[llvm] [AMDGPU] Baseline gfx1250 speed model. (PR #145217)

[Stanislav Mekhanoshin via llvm-commits]

https://github.com/rampitec created https://github.com/llvm/llvm-project/pull/145217

None

>From da790561e81f18f9c7fd87a07f743d2f310708a3 Mon Sep 17 00:00:00 2001
From: Stanislav Mekhanoshin <Stanislav.Mekhanoshin at amd.com>
Date: Sun, 22 Jun 2025 00:33:40 -0700
Subject: [PATCH] [AMDGPU] Baseline gfx1250 speed model.

---
 llvm/lib/Target/AMDGPU/GCNProcessors.td |  2 +-
 llvm/lib/Target/AMDGPU/SISchedule.td    | 33 +++++++++++++++++++++++++
 2 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/llvm/lib/Target/AMDGPU/GCNProcessors.td b/llvm/lib/Target/AMDGPU/GCNProcessors.td
index 0b331bd3f3fb6..b5ffa64c3a4b4 100644
--- a/llvm/lib/Target/AMDGPU/GCNProcessors.td
+++ b/llvm/lib/Target/AMDGPU/GCNProcessors.td
@@ -326,6 +326,6 @@ def : ProcessorModel<"gfx12-generic", GFX12SpeedModel,
   FeatureISAVersion12_Generic.Features
 >;
 
-def : ProcessorModel<"gfx1250", GFX12SpeedModel,
+def : ProcessorModel<"gfx1250", GFX1250SpeedModel,
   FeatureISAVersion12_50.Features
 >;
diff --git a/llvm/lib/Target/AMDGPU/SISchedule.td b/llvm/lib/Target/AMDGPU/SISchedule.td
index 2a374b360b04a..1679cee320067 100644
--- a/llvm/lib/Target/AMDGPU/SISchedule.td
+++ b/llvm/lib/Target/AMDGPU/SISchedule.td
@@ -99,6 +99,7 @@ def SIDPGFX950FullSpeedModel : SISchedMachineModel;
 def GFX10SpeedModel : SISchedMachineModel;
 def GFX11SpeedModel : SISchedMachineModel;
 def GFX12SpeedModel : SISchedMachineModel;
+def GFX1250SpeedModel : SISchedMachineModel;
 
 // XXX: Are the resource counts correct?
 def HWBranch : ProcResource<1> {
@@ -455,3 +456,35 @@ def : HWWriteRes<WriteBarrier,           [HWBranch],       2000>;
 def : InstRW<[WriteCopy], (instrs COPY)>;
 
 }  // End SchedModel = GFX12SpeedModel
+
+multiclass GFX125xCommonWriteRes {
+
+def : HWWriteRes<Write32Bit,             [HWVALU, HWRC],   5>;
+def : HWWriteRes<WriteFloatCvt,          [HWVALU, HWRC],   5>;
+def : HWWriteRes<WriteTrans32,           [HWTransVALU, HWRC],   7>;
+def : HWWriteRes<WriteQuarterRate32,     [HWVALU, HWRC],   6>;
+def : HWWriteRes<WriteFloatFMA,          [HWVALU, HWRC],   5>;
+def : HWWriteRes<WritePseudoScalarTrans, [HWVALU, HWRC],   8>;
+
+def : HWWriteRes<WriteBranch,            [HWBranch],       32>;
+def : HWWriteRes<WriteExport,            [HWExport, HWRC], 16>;
+def : HWWriteRes<WriteLDS,               [HWLGKM,   HWRC], 20>;
+def : HWWriteRes<WriteSALU,              [HWSALU,   HWRC], 2>;
+def : HWWriteRes<WriteSFPU,              [HWSALU,   HWRC], 4>;
+def : HWWriteRes<WriteSMEM,              [HWLGKM,   HWRC], 20>;
+def : HWWriteRes<WriteVMEM,              [HWVMEM,   HWRC], 320>;
+def : HWWriteRes<WriteBarrier,           [HWBranch],       2000>;
+
+def : InstRW<[WriteCopy], (instrs COPY)>;
+} // End GFX125xCommonWriteRes
+
+let SchedModel = GFX1250SpeedModel in {
+defm : GFX125xCommonWriteRes;
+
+def : HWWriteRes<Write64Bit,             [HWVALU, HWRC],   7>;
+def : HWWriteRes<WriteIntMul,            [HWVALU, HWRC],   11>;
+def : HWWriteRes<WriteDouble,            [HWVALU, HWRC],   32>;
+def : HWWriteRes<WriteDoubleAdd,         [HWVALU, HWRC],   32>;
+def : HWWriteRes<WriteDoubleCvt,         [HWVALU, HWRC],   32>;
+def : HWWriteRes<WriteTrans64,           [HWVALU, HWTransVALU, HWRC], 38>;
+} // SchedModel = GFX1250SpeedModel