diff options
| author | Korey Sewell <ksewell@umich.edu> | 2009-05-12 15:01:15 -0400 |
|---|---|---|
| committer | Korey Sewell <ksewell@umich.edu> | 2009-05-12 15:01:15 -0400 |
| commit | 6211fe5d2ee00dae9cd72d9cccdc900241a8f9a2 (patch) | |
| tree | ee0ac43983c31c9c22b7ea28e69725d033287ef4 /src/cpu/inorder/resources/tlb_unit.cc | |
| parent | 3603dd25efb70ec400e8ea1e76137e8e288e533a (diff) | |
| download | gem5-6211fe5d2ee00dae9cd72d9cccdc900241a8f9a2.tar.xz | |
inorder-float: Fix storage of FP results
inorder was incorrectly storing FP values and confusing the integer/fp storage view of floating point operations. A big issue was knowing trying to infer when were doing single or double precision access
because this lets you know the size of value to store (32-64 bits). This isnt exactly straightforward since alpha uses all 64-bit regs while mips/sparc uses a dual-reg view. by getting this value from
the actual floating point register file, the model can figure out what it needs to store
Diffstat (limited to 'src/cpu/inorder/resources/tlb_unit.cc')
| -rw-r--r-- | src/cpu/inorder/resources/tlb_unit.cc | 13 |
1 files changed, 7 insertions, 6 deletions
diff --git a/src/cpu/inorder/resources/tlb_unit.cc b/src/cpu/inorder/resources/tlb_unit.cc index 8532a30ed..238807ebc 100644 --- a/src/cpu/inorder/resources/tlb_unit.cc +++ b/src/cpu/inorder/resources/tlb_unit.cc @@ -160,13 +160,14 @@ TLBUnit::execute(int slot_idx) DPRINTF(InOrderTLB, "[tid:%i]: %s encountered while translating " "addr:%08p for [sn:%i] %s.\n", tid, tlb_req->fault->name(), tlb_req->memReq->getVaddr(), seq_num, inst->instName()); - //insert(inst); - cpu->pipelineStage[stage_num]->setResStall(tlb_req, tid); - tlbBlocked[tid] = true; - scheduleEvent(slot_idx, 1); - // Let CPU handle the fault - cpu->trap(tlb_req->fault, tid); + cpu->pipelineStage[stage_num]->setResStall(tlb_req, tid); + tlbBlocked[tid] = true; + scheduleEvent(slot_idx, 1); + + // Let CPU handle the fault + cpu->trap(tlb_req->fault, tid); + } else { DPRINTF(InOrderTLB, "[tid:%i]: [sn:%i] virt. addr %08p translated " "to phys. addr:%08p.\n", tid, seq_num, |