[llvm] e02d1e2 - [AMDGPU][CodeGen] Do not rematerialize convergent MIs (#214711)

via llvm-commits llvm-commits at lists.llvm.org
Fri Aug 7 06:25:29 PDT 2026


Author: Lucas Ramirez
Date: 2026-08-07T15:25:24+02:00
New Revision: e02d1e2d88f753f115a716e7ec6f30083169ca73

URL: https://github.com/llvm/llvm-project/commit/e02d1e2d88f753f115a716e7ec6f30083169ca73
DIFF: https://github.com/llvm/llvm-project/commit/e02d1e2d88f753f115a716e7ec6f30083169ca73.diff

LOG: [AMDGPU][CodeGen] Do not rematerialize convergent MIs (#214711)

It is generally not safe to rematerialize convergent instructions to
different scheduling regions/blocks. This adds a check to the
scheduler's `PreRARematStage` to prevent rematerialization of convergent
instructions in all cases.

Added: 
    

Modified: 
    llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
    llvm/test/CodeGen/AMDGPU/machine-scheduler-sink-trivial-remats.mir

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp b/llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
index 2701a71b77b87..6cfdc8717ef64 100644
--- a/llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
@@ -1550,6 +1550,15 @@ bool PreRARematStage::initGCNSchedStage() {
     if (NumUsers != 1)
       continue;
 
+    // Rematerialization moves the defining instruction into the region of its
+    // use, which may sit under 
diff erent control dependencies (e.g., across a
+    // change of EXEC). Convergent operations must not be made control-dependent
+    // on additional values, so they cannot be safely relocated this way. This
+    // mirrors the check MachineSink performs before sinking an instruction.
+    if (any_of(CandReg.Defs,
+               [](const MachineInstr *DefMI) { return DefMI->isConvergent(); }))
+      continue;
+
     // We further filter the registers that we can rematerialize based on our
     // current tracking capabilities in the stage. The user cannot itself be
     // marked rematerializable, and no register operand of the defining MI can

diff  --git a/llvm/test/CodeGen/AMDGPU/machine-scheduler-sink-trivial-remats.mir b/llvm/test/CodeGen/AMDGPU/machine-scheduler-sink-trivial-remats.mir
index c1e1c2f6d5c31..fb75d4b465148 100644
--- a/llvm/test/CodeGen/AMDGPU/machine-scheduler-sink-trivial-remats.mir
+++ b/llvm/test/CodeGen/AMDGPU/machine-scheduler-sink-trivial-remats.mir
@@ -13372,3 +13372,194 @@ body:             |
 
     S_ENDPGM 0
 ...
+---
+name:            dont_remat_convergent_mis
+tracksRegLiveness: true
+machineFunctionInfo:
+  isEntryFunction: true
+body:             |
+  ; GFX908-LABEL: name: dont_remat_convergent_mis
+  ; GFX908: bb.0:
+  ; GFX908-NEXT:   successors: %bb.1(0x80000000)
+  ; GFX908-NEXT: {{  $}}
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 0, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_1:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 1, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_2:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 2, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_3:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 3, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_4:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 4, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_5:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 5, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_6:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 6, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_7:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 7, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_8:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 8, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_9:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 9, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_10:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 10, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_11:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 11, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_12:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 12, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_13:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 13, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_14:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 14, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_15:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 15, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_16:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 16, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_17:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 17, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_18:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 18, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_19:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 19, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_20:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 20, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_21:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 21, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_22:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 22, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_23:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 23, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_24:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 24, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_25:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 25, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_26:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 26, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_27:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 27, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_28:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 28, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_29:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 29, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_30:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 30, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   [[V_CVT_I32_F64_e32_31:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 31, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-NEXT:   %conv:vgpr_32 = V_MOV_B32_dpp [[V_CVT_I32_F64_e32_30]], [[V_CVT_I32_F64_e32_31]], 1, 15, 15, 1, implicit $exec
+  ; GFX908-NEXT: {{  $}}
+  ; GFX908-NEXT: bb.1:
+  ; GFX908-NEXT:   successors: %bb.2(0x80000000)
+  ; GFX908-NEXT: {{  $}}
+  ; GFX908-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_]], implicit [[V_CVT_I32_F64_e32_16]]
+  ; GFX908-NEXT:   S_NOP 0, implicit %conv
+  ; GFX908-NEXT: {{  $}}
+  ; GFX908-NEXT: bb.2:
+  ; GFX908-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_1]], implicit [[V_CVT_I32_F64_e32_17]]
+  ; GFX908-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_2]], implicit [[V_CVT_I32_F64_e32_18]]
+  ; GFX908-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_3]], implicit [[V_CVT_I32_F64_e32_19]]
+  ; GFX908-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_4]], implicit [[V_CVT_I32_F64_e32_20]]
+  ; GFX908-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_5]], implicit [[V_CVT_I32_F64_e32_21]]
+  ; GFX908-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_6]], implicit [[V_CVT_I32_F64_e32_22]]
+  ; GFX908-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_7]], implicit [[V_CVT_I32_F64_e32_23]]
+  ; GFX908-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_8]], implicit [[V_CVT_I32_F64_e32_24]]
+  ; GFX908-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_9]], implicit [[V_CVT_I32_F64_e32_25]]
+  ; GFX908-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_10]], implicit [[V_CVT_I32_F64_e32_26]]
+  ; GFX908-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_11]], implicit [[V_CVT_I32_F64_e32_27]]
+  ; GFX908-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_12]], implicit [[V_CVT_I32_F64_e32_28]]
+  ; GFX908-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_13]], implicit [[V_CVT_I32_F64_e32_29]]
+  ; GFX908-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_14]], implicit [[V_CVT_I32_F64_e32_30]]
+  ; GFX908-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_15]], implicit [[V_CVT_I32_F64_e32_31]]
+  ; GFX908-NEXT:   S_ENDPGM 0
+  ;
+  ; GFX908-GCNTRACKERS-LABEL: name: dont_remat_convergent_mis
+  ; GFX908-GCNTRACKERS: bb.0:
+  ; GFX908-GCNTRACKERS-NEXT:   successors: %bb.1(0x80000000)
+  ; GFX908-GCNTRACKERS-NEXT: {{  $}}
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 0, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_1:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 1, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_2:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 2, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_3:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 3, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_4:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 4, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_5:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 5, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_6:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 6, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_7:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 7, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_8:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 8, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_9:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 9, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_10:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 10, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_11:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 11, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_12:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 12, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_13:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 13, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_14:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 14, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_15:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 15, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_16:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 16, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_17:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 17, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_18:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 18, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_19:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 19, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_20:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 20, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_21:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 21, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_22:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 22, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_23:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 23, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_24:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 24, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_25:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 25, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_26:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 26, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_27:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 27, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_28:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 28, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_29:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 29, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_30:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 30, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   [[V_CVT_I32_F64_e32_31:%[0-9]+]]:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 31, implicit $exec, implicit $mode, implicit-def $m0
+  ; GFX908-GCNTRACKERS-NEXT:   %conv:vgpr_32 = V_MOV_B32_dpp [[V_CVT_I32_F64_e32_30]], [[V_CVT_I32_F64_e32_31]], 1, 15, 15, 1, implicit $exec
+  ; GFX908-GCNTRACKERS-NEXT: {{  $}}
+  ; GFX908-GCNTRACKERS-NEXT: bb.1:
+  ; GFX908-GCNTRACKERS-NEXT:   successors: %bb.2(0x80000000)
+  ; GFX908-GCNTRACKERS-NEXT: {{  $}}
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_]], implicit [[V_CVT_I32_F64_e32_16]]
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit %conv
+  ; GFX908-GCNTRACKERS-NEXT: {{  $}}
+  ; GFX908-GCNTRACKERS-NEXT: bb.2:
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_1]], implicit [[V_CVT_I32_F64_e32_17]]
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_2]], implicit [[V_CVT_I32_F64_e32_18]]
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_3]], implicit [[V_CVT_I32_F64_e32_19]]
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_4]], implicit [[V_CVT_I32_F64_e32_20]]
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_5]], implicit [[V_CVT_I32_F64_e32_21]]
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_6]], implicit [[V_CVT_I32_F64_e32_22]]
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_7]], implicit [[V_CVT_I32_F64_e32_23]]
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_8]], implicit [[V_CVT_I32_F64_e32_24]]
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_9]], implicit [[V_CVT_I32_F64_e32_25]]
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_10]], implicit [[V_CVT_I32_F64_e32_26]]
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_11]], implicit [[V_CVT_I32_F64_e32_27]]
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_12]], implicit [[V_CVT_I32_F64_e32_28]]
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_13]], implicit [[V_CVT_I32_F64_e32_29]]
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_14]], implicit [[V_CVT_I32_F64_e32_30]]
+  ; GFX908-GCNTRACKERS-NEXT:   S_NOP 0, implicit [[V_CVT_I32_F64_e32_15]], implicit [[V_CVT_I32_F64_e32_31]]
+  ; GFX908-GCNTRACKERS-NEXT:   S_ENDPGM 0
+  bb.0:
+  successors: %bb.1
+
+    %0:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 0, implicit $exec, implicit $mode, implicit-def $m0
+    %1:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 1, implicit $exec, implicit $mode, implicit-def $m0
+    %2:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 2, implicit $exec, implicit $mode, implicit-def $m0
+    %3:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 3, implicit $exec, implicit $mode, implicit-def $m0
+    %4:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 4, implicit $exec, implicit $mode, implicit-def $m0
+    %5:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 5, implicit $exec, implicit $mode, implicit-def $m0
+    %6:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 6, implicit $exec, implicit $mode, implicit-def $m0
+    %7:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 7, implicit $exec, implicit $mode, implicit-def $m0
+    %8:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 8, implicit $exec, implicit $mode, implicit-def $m0
+    %9:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 9, implicit $exec, implicit $mode, implicit-def $m0
+    %10:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 10, implicit $exec, implicit $mode, implicit-def $m0
+    %11:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 11, implicit $exec, implicit $mode, implicit-def $m0
+    %12:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 12, implicit $exec, implicit $mode, implicit-def $m0
+    %13:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 13, implicit $exec, implicit $mode, implicit-def $m0
+    %14:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 14, implicit $exec, implicit $mode, implicit-def $m0
+    %15:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 15, implicit $exec, implicit $mode, implicit-def $m0
+    %16:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 16, implicit $exec, implicit $mode, implicit-def $m0
+    %17:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 17, implicit $exec, implicit $mode, implicit-def $m0
+    %18:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 18, implicit $exec, implicit $mode, implicit-def $m0
+    %19:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 19, implicit $exec, implicit $mode, implicit-def $m0
+    %20:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 20, implicit $exec, implicit $mode, implicit-def $m0
+    %21:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 21, implicit $exec, implicit $mode, implicit-def $m0
+    %22:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 22, implicit $exec, implicit $mode, implicit-def $m0
+    %23:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 23, implicit $exec, implicit $mode, implicit-def $m0
+    %24:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 24, implicit $exec, implicit $mode, implicit-def $m0
+    %25:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 25, implicit $exec, implicit $mode, implicit-def $m0
+    %26:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 26, implicit $exec, implicit $mode, implicit-def $m0
+    %27:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 27, implicit $exec, implicit $mode, implicit-def $m0
+    %28:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 28, implicit $exec, implicit $mode, implicit-def $m0
+    %29:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 29, implicit $exec, implicit $mode, implicit-def $m0
+    %30:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 30, implicit $exec, implicit $mode, implicit-def $m0
+    %31:vgpr_32 = nofpexcept V_CVT_I32_F64_e32 31, implicit $exec, implicit $mode, implicit-def $m0
+    %conv:vgpr_32 = V_MOV_B32_dpp %30, %31, 1, 15, 15, 1, implicit $exec
+
+  bb.1:
+  successors: %bb.2
+
+    S_NOP 0, implicit %0, implicit %16
+    S_NOP 0, implicit %conv
+
+  bb.2:
+    S_NOP 0, implicit %1, implicit %17
+    S_NOP 0, implicit %2, implicit %18
+    S_NOP 0, implicit %3, implicit %19
+    S_NOP 0, implicit %4, implicit %20
+    S_NOP 0, implicit %5, implicit %21
+    S_NOP 0, implicit %6, implicit %22
+    S_NOP 0, implicit %7, implicit %23
+    S_NOP 0, implicit %8, implicit %24
+    S_NOP 0, implicit %9, implicit %25
+    S_NOP 0, implicit %10, implicit %26
+    S_NOP 0, implicit %11, implicit %27
+    S_NOP 0, implicit %12, implicit %28
+    S_NOP 0, implicit %13, implicit %29
+    S_NOP 0, implicit %14, implicit %30
+    S_NOP 0, implicit %15, implicit %31
+
+    S_ENDPGM 0
+...


        


More information about the llvm-commits mailing list