arch-gcn3: Update LmReqsInPipe in atomic flats when execMask=0

In flat instructions, wrLmReqsInPipe/rdLmReqsInPipe are decremented
in the calcAddr() function. However, the calcAddr() function is only
called when execMask != 0.

This patch adds in statements to decrement wrLmReqsInPipe and
rdLmReqsInPipe in all implemented atomic flats when execMask is 0.

This fixes a scenario where vector local memory and flat instructions
are unable to execute due to LocalMemPipeline::isLMReqFIFOWrRdy
always returning false in ScheduleStage::dispatchReady after too many
atomic flats execute with execMask = 0

Change-Id: I081cfd3faf74bbfcf0728445e7160fa2a76a6a7e
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/32614
Reviewed-by: Matt Sinclair <mattdsinclair@gmail.com>
Reviewed-by: Alexandru Duțu <alexandru.dutu@amd.com>
Maintainer: Anthony Gutierrez <anthony.gutierrez@amd.com>
Tested-by: kokoro <noreply+kokoro@google.com>

diff --git a/src/arch/gcn3/insts/instructions.cc b/src/arch/gcn3/insts/instructions.cc
index fd89ae291c2688df8203df2c12947552201e640d..296dbadf1beb8109811d1a59ca3950db07a1b181 100644 (file)
--- a/src/arch/gcn3/insts/instructions.cc
+++ b/src/arch/gcn3/insts/instructions.cc
@@ -40374,6 +40374,8 @@ namespace Gcn3ISA
             wf->decLGKMInstsIssued();
             wf->wrGmReqsInPipe--;
             wf->rdGmReqsInPipe--;
+            wf->wrLmReqsInPipe--;
+            wf->rdLmReqsInPipe--;
             if (instData.GLC) {
                 gpuDynInst->exec_mask = wf->execMask();
                 wf->computeUnit->vrf[wf->simdId]->
@@ -40481,6 +40483,8 @@ namespace Gcn3ISA
             wf->decLGKMInstsIssued();
             wf->wrGmReqsInPipe--;
             wf->rdGmReqsInPipe--;
+            wf->wrLmReqsInPipe--;
+            wf->rdLmReqsInPipe--;
             if (instData.GLC) {
                 gpuDynInst->exec_mask = wf->execMask();
                 wf->computeUnit->vrf[wf->simdId]->
@@ -40589,6 +40593,8 @@ namespace Gcn3ISA
             wf->decLGKMInstsIssued();
             wf->wrGmReqsInPipe--;
             wf->rdGmReqsInPipe--;
+            wf->wrLmReqsInPipe--;
+            wf->rdLmReqsInPipe--;
             if (instData.GLC) {
                 gpuDynInst->exec_mask = wf->execMask();
                 wf->computeUnit->vrf[wf->simdId]->
@@ -40684,6 +40690,8 @@ namespace Gcn3ISA
             wf->decLGKMInstsIssued();
             wf->wrGmReqsInPipe--;
             wf->rdGmReqsInPipe--;
+            wf->wrLmReqsInPipe--;
+            wf->rdLmReqsInPipe--;
             if (instData.GLC) {
                 gpuDynInst->exec_mask = wf->execMask();
                 wf->computeUnit->vrf[wf->simdId]->
@@ -40953,6 +40961,8 @@ namespace Gcn3ISA
             wf->decLGKMInstsIssued();
             wf->wrGmReqsInPipe--;
             wf->rdGmReqsInPipe--;
+            wf->wrLmReqsInPipe--;
+            wf->rdLmReqsInPipe--;
             if (instData.GLC) {
                 gpuDynInst->exec_mask = wf->execMask();
                 wf->computeUnit->vrf[wf->simdId]->
@@ -41048,6 +41058,8 @@ namespace Gcn3ISA
             wf->decLGKMInstsIssued();
             wf->wrGmReqsInPipe--;
             wf->rdGmReqsInPipe--;
+            wf->wrLmReqsInPipe--;
+            wf->rdLmReqsInPipe--;
             if (instData.GLC) {
                 gpuDynInst->exec_mask = wf->execMask();
                 wf->computeUnit->vrf[wf->simdId]->
@@ -41172,6 +41184,8 @@ namespace Gcn3ISA
             wf->decLGKMInstsIssued();
             wf->wrGmReqsInPipe--;
             wf->rdGmReqsInPipe--;
+            wf->wrLmReqsInPipe--;
+            wf->rdLmReqsInPipe--;
             if (instData.GLC) {
                 gpuDynInst->exec_mask = wf->execMask();
                 wf->computeUnit->vrf[wf->simdId]->
@@ -41281,6 +41295,8 @@ namespace Gcn3ISA
             wf->decLGKMInstsIssued();
             wf->wrGmReqsInPipe--;
             wf->rdGmReqsInPipe--;
+            wf->wrLmReqsInPipe--;
+            wf->rdLmReqsInPipe--;
             if (instData.GLC) {
                 gpuDynInst->exec_mask = wf->execMask();
                 wf->computeUnit->vrf[wf->simdId]->
@@ -41378,6 +41394,8 @@ namespace Gcn3ISA
             wf->decLGKMInstsIssued();
             wf->wrGmReqsInPipe--;
             wf->rdGmReqsInPipe--;
+            wf->wrLmReqsInPipe--;
+            wf->rdLmReqsInPipe--;
             if (instData.GLC) {
                 gpuDynInst->exec_mask = wf->execMask();
                 wf->computeUnit->vrf[wf->simdId]->
@@ -41657,6 +41675,8 @@ namespace Gcn3ISA
             wf->decLGKMInstsIssued();
             wf->wrGmReqsInPipe--;
             wf->rdGmReqsInPipe--;
+            wf->wrLmReqsInPipe--;
+            wf->rdLmReqsInPipe--;
             if (instData.GLC) {
                 gpuDynInst->exec_mask = wf->execMask();
                 wf->computeUnit->vrf[wf->simdId]->
@@ -41755,6 +41775,8 @@ namespace Gcn3ISA
             wf->decLGKMInstsIssued();
             wf->wrGmReqsInPipe--;
             wf->rdGmReqsInPipe--;
+            wf->wrLmReqsInPipe--;
+            wf->rdLmReqsInPipe--;
             if (instData.GLC) {
                 gpuDynInst->exec_mask = wf->execMask();
                 wf->computeUnit->vrf[wf->simdId]->