $exec
- ; GFX9-SUNK-NEXT: S_BRANCH %bb.1
- ; GFX9-SUNK-NEXT: {{ $}}
- ; GFX9-SUNK-NEXT: bb.1:
- ; GFX9-SUNK-NEXT: successors: %bb.2(0x40000000), %bb.3(0x40000000)
- ; GFX9-SUNK-NEXT: {{ $}}
- ; GFX9-SUNK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, implicit [[V_ADD_CO_U32_e64_]], implicit [[V_ADD_CO_U32_e64_1]]
- ; GFX9-SUNK-NEXT: S_CBRANCH_EXECZ %bb.2, implicit $exec
- ; GFX9-SUNK-NEXT: S_BRANCH %bb.3
- ; GFX9-SUNK-NEXT: {{ $}}
- ; GFX9-SUNK-NEXT: bb.2:
- ; GFX9-SUNK-NEXT: successors: %bb.4(0x80000000)
- ; GFX9-SUNK-NEXT: {{ $}}
; GFX9-SUNK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, implicit [[DEF]], implicit [[DEF1]], implicit [[DEF2]], implicit [[DEF3]], implicit [[DEF4]]
; GFX9-SUNK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, implicit [[V_ADD_U32_e64_]], implicit [[V_ADD_U32_e64_1]], implicit [[V_ADD_U32_e64_2]], implicit [[V_ADD_U32_e64_3]], implicit [[V_ADD_U32_e64_4]], implicit [[V_ADD_U32_e64_5]], implicit [[V_ADD_U32_e64_6]], implicit [[V_ADD_U32_e64_7]], implicit [[V_ADD_U32_e64_8]], implicit [[V_ADD_U32_e64_9]], implicit [[V_ADD_U32_e64_10]], implicit [[V_ADD_U32_e64_11]], implicit [[V_ADD_U32_e64_12]], implicit [[V_ADD_U32_e64_13]], implicit [[V_ADD_U32_e64_14]], implicit [[V_ADD_U32_e64_15]], implicit [[V_ADD_U32_e64_16]], implicit [[V_ADD_U32_e64_17]], implicit [[V_ADD_U32_e64_18]], implicit [[V_ADD_U32_e64_19]], implicit [[V_ADD_U32_e64_20]], implicit [[V_ADD_U32_e64_21]], implicit [[V_ADD_U32_e64_22]], implicit [[V_ADD_U32_e64_23]], implicit [[V_ADD_U32_e64_24]], implicit [[V_ADD_U32_e64_25]], implicit [[V_ADD_U32_e64_26]]
; GFX9-SUNK-NEXT: S_BRANCH %bb.4
@@ -1125,8 +1125,35 @@ body: |
; GFX9-SUNK-NEXT: bb.3:
; GFX9-SUNK-NEXT: successors: %bb.4(0x80000000)
; GFX9-SUNK-NEXT: {{ $}}
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_27:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub0, [[DEF1]].sub0, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_28:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub1, [[DEF1]].sub0, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_29:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub2, [[DEF1]].sub0, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_30:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub3, [[DEF1]].sub0, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_31:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub4, [[DEF1]].sub0, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_32:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub5, [[DEF1]].sub0, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_33:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub6, [[DEF1]].sub0, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_34:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub7, [[DEF1]].sub0, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_35:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub0, [[DEF1]].sub1, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_36:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub1, [[DEF1]].sub1, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_37:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub2, [[DEF1]].sub1, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_38:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub3, [[DEF1]].sub1, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_39:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub4, [[DEF1]].sub1, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_40:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub5, [[DEF1]].sub1, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_41:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub6, [[DEF1]].sub1, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_42:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub7, [[DEF1]].sub1, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_43:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub0, [[DEF1]].sub2, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_44:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub1, [[DEF1]].sub2, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_45:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub2, [[DEF1]].sub2, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_46:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub3, [[DEF1]].sub2, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_47:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub4, [[DEF1]].sub2, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_48:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub5, [[DEF1]].sub2, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_49:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub6, [[DEF1]].sub2, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_50:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub7, [[DEF1]].sub2, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_51:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub0, [[DEF1]].sub3, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_52:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub1, [[DEF1]].sub3, 0, implicit $exec
+ ; GFX9-SUNK-NEXT: [[V_ADD_U32_e64_53:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub2, [[DEF1]].sub3, 0, implicit $exec
; GFX9-SUNK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, implicit [[DEF]], implicit [[DEF1]], implicit [[DEF2]], implicit [[DEF3]], implicit [[DEF4]]
- ; GFX9-SUNK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, implicit [[V_ADD_U32_e64_]], implicit [[V_ADD_U32_e64_1]], implicit [[V_ADD_U32_e64_2]], implicit [[V_ADD_U32_e64_3]], implicit [[V_ADD_U32_e64_4]], implicit [[V_ADD_U32_e64_5]], implicit [[V_ADD_U32_e64_6]], implicit [[V_ADD_U32_e64_7]], implicit [[V_ADD_U32_e64_8]], implicit [[V_ADD_U32_e64_9]], implicit [[V_ADD_U32_e64_10]], implicit [[V_ADD_U32_e64_11]], implicit [[V_ADD_U32_e64_12]], implicit [[V_ADD_U32_e64_13]], implicit [[V_ADD_U32_e64_14]], implicit [[V_ADD_U32_e64_15]], implicit [[V_ADD_U32_e64_16]], implicit [[V_ADD_U32_e64_17]], implicit [[V_ADD_U32_e64_18]], implicit [[V_ADD_U32_e64_19]], implicit [[V_ADD_U32_e64_20]], implicit [[V_ADD_U32_e64_21]], implicit [[V_ADD_U32_e64_22]], implicit [[V_ADD_U32_e64_23]], implicit [[V_ADD_U32_e64_24]], implicit [[V_ADD_U32_e64_25]], implicit [[V_ADD_U32_e64_26]]
+ ; GFX9-SUNK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, implicit [[V_ADD_U32_e64_27]], implicit [[V_ADD_U32_e64_28]], implicit [[V_ADD_U32_e64_29]], implicit [[V_ADD_U32_e64_30]], implicit [[V_ADD_U32_e64_31]], implicit [[V_ADD_U32_e64_32]], implicit [[V_ADD_U32_e64_33]], implicit [[V_ADD_U32_e64_34]], implicit [[V_ADD_U32_e64_35]], implicit [[V_ADD_U32_e64_36]], implicit [[V_ADD_U32_e64_37]], implicit [[V_ADD_U32_e64_38]], implicit [[V_ADD_U32_e64_39]], implicit [[V_ADD_U32_e64_40]], implicit [[V_ADD_U32_e64_41]], implicit [[V_ADD_U32_e64_42]], implicit [[V_ADD_U32_e64_43]], implicit [[V_ADD_U32_e64_44]], implicit [[V_ADD_U32_e64_45]], implicit [[V_ADD_U32_e64_46]], implicit [[V_ADD_U32_e64_47]], implicit [[V_ADD_U32_e64_48]], implicit [[V_ADD_U32_e64_49]], implicit [[V_ADD_U32_e64_50]], implicit [[V_ADD_U32_e64_51]], implicit [[V_ADD_U32_e64_52]], implicit [[V_ADD_U32_e64_53]]
; GFX9-SUNK-NEXT: S_BRANCH %bb.4
; GFX9-SUNK-NEXT: {{ $}}
; GFX9-SUNK-NEXT: bb.4:
@@ -1149,6 +1176,19 @@ body: |
; GFX10-SUNK-NEXT: [[DEF2:%[0-9]+]]:vreg_256 = IMPLICIT_DEF
; GFX10-SUNK-NEXT: [[DEF3:%[0-9]+]]:vreg_256 = IMPLICIT_DEF
; GFX10-SUNK-NEXT: [[DEF4:%[0-9]+]]:vreg_256 = IMPLICIT_DEF
+ ; GFX10-SUNK-NEXT: [[V_ADD_CO_U32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_CO_U32_e64 [[DEF]].sub2, [[DEF1]].sub4, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: S_BRANCH %bb.1
+ ; GFX10-SUNK-NEXT: {{ $}}
+ ; GFX10-SUNK-NEXT: bb.1:
+ ; GFX10-SUNK-NEXT: successors: %bb.2(0x40000000), %bb.3(0x40000000)
+ ; GFX10-SUNK-NEXT: {{ $}}
+ ; GFX10-SUNK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, implicit [[V_ADD_CO_U32_e64_]], implicit [[V_ADD_CO_U32_e64_1]]
+ ; GFX10-SUNK-NEXT: S_CBRANCH_EXECZ %bb.2, implicit $exec
+ ; GFX10-SUNK-NEXT: S_BRANCH %bb.3
+ ; GFX10-SUNK-NEXT: {{ $}}
+ ; GFX10-SUNK-NEXT: bb.2:
+ ; GFX10-SUNK-NEXT: successors: %bb.4(0x80000000)
+ ; GFX10-SUNK-NEXT: {{ $}}
; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub0, [[DEF1]].sub0, 0, implicit $exec
; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub1, [[DEF1]].sub0, 0, implicit $exec
; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_2:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub2, [[DEF1]].sub0, 0, implicit $exec
@@ -1176,19 +1216,6 @@ body: |
; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_24:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub0, [[DEF1]].sub3, 0, implicit $exec
; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_25:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub1, [[DEF1]].sub3, 0, implicit $exec
; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_26:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub2, [[DEF1]].sub3, 0, implicit $exec
- ; GFX10-SUNK-NEXT: [[V_ADD_CO_U32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADD_CO_U32_e64 [[DEF]].sub2, [[DEF1]].sub4, 0, implicit $exec
- ; GFX10-SUNK-NEXT: S_BRANCH %bb.1
- ; GFX10-SUNK-NEXT: {{ $}}
- ; GFX10-SUNK-NEXT: bb.1:
- ; GFX10-SUNK-NEXT: successors: %bb.2(0x40000000), %bb.3(0x40000000)
- ; GFX10-SUNK-NEXT: {{ $}}
- ; GFX10-SUNK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, implicit [[V_ADD_CO_U32_e64_]], implicit [[V_ADD_CO_U32_e64_1]]
- ; GFX10-SUNK-NEXT: S_CBRANCH_EXECZ %bb.2, implicit $exec
- ; GFX10-SUNK-NEXT: S_BRANCH %bb.3
- ; GFX10-SUNK-NEXT: {{ $}}
- ; GFX10-SUNK-NEXT: bb.2:
- ; GFX10-SUNK-NEXT: successors: %bb.4(0x80000000)
- ; GFX10-SUNK-NEXT: {{ $}}
; GFX10-SUNK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, implicit [[DEF]], implicit [[DEF1]], implicit [[DEF2]], implicit [[DEF3]], implicit [[DEF4]]
; GFX10-SUNK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, implicit [[V_ADD_U32_e64_]], implicit [[V_ADD_U32_e64_1]], implicit [[V_ADD_U32_e64_2]], implicit [[V_ADD_U32_e64_3]], implicit [[V_ADD_U32_e64_4]], implicit [[V_ADD_U32_e64_5]], implicit [[V_ADD_U32_e64_6]], implicit [[V_ADD_U32_e64_7]], implicit [[V_ADD_U32_e64_8]], implicit [[V_ADD_U32_e64_9]], implicit [[V_ADD_U32_e64_10]], implicit [[V_ADD_U32_e64_11]], implicit [[V_ADD_U32_e64_12]], implicit [[V_ADD_U32_e64_13]], implicit [[V_ADD_U32_e64_14]], implicit [[V_ADD_U32_e64_15]], implicit [[V_ADD_U32_e64_16]], implicit [[V_ADD_U32_e64_17]], implicit [[V_ADD_U32_e64_18]], implicit [[V_ADD_U32_e64_19]], implicit [[V_ADD_U32_e64_20]], implicit [[V_ADD_U32_e64_21]], implicit [[V_ADD_U32_e64_22]], implicit [[V_ADD_U32_e64_23]], implicit [[V_ADD_U32_e64_24]], implicit [[V_ADD_U32_e64_25]], implicit [[V_ADD_U32_e64_26]]
; GFX10-SUNK-NEXT: S_BRANCH %bb.4
@@ -1196,8 +1223,35 @@ body: |
; GFX10-SUNK-NEXT: bb.3:
; GFX10-SUNK-NEXT: successors: %bb.4(0x80000000)
; GFX10-SUNK-NEXT: {{ $}}
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_27:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub0, [[DEF1]].sub0, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_28:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub1, [[DEF1]].sub0, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_29:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub2, [[DEF1]].sub0, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_30:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub3, [[DEF1]].sub0, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_31:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub4, [[DEF1]].sub0, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_32:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub5, [[DEF1]].sub0, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_33:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub6, [[DEF1]].sub0, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_34:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub7, [[DEF1]].sub0, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_35:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub0, [[DEF1]].sub1, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_36:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub1, [[DEF1]].sub1, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_37:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub2, [[DEF1]].sub1, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_38:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub3, [[DEF1]].sub1, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_39:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub4, [[DEF1]].sub1, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_40:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub5, [[DEF1]].sub1, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_41:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub6, [[DEF1]].sub1, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_42:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub7, [[DEF1]].sub1, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_43:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub0, [[DEF1]].sub2, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_44:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub1, [[DEF1]].sub2, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_45:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub2, [[DEF1]].sub2, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_46:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub3, [[DEF1]].sub2, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_47:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub4, [[DEF1]].sub2, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_48:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub5, [[DEF1]].sub2, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_49:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub6, [[DEF1]].sub2, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_50:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub7, [[DEF1]].sub2, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_51:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub0, [[DEF1]].sub3, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_52:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub1, [[DEF1]].sub3, 0, implicit $exec
+ ; GFX10-SUNK-NEXT: [[V_ADD_U32_e64_53:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[DEF]].sub2, [[DEF1]].sub3, 0, implicit $exec
; GFX10-SUNK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, implicit [[DEF]], implicit [[DEF1]], implicit [[DEF2]], implicit [[DEF3]], implicit [[DEF4]]
- ; GFX10-SUNK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, implicit [[V_ADD_U32_e64_]], implicit [[V_ADD_U32_e64_1]], implicit [[V_ADD_U32_e64_2]], implicit [[V_ADD_U32_e64_3]], implicit [[V_ADD_U32_e64_4]], implicit [[V_ADD_U32_e64_5]], implicit [[V_ADD_U32_e64_6]], implicit [[V_ADD_U32_e64_7]], implicit [[V_ADD_U32_e64_8]], implicit [[V_ADD_U32_e64_9]], implicit [[V_ADD_U32_e64_10]], implicit [[V_ADD_U32_e64_11]], implicit [[V_ADD_U32_e64_12]], implicit [[V_ADD_U32_e64_13]], implicit [[V_ADD_U32_e64_14]], implicit [[V_ADD_U32_e64_15]], implicit [[V_ADD_U32_e64_16]], implicit [[V_ADD_U32_e64_17]], implicit [[V_ADD_U32_e64_18]], implicit [[V_ADD_U32_e64_19]], implicit [[V_ADD_U32_e64_20]], implicit [[V_ADD_U32_e64_21]], implicit [[V_ADD_U32_e64_22]], implicit [[V_ADD_U32_e64_23]], implicit [[V_ADD_U32_e64_24]], implicit [[V_ADD_U32_e64_25]], implicit [[V_ADD_U32_e64_26]]
+ ; GFX10-SUNK-NEXT: INLINEASM &"", 1 /* sideeffect attdialect */, implicit [[V_ADD_U32_e64_27]], implicit [[V_ADD_U32_e64_28]], implicit [[V_ADD_U32_e64_29]], implicit [[V_ADD_U32_e64_30]], implicit [[V_ADD_U32_e64_31]], implicit [[V_ADD_U32_e64_32]], implicit [[V_ADD_U32_e64_33]], implicit [[V_ADD_U32_e64_34]], implicit [[V_ADD_U32_e64_35]], implicit [[V_ADD_U32_e64_36]], implicit [[V_ADD_U32_e64_37]], implicit [[V_ADD_U32_e64_38]], implicit [[V_ADD_U32_e64_39]], implicit [[V_ADD_U32_e64_40]], implicit [[V_ADD_U32_e64_41]], implicit [[V_ADD_U32_e64_42]], implicit [[V_ADD_U32_e64_43]], implicit [[V_ADD_U32_e64_44]], implicit [[V_ADD_U32_e64_45]], implicit [[V_ADD_U32_e64_46]], implicit [[V_ADD_U32_e64_47]], implicit [[V_ADD_U32_e64_48]], implicit [[V_ADD_U32_e64_49]], implicit [[V_ADD_U32_e64_50]], implicit [[V_ADD_U32_e64_51]], implicit [[V_ADD_U32_e64_52]], implicit [[V_ADD_U32_e64_53]]
; GFX10-SUNK-NEXT: S_BRANCH %bb.4
; GFX10-SUNK-NEXT: {{ $}}
; GFX10-SUNK-NEXT: bb.4:
``````````
</details>
https://github.com/llvm/llvm-project/pull/127133
More information about the llvm-commits
mailing list