aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--llvm/lib/Target/AMDGPU/GCNDPPCombine.cpp7
-rw-r--r--llvm/test/CodeGen/AMDGPU/dpp_combine.mir20
2 files changed, 27 insertions, 0 deletions
diff --git a/llvm/lib/Target/AMDGPU/GCNDPPCombine.cpp b/llvm/lib/Target/AMDGPU/GCNDPPCombine.cpp
index 53c84639abda..2bf365168048 100644
--- a/llvm/lib/Target/AMDGPU/GCNDPPCombine.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNDPPCombine.cpp
@@ -123,6 +123,13 @@ bool GCNDPPCombine::isShrinkable(MachineInstr &MI) const {
LLVM_DEBUG(dbgs() << " Inst hasn't e32 equivalent\n");
return false;
}
+ if (const auto *SDst = TII->getNamedOperand(MI, AMDGPU::OpName::sdst)) {
+ // Give up if there are any uses of the carry-out from instructions like
+ // V_ADD_CO_U32. The shrunken form of the instruction would write it to vcc
+ // instead of to a virtual register.
+ if (!MRI->use_nodbg_empty(SDst->getReg()))
+ return false;
+ }
// check if other than abs|neg modifiers are set (opsel for example)
const int64_t Mask = ~(SISrcMods::ABS | SISrcMods::NEG);
if (!hasNoImmOrEqual(MI, AMDGPU::OpName::src0_modifiers, 0, Mask) ||
diff --git a/llvm/test/CodeGen/AMDGPU/dpp_combine.mir b/llvm/test/CodeGen/AMDGPU/dpp_combine.mir
index c00c71a0d538..1c896b44b3ac 100644
--- a/llvm/test/CodeGen/AMDGPU/dpp_combine.mir
+++ b/llvm/test/CodeGen/AMDGPU/dpp_combine.mir
@@ -354,6 +354,26 @@ body: |
%6:vgpr_32 = V_ADD_U32_e64 %5, %1, 1, implicit $exec
...
+# GCN-LABEL: name: add_co_u32_e64
+# GCN: %4:vgpr_32, %5:sreg_64_xexec = V_ADD_CO_U32_e64 %3, %1, 0, implicit $exec
+
+name: add_co_u32_e64
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1
+
+ %0:vgpr_32 = COPY $vgpr0
+ %1:vgpr_32 = COPY $vgpr1
+ %2:vgpr_32 = IMPLICIT_DEF
+
+ ; this shouldn't be combined as the carry-out is used
+ %3:vgpr_32 = V_MOV_B32_dpp undef %2, %0, 1, 15, 15, 1, implicit $exec
+ %4:vgpr_32, %5:sreg_64_xexec = V_ADD_CO_U32_e64 %3, %1, 0, implicit $exec
+
+ S_NOP 0, implicit %5
+...
+
# tests on sequences of dpp consumers
# GCN-LABEL: name: dpp_seq
# GCN: %4:vgpr_32 = V_ADD_CO_U32_dpp %1, %0, %1, 1, 14, 15, 0, implicit-def $vcc, implicit $exec