[llvm] [RISCV] Add scheduling model for SiFive P800 processors (PR #139316)

[Pengcheng Wang via llvm-commits]

================
@@ -0,0 +1,1185 @@
+//==- RISCVSchedSiFiveP800.td - SiFiveP800 Scheduling Defs ---*- tablegen -*-=//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+//===----------------------------------------------------------------------===//
+
+/// c is true if mx has the worst case behavior compared to LMULs in MxList.
+/// On the SiFiveP800, the worst case LMUL is the Largest LMUL
+/// and the worst case sew is the smallest SEW for that LMUL.
+class SiFiveP800IsWorstCaseMX<string mx, list<string> MxList> {
+  string LLMUL = LargestLMUL<MxList>.r;
+  bit c = !eq(mx, LLMUL);
+}
+
+class SiFiveP800IsWorstCaseMXSEW<string mx, int sew, list<string> MxList, bit isF = 0> {
+  string LLMUL = LargestLMUL<MxList>.r;
+  int SSEW = SmallestSEW<mx, isF>.r;
+  bit c = !and(!eq(mx, LLMUL), !eq(sew, SSEW));
+}
+
+// 1 Micro-Op per cycle.
+class SiFiveP800GetLMulCycles<string mx> {
+  int c = !cond(
+    !eq(mx, "M1") : 1,
+    !eq(mx, "M2") : 2,
+    !eq(mx, "M4") : 4,
+    !eq(mx, "M8") : 8,
+    !eq(mx, "MF2") : 1,
+    !eq(mx, "MF4") : 1,
+    !eq(mx, "MF8") : 1
+  );
+}
+
+// Latency for segmented loads and stores are calculated as vl.
+class SiFiveP800GetCyclesSegmented<string mx, int sew> {
+  defvar VLEN = 128;
+  int c = !cond(
+    !eq(mx, "M1") : !div(VLEN, sew),
+    !eq(mx, "M2") : !div(!mul(VLEN, 2), sew),
+    !eq(mx, "M4") : !div(!mul(VLEN, 4), sew),
+    !eq(mx, "M8") : !div(!mul(VLEN, 8), sew),
+    !eq(mx, "MF2") : !div(!div(VLEN, 2), sew),
+    !eq(mx, "MF4") : !div(!div(VLEN, 4), sew),
+    !eq(mx, "MF8") : !div(!div(VLEN, 8), sew),
+  );
+}
+
+class SiFiveP800VSM3CCycles<string mx> {
+  // c = ceil(LMUL / 2)
+  int c = !cond(!eq(mx, "M2") : 1,
+                !eq(mx, "M4") : 2,
+                !eq(mx, "M8") : 4,
+                true : 1);
+}
+
+// SiFiveP800 machine model for scheduling and other instruction cost heuristics.
+def SiFiveP800Model : SchedMachineModel {
+  let IssueWidth = 6;          // 6 micro-ops are dispatched per cycle.
+  let MicroOpBufferSize = 288; // Max micro-ops that can be buffered.
+  let LoadLatency = 4;         // Cycles for loads to access the cache.
+  let MispredictPenalty = 9;   // Extra cycles for a mispredicted branch.
+  let UnsupportedFeatures = [HasStdExtZbkb, HasStdExtZbkc, HasStdExtZbkx,
+                             HasStdExtZknd, HasStdExtZkne, HasStdExtZknh,
+                             HasStdExtZksed, HasStdExtZksh, HasStdExtZkr,
+                             HasVendorXSfvqmaccqoq, HasVendorXSfvqmaccdod];
+  let CompleteModel = false;
+}
+
+let SchedModel = SiFiveP800Model in {
+
+def SiFiveP800IEXQ0       : ProcResource<1>;
----------------
wangpc-pp wrote:

It seems each unit has it own buffer (for example, 32 entries for load/store), should we model that?

https://github.com/llvm/llvm-project/pull/139316