[X86] Swap ports 10 and 11 in SapphireRapids Scheduling Model #117468
+5,578
−5,581
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Based on intel/perfmon#149, the documentation is incorrect and the pfm counter names are actually correct. This patch adjusts the SapphireRapids scheduling model to match the performance counter naming/ correct naming that will soon be reflected in the optimization manual. This fixes part of llvm#117360.
|
@llvm/pr-subscribers-backend-x86 Author: Aiden Grossman (boomanaiden154) ChangesBased on intel/perfmon#149, the documentation is incorrect and the pfm counter names are actually correct. This patch adjusts the SapphireRapids scheduling model to match the performance counter naming/ correct naming that will soon be reflected in the optimization manual. This fixes part of #117360. Patch is 2.05 MiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/117468.diff 66 Files Affected:
diff --git a/llvm/lib/Target/X86/X86PfmCounters.td b/llvm/lib/Target/X86/X86PfmCounters.td
index 0c80f1eaadadb8..c15a2adc590f58 100644
--- a/llvm/lib/Target/X86/X86PfmCounters.td
+++ b/llvm/lib/Target/X86/X86PfmCounters.td
@@ -229,10 +229,7 @@ def SapphireRapidsPfmCounters : ProcPfmCounters {
let IssueCounters = [
PfmIssueCounter<"SPRPort00", "uops_dispatched:port_0">,
PfmIssueCounter<"SPRPort01", "uops_dispatched:port_1">,
- // The perfmon documentation and thus libpfm seems to incorrectly label
- // this performance counter, as ports 2,3, and 11 are actually grouped
- // according to most documentation. See #113941 for additional details.
- PfmIssueCounter<"SPRPort02_03_11", "uops_dispatched:port_2_3_10">,
+ PfmIssueCounter<"SPRPort02_03_10", "uops_dispatched:port_2_3_10">,
PfmIssueCounter<"SPRPort04_09", "uops_dispatched:port_4_9">,
PfmIssueCounter<"SPRPort05_11", "uops_dispatched:port_5_11">,
PfmIssueCounter<"SPRPort06", "uops_dispatched:port_6">,
diff --git a/llvm/lib/Target/X86/X86SchedSapphireRapids.td b/llvm/lib/Target/X86/X86SchedSapphireRapids.td
index 8a23d1b103aa6b..e04ff68d278b2b 100644
--- a/llvm/lib/Target/X86/X86SchedSapphireRapids.td
+++ b/llvm/lib/Target/X86/X86SchedSapphireRapids.td
@@ -56,15 +56,15 @@ def SPRPort00_05 : ProcResGroup<[SPRPort00, SPRPort05]>;
def SPRPort00_05_06 : ProcResGroup<[SPRPort00, SPRPort05, SPRPort06]>;
def SPRPort00_06 : ProcResGroup<[SPRPort00, SPRPort06]>;
def SPRPort01_05 : ProcResGroup<[SPRPort01, SPRPort05]>;
-def SPRPort01_05_10 : ProcResGroup<[SPRPort01, SPRPort05, SPRPort10]>;
+def SPRPort01_05_11 : ProcResGroup<[SPRPort01, SPRPort05, SPRPort11]>;
def SPRPort02_03 : ProcResGroup<[SPRPort02, SPRPort03]>;
-def SPRPort02_03_11 : ProcResGroup<[SPRPort02, SPRPort03, SPRPort11]>;
+def SPRPort02_03_10 : ProcResGroup<[SPRPort02, SPRPort03, SPRPort10]>;
def SPRPort05_11 : ProcResGroup<[SPRPort05, SPRPort11]>;
def SPRPort07_08 : ProcResGroup<[SPRPort07, SPRPort08]>;
// EU has 112 reservation stations.
-def SPRPort00_01_05_06_10 : ProcResGroup<[SPRPort00, SPRPort01, SPRPort05,
- SPRPort06, SPRPort10]> {
+def SPRPort00_01_05_06_11 : ProcResGroup<[SPRPort00, SPRPort01, SPRPort05,
+ SPRPort06, SPRPort11]> {
let BufferSize = 112;
}
@@ -74,8 +74,8 @@ def SPRPort04_09 : ProcResGroup<[SPRPort04, SPRPort09]> {
}
// MEM has 72 reservation stations.
-def SPRPort02_03_07_08_11 : ProcResGroup<[SPRPort02, SPRPort03, SPRPort07,
- SPRPort08, SPRPort11]> {
+def SPRPort02_03_07_08_10 : ProcResGroup<[SPRPort02, SPRPort03, SPRPort07,
+ SPRPort08, SPRPort10]> {
let BufferSize = 72;
}
@@ -113,7 +113,7 @@ multiclass SPRWriteResPair<X86FoldableSchedWrite SchedRW,
// Memory variant also uses a cycle on port 2/3/11 and adds LoadLat cycles to
// the latency (default = 5).
- def : WriteRes<SchedRW.Folded, !listconcat([SPRPort02_03_11], ExePorts)> {
+ def : WriteRes<SchedRW.Folded, !listconcat([SPRPort02_03_10], ExePorts)> {
let Latency = !add(Lat, LoadLat);
let ReleaseAtCycles = !listconcat([1], Res);
let NumMicroOps = !add(UOps, LoadUOps);
@@ -126,71 +126,71 @@ multiclass SPRWriteResPair<X86FoldableSchedWrite SchedRW,
// Infered SchedWrite definition.
def : WriteRes<WriteADC, [SPRPort00_06]>;
-defm : X86WriteRes<WriteADCLd, [SPRPort00_01_05_06_10, SPRPort00_06], 11, [1, 1], 2>;
+defm : X86WriteRes<WriteADCLd, [SPRPort00_01_05_06_11, SPRPort00_06], 11, [1, 1], 2>;
defm : SPRWriteResPair<WriteAESDecEnc, [SPRPort00_01], 5, [1], 1, 7>;
defm : SPRWriteResPair<WriteAESIMC, [SPRPort00_01], 8, [2], 2, 7>;
defm : X86WriteRes<WriteAESKeyGen, [SPRPort00, SPRPort00_01, SPRPort00_01_05, SPRPort00_06, SPRPort01_05, SPRPort05], 7, [4, 1, 1, 2, 3, 3], 14>;
-defm : X86WriteRes<WriteAESKeyGenLd, [SPRPort00, SPRPort00_01, SPRPort00_06, SPRPort01_05, SPRPort02_03_11, SPRPort05], 12, [4, 1, 2, 3, 1, 3], 14>;
-def : WriteRes<WriteALU, [SPRPort00_01_05_06_10]>;
-def : WriteRes<WriteALULd, [SPRPort00_01_05_06_10]> {
+defm : X86WriteRes<WriteAESKeyGenLd, [SPRPort00, SPRPort00_01, SPRPort00_06, SPRPort01_05, SPRPort02_03_10, SPRPort05], 12, [4, 1, 2, 3, 1, 3], 14>;
+def : WriteRes<WriteALU, [SPRPort00_01_05_06_11]>;
+def : WriteRes<WriteALULd, [SPRPort00_01_05_06_11]> {
let Latency = 11;
}
defm : SPRWriteResPair<WriteBEXTR, [SPRPort00_06, SPRPort01], 6, [1, 1], 2>;
-defm : SPRWriteResPair<WriteBLS, [SPRPort01_05_10], 2, [1]>;
+defm : SPRWriteResPair<WriteBLS, [SPRPort01_05_11], 2, [1]>;
defm : SPRWriteResPair<WriteBSF, [SPRPort01], 3, [1]>;
defm : SPRWriteResPair<WriteBSR, [SPRPort01], 3, [1]>;
def : WriteRes<WriteBSWAP32, [SPRPort01]>;
defm : X86WriteRes<WriteBSWAP64, [SPRPort00_06, SPRPort01], 2, [1, 1], 2>;
defm : SPRWriteResPair<WriteBZHI, [SPRPort01], 3, [1]>;
def : WriteRes<WriteBitTest, [SPRPort01]>;
-defm : X86WriteRes<WriteBitTestImmLd, [SPRPort01, SPRPort02_03_11], 6, [1, 1], 2>;
-defm : X86WriteRes<WriteBitTestRegLd, [SPRPort00_01_05_06_10, SPRPort00_06, SPRPort01, SPRPort01_05_10, SPRPort02_03_11], 11, [4, 2, 1, 2, 1], 10>;
+defm : X86WriteRes<WriteBitTestImmLd, [SPRPort01, SPRPort02_03_10], 6, [1, 1], 2>;
+defm : X86WriteRes<WriteBitTestRegLd, [SPRPort00_01_05_06_11, SPRPort00_06, SPRPort01, SPRPort01_05_11, SPRPort02_03_10], 11, [4, 2, 1, 2, 1], 10>;
def : WriteRes<WriteBitTestSet, [SPRPort01]>;
def : WriteRes<WriteBitTestSetImmLd, [SPRPort01]> {
let Latency = 11;
}
-defm : X86WriteRes<WriteBitTestSetRegLd, [SPRPort00_01_05_06_10, SPRPort00_06, SPRPort01, SPRPort01_05_10], 17, [3, 2, 1, 2], 8>;
+defm : X86WriteRes<WriteBitTestSetRegLd, [SPRPort00_01_05_06_11, SPRPort00_06, SPRPort01, SPRPort01_05_11], 17, [3, 2, 1, 2], 8>;
defm : SPRWriteResPair<WriteBlend, [SPRPort01_05], 1, [1], 1, 7>;
defm : SPRWriteResPair<WriteBlendY, [SPRPort00_01_05], 1, [1], 1, 8>;
defm : SPRWriteResPair<WriteCLMul, [SPRPort05], 3, [1], 1, 7>;
defm : SPRWriteResPair<WriteCMOV, [SPRPort00_06], 1, [1], 1, 6>;
-defm : X86WriteRes<WriteCMPXCHG, [SPRPort00_01_05_06_10, SPRPort00_06], 3, [3, 2], 5>;
-defm : X86WriteRes<WriteCMPXCHGRMW, [SPRPort00_01_05_06_10, SPRPort00_06, SPRPort02_03_11, SPRPort04_09, SPRPort07_08], 12, [1, 2, 1, 1, 1], 6>;
+defm : X86WriteRes<WriteCMPXCHG, [SPRPort00_01_05_06_11, SPRPort00_06], 3, [3, 2], 5>;
+defm : X86WriteRes<WriteCMPXCHGRMW, [SPRPort00_01_05_06_11, SPRPort00_06, SPRPort02_03_10, SPRPort04_09, SPRPort07_08], 12, [1, 2, 1, 1, 1], 6>;
defm : SPRWriteResPair<WriteCRC32, [SPRPort01], 3, [1]>;
defm : X86WriteRes<WriteCvtI2PD, [SPRPort00_01, SPRPort05], 5, [1, 1], 2>;
-defm : X86WriteRes<WriteCvtI2PDLd, [SPRPort00_01, SPRPort02_03_11], 11, [1, 1], 2>;
+defm : X86WriteRes<WriteCvtI2PDLd, [SPRPort00_01, SPRPort02_03_10], 11, [1, 1], 2>;
defm : X86WriteRes<WriteCvtI2PDY, [SPRPort00_01, SPRPort05], 7, [1, 1], 2>;
-defm : X86WriteRes<WriteCvtI2PDYLd, [SPRPort00_01, SPRPort02_03_11], 12, [1, 1], 2>;
+defm : X86WriteRes<WriteCvtI2PDYLd, [SPRPort00_01, SPRPort02_03_10], 12, [1, 1], 2>;
defm : SPRWriteResPair<WriteCvtI2PDZ, [SPRPort00], 4, [1], 1, 8>;
defm : SPRWriteResPair<WriteCvtI2PS, [SPRPort00_01], 4, [1], 1, 7>;
defm : SPRWriteResPair<WriteCvtI2PSY, [SPRPort00_01], 4, [1], 1, 8>;
defm : SPRWriteResPair<WriteCvtI2PSZ, [SPRPort00], 4, [1], 1, 8>;
defm : X86WriteRes<WriteCvtI2SD, [SPRPort00_01, SPRPort05], 7, [1, 1], 2>;
-defm : X86WriteRes<WriteCvtI2SDLd, [SPRPort00_01, SPRPort02_03_11], 11, [1, 1], 2>;
+defm : X86WriteRes<WriteCvtI2SDLd, [SPRPort00_01, SPRPort02_03_10], 11, [1, 1], 2>;
defm : X86WriteRes<WriteCvtI2SS, [SPRPort00_01, SPRPort00_01_05, SPRPort05], 9, [1, 1, 1], 3>;
-defm : X86WriteRes<WriteCvtI2SSLd, [SPRPort00_01, SPRPort02_03_11], 11, [1, 1], 2>;
+defm : X86WriteRes<WriteCvtI2SSLd, [SPRPort00_01, SPRPort02_03_10], 11, [1, 1], 2>;
defm : X86WriteRes<WriteCvtPD2I, [SPRPort00_01, SPRPort05], 5, [1, 1], 2>;
-defm : X86WriteRes<WriteCvtPD2ILd, [SPRPort00_01, SPRPort02_03_11], 12, [1, 1], 2>;
+defm : X86WriteRes<WriteCvtPD2ILd, [SPRPort00_01, SPRPort02_03_10], 12, [1, 1], 2>;
defm : X86WriteRes<WriteCvtPD2IY, [SPRPort00_01, SPRPort05], 7, [1, 1], 2>;
-defm : X86WriteRes<WriteCvtPD2IYLd, [SPRPort00_01, SPRPort02_03_11], 12, [1, 1], 2>;
+defm : X86WriteRes<WriteCvtPD2IYLd, [SPRPort00_01, SPRPort02_03_10], 12, [1, 1], 2>;
defm : X86WriteRes<WriteCvtPD2IZ, [SPRPort00, SPRPort05], 7, [1, 1], 2>;
-defm : X86WriteRes<WriteCvtPD2IZLd, [SPRPort00, SPRPort02_03_11], 12, [1, 1], 2>;
+defm : X86WriteRes<WriteCvtPD2IZLd, [SPRPort00, SPRPort02_03_10], 12, [1, 1], 2>;
defm : SPRWriteResPair<WriteCvtPD2PS, [SPRPort00_01, SPRPort05], 5, [1, 1], 2, 7>;
defm : SPRWriteResPair<WriteCvtPD2PSY, [SPRPort00_01, SPRPort05], 7, [1, 1], 2, 8>;
defm : SPRWriteResPair<WriteCvtPD2PSZ, [SPRPort00, SPRPort05], 7, [1, 1], 2, 8>;
defm : X86WriteRes<WriteCvtPH2PS, [SPRPort00_01, SPRPort05], 6, [1, 1], 2>;
-defm : X86WriteRes<WriteCvtPH2PSLd, [SPRPort00_01, SPRPort02_03_11], 12, [1, 1], 2>;
+defm : X86WriteRes<WriteCvtPH2PSLd, [SPRPort00_01, SPRPort02_03_10], 12, [1, 1], 2>;
defm : X86WriteRes<WriteCvtPH2PSY, [SPRPort00_01, SPRPort05], 8, [1, 1], 2>;
-defm : X86WriteRes<WriteCvtPH2PSYLd, [SPRPort00_01, SPRPort02_03_11], 12, [1, 1], 2>;
+defm : X86WriteRes<WriteCvtPH2PSYLd, [SPRPort00_01, SPRPort02_03_10], 12, [1, 1], 2>;
defm : SPRWriteResPair<WriteCvtPH2PSZ, [SPRPort00, SPRPort05], 11, [1, 1], 2>;
defm : SPRWriteResPair<WriteCvtPS2I, [SPRPort00_01], 4, [1], 1, 7>;
defm : SPRWriteResPair<WriteCvtPS2IY, [SPRPort00_01], 4, [1], 1, 8>;
defm : X86WriteRes<WriteCvtPS2IZ, [SPRPort00, SPRPort00_05, SPRPort05], 10, [1, 2, 1], 4>;
-defm : X86WriteRes<WriteCvtPS2IZLd, [SPRPort00, SPRPort00_05, SPRPort00_06, SPRPort02_03_11, SPRPort05], 18, [1, 2, 1, 1, 1], 6>;
+defm : X86WriteRes<WriteCvtPS2IZLd, [SPRPort00, SPRPort00_05, SPRPort00_06, SPRPort02_03_10, SPRPort05], 18, [1, 2, 1, 1, 1], 6>;
defm : X86WriteRes<WriteCvtPS2PD, [SPRPort00_01, SPRPort05], 5, [1, 1], 2>;
-defm : X86WriteRes<WriteCvtPS2PDLd, [SPRPort00_01, SPRPort02_03_11], 11, [1, 1], 2>;
+defm : X86WriteRes<WriteCvtPS2PDLd, [SPRPort00_01, SPRPort02_03_10], 11, [1, 1], 2>;
defm : X86WriteRes<WriteCvtPS2PDY, [SPRPort00_01, SPRPort05], 7, [1, 1], 2>;
-defm : X86WriteRes<WriteCvtPS2PDYLd, [SPRPort00_01, SPRPort02_03_11], 12, [1, 1], 2>;
+defm : X86WriteRes<WriteCvtPS2PDYLd, [SPRPort00_01, SPRPort02_03_10], 12, [1, 1], 2>;
defm : SPRWriteResPair<WriteCvtPS2PDZ, [SPRPort00, SPRPort05], 7, [1, 1], 2, 6>;
defm : X86WriteRes<WriteCvtPS2PH, [SPRPort00_01, SPRPort05], 6, [1, 1], 2>;
defm : X86WriteRes<WriteCvtPS2PHSt, [SPRPort00_01, SPRPort04_09, SPRPort07_08], 12, [1, 1, 1], 3>;
@@ -202,12 +202,12 @@ defm : SPRWriteResPair<WriteCvtSD2I, [SPRPort00, SPRPort00_01], 7, [1, 1], 2>;
defm : SPRWriteResPair<WriteCvtSD2SS, [SPRPort00_01, SPRPort05], 5, [1, 1], 2, 7>;
defm : SPRWriteResPair<WriteCvtSS2I, [SPRPort00, SPRPort00_01], 7, [1, 1], 2>;
defm : X86WriteRes<WriteCvtSS2SD, [SPRPort00_01, SPRPort05], 5, [1, 1], 2>;
-defm : X86WriteRes<WriteCvtSS2SDLd, [SPRPort00_01, SPRPort02_03_11], 11, [1, 1], 2>;
+defm : X86WriteRes<WriteCvtSS2SDLd, [SPRPort00_01, SPRPort02_03_10], 11, [1, 1], 2>;
defm : SPRWriteResPair<WriteDPPD, [SPRPort00_01, SPRPort01_05], 9, [2, 1], 3, 7>;
defm : SPRWriteResPair<WriteDPPS, [SPRPort00_01, SPRPort00_06, SPRPort01_05, SPRPort05], 14, [2, 1, 2, 1], 6, 7>;
defm : SPRWriteResPair<WriteDPPSY, [SPRPort00_01, SPRPort00_06, SPRPort01_05, SPRPort05], 14, [2, 1, 2, 1], 6, 8>;
-defm : SPRWriteResPair<WriteDiv16, [SPRPort00_01_05_06_10, SPRPort01], 16, [1, 3], 4, 4>;
-defm : SPRWriteResPair<WriteDiv32, [SPRPort00_01_05_06_10, SPRPort01], 15, [1, 3], 4, 4>;
+defm : SPRWriteResPair<WriteDiv16, [SPRPort00_01_05_06_11, SPRPort01], 16, [1, 3], 4, 4>;
+defm : SPRWriteResPair<WriteDiv32, [SPRPort00_01_05_06_11, SPRPort01], 15, [1, 3], 4, 4>;
defm : SPRWriteResPair<WriteDiv64, [SPRPort01], 18, [3], 3>;
defm : X86WriteRes<WriteDiv8, [SPRPort01], 17, [3], 3>;
defm : X86WriteRes<WriteDiv8Ld, [SPRPort01], 22, [3], 3>;
@@ -235,7 +235,7 @@ defm : SPRWriteResPair<WriteFCmpY, [SPRPort00_01], 4, [1], 1, 8>;
def : WriteRes<WriteFCmpZ, [SPRPort05]> {
let Latency = 3;
}
-defm : X86WriteRes<WriteFCmpZLd, [SPRPort00, SPRPort02_03_11], 12, [1, 1], 2>;
+defm : X86WriteRes<WriteFCmpZLd, [SPRPort00, SPRPort02_03_10], 12, [1, 1], 2>;
defm : SPRWriteResPair<WriteFCom, [SPRPort05], 1, [1], 1, 7>;
defm : SPRWriteResPair<WriteFComX, [SPRPort00], 3, [1]>;
defm : SPRWriteResPair<WriteFDiv, [SPRPort00], 11, [1], 1, 7>;
@@ -251,13 +251,13 @@ defm : SPRWriteResPair<WriteFHAddY, [SPRPort01_05, SPRPort05], 5, [1, 2], 3, 8>;
def : WriteRes<WriteFLD0, [SPRPort00_05]>;
defm : X86WriteRes<WriteFLD1, [SPRPort00_05], 1, [2], 2>;
defm : X86WriteRes<WriteFLDC, [SPRPort00_05], 1, [2], 2>;
-def : WriteRes<WriteFLoad, [SPRPort02_03_11]> {
+def : WriteRes<WriteFLoad, [SPRPort02_03_10]> {
let Latency = 7;
}
-def : WriteRes<WriteFLoadX, [SPRPort02_03_11]> {
+def : WriteRes<WriteFLoadX, [SPRPort02_03_10]> {
let Latency = 7;
}
-def : WriteRes<WriteFLoadY, [SPRPort02_03_11]> {
+def : WriteRes<WriteFLoadY, [SPRPort02_03_10]> {
let Latency = 8;
}
defm : SPRWriteResPair<WriteFLogic, [SPRPort00_01_05], 1, [1], 1, 7>;
@@ -270,8 +270,8 @@ defm : SPRWriteResPair<WriteFMAZ, [SPRPort00], 4, [1], 1, 8>;
def : WriteRes<WriteFMOVMSK, [SPRPort00]> {
let Latency = 3;
}
-defm : X86WriteRes<WriteFMaskedLoad, [SPRPort00_01_05, SPRPort02_03_11], 8, [1, 1], 2>;
-defm : X86WriteRes<WriteFMaskedLoadY, [SPRPort00_01_05, SPRPort02_03_11], 9, [1, 1], 2>;
+defm : X86WriteRes<WriteFMaskedLoad, [SPRPort00_01_05, SPRPort02_03_10], 8, [1, 1], 2>;
+defm : X86WriteRes<WriteFMaskedLoadY, [SPRPort00_01_05, SPRPort02_03_10], 9, [1, 1], 2>;
defm : X86WriteRes<WriteFMaskedStore32, [SPRPort00, SPRPort04_09, SPRPort07_08], 14, [1, 1, 1], 3>;
defm : X86WriteRes<WriteFMaskedStore32Y, [SPRPort00, SPRPort04_09, SPRPort07_08], 14, [1, 1, 1], 3>;
defm : X86WriteRes<WriteFMaskedStore64, [SPRPort00, SPRPort04_09, SPRPort07_08], 14, [1, 1, 1], 3>;
@@ -334,15 +334,15 @@ defm : SPRWriteResPair<WriteFVarShuffleZ, [SPRPort05], 1, [1], 1, 8>;
def : WriteRes<WriteFence, [SPRPort00_06]> {
let Latency = 2;
}
-defm : SPRWriteResPair<WriteIDiv16, [SPRPort00_01_05_06_10, SPRPort01], 16, [1, 3], 4, 4>;
-defm : SPRWriteResPair<WriteIDiv32, [SPRPort00_01_05_06_10, SPRPort01], 15, [1, 3], 4, 4>;
+defm : SPRWriteResPair<WriteIDiv16, [SPRPort00_01_05_06_11, SPRPort01], 16, [1, 3], 4, 4>;
+defm : SPRWriteResPair<WriteIDiv32, [SPRPort00_01_05_06_11, SPRPort01], 15, [1, 3], 4, 4>;
defm : SPRWriteResPair<WriteIDiv64, [SPRPort01], 18, [3], 3>;
defm : X86WriteRes<WriteIDiv8, [SPRPort01], 17, [3], 3>;
defm : X86WriteRes<WriteIDiv8Ld, [SPRPort01], 22, [3], 3>;
-defm : SPRWriteResPair<WriteIMul16, [SPRPort00_01_05_06_10, SPRPort00_06, SPRPort01], 5, [2, 1, 1], 4>;
-defm : SPRWriteResPair<WriteIMul16Imm, [SPRPort00_01_05_06_10, SPRPort01], 4, [1, 1], 2>;
+defm : SPRWriteResPair<WriteIMul16, [SPRPort00_01_05_06_11, SPRPort00_06, SPRPort01], 5, [2, 1, 1], 4>;
+defm : SPRWriteResPair<WriteIMul16Imm, [SPRPort00_01_05_06_11, SPRPort01], 4, [1, 1], 2>;
defm : SPRWriteResPair<WriteIMul16Reg, [SPRPort01], 3, [1]>;
-defm : SPRWriteResPair<WriteIMul32, [SPRPort00_01_05_06_10, SPRPort00_06, SPRPort01], 4, [1, 1, 1], 3>;
+defm : SPRWriteResPair<WriteIMul32, [SPRPort00_01_05_06_11, SPRPort00_06, SPRPort01], 4, [1, 1, 1], 3>;
defm : SPRWriteResPair<WriteIMul32Imm, [SPRPort01], 3, [1]>;
defm : SPRWriteResPair<WriteIMul32Reg, [SPRPort01], 3, [1]>;
defm : SPRWriteResPair<WriteIMul64, [SPRPort01, SPRPort05], 4, [1, 1], 2>;
@@ -359,10 +359,10 @@ defm : SPRWriteResPair<WriteJump, [SPRPort00_06], 1, [1]>;
def : WriteRes<WriteLAHFSAHF, [SPRPort00_06]> {
let Latency = 3;
}
-defm : X86WriteRes<WriteLDMXCSR, [SPRPort00, SPRPort00_01_05, SPRPort00_06, SPRPort02_03_11], 7, [1, 1, 1, 1], 4>;
+defm : X86WriteRes<WriteLDMXCSR, [SPRPort00, SPRPort00_01_05, SPRPort00_06, SPRPort02_03_10], 7, [1, 1, 1, 1], 4>;
def : WriteRes<WriteLEA, [SPRPort01]>;
defm : SPRWriteResPair<WriteLZCNT, [SPRPort01], 3, [1]>;
-def : WriteRes<WriteLoad, [SPRPort02_03_11]> {
+def : WriteRes<WriteLoad, [SPRPort02_03_10]> {
let Latency = 5;
}
def : WriteRes<WriteMMXMOVMSK, [SPRPort00]> {
@@ -370,7 +370,7 @@ def : WriteRes<WriteMMXMOVMSK, [SPRPort00]> {
}
defm : SPRWriteResPair<WriteMPSAD, [SPRPort01_05, SPRPort05], 4, [1, 1], 2, 7>;
defm : SPRWriteResPair<WriteMPSADY, [SPRPort01_05, SPRPort05], 4, [1, 1], 2, 8>;
-defm : SPRWriteResPair<WriteMULX32, [SPRPort00_01_05_06_10, SPRPort00_06, SPRPort01], 4, [1, 1, 1], 2>;
+defm : SPRWriteResPair<WriteMULX32, [SPRPort00_01_05_06_11, SPRPort00_06, SPRPort01], 4, [1, 1, 1], 2>;
defm : SPRWriteResPair<WriteMULX64, [SPRPort01, SPRPort05], 4, [1, 1]>;
def : WriteRes<WriteMicrocoded, [SPRPort00_01_05_06]> {
let Latency = SapphireRapidsModel.MaxLatency;
@@ -380,9 +380,9 @@ def : WriteRes<WriteMove, [SPRPort00]> {
}
defm : X86WriteRes<WriteNop, [], 1, [], 0>;
defm : X86WriteRes<WritePCmpEStrI, [SPRPort00, SPRPort00_01_05, SPRPort00_06, SPRPort01, SPRPort05], 16, [3, 2, 1, 1, 1], 8>;
-defm : X86WriteRes<WritePCmpEStrILd, [SPRPort00, SPRPort00_01_05, SPRPort00_06, SPRPort01, SPRPort02_03_11, SPRPort05], 31, [3, 1, 1, 1, 1, 1], 8>;
+defm : X86WriteRes<WritePCmpEStrILd, [SPRPort00, SPRPort00_01_05, SPRPort00_06, SPRPort01, SPRPort02_03_10, SPRPort05], 31, [3, 1, 1, 1, 1, 1], 8>;
defm : X86WriteRes<WritePCmpEStrM, [SPRPort00, SPRPort00_01_05, SPRPort00_06, SPRPort01, SPRPort05], 16, [3, 3, 1, 1, 1], 9>;
-defm : X86WriteRes<WritePCmpEStrMLd, [SPRPort00, SPRPort00_01_05, SPRPort00_06, SPRPort01, SPRPort02_03_11, SPRPort05], 17, [3, 2, 1, 1, 1, 1], 9>;
+defm : X86WriteRes<WritePCmpEStrMLd, [SPRPort00, SPRPort00_01_05, SPRPort00_06, SPRPort01, SPRPort02_03_10, SPRPort05], 17, [3, 2, 1, 1, 1, 1], 9>;
defm : SPRWriteResPair<WritePCmpIStrI, [SPRPort00], 11, [3], 3, 20>;
defm : SPRWriteResPair<WritePCmpIStrM, [SPRPort00], 11, [3], 3>;
defm : SPRWriteResPair<WritePHAdd, [SPRPort00_05, SPRPort05], 3, [1, 2], 3, 8>;
@@ -397,16 +397,16 @@ defm : SPRWriteResPair<WritePSADBW, [SPRPort05], 3, [1], 1, 8>;
defm : SPRWriteResPair<WritePSADBWX, [SPRPort05], 3, [1], 1, 7>;
defm : SPRWriteResPair<WritePSADBWY, [SPRPort05], 3, [1], 1, 8>;
defm : SPRWriteResPair<WritePSADBWZ, [SPRPort05], 3, [1], 1, 8>;
-defm : X86WriteRes<WriteRMW, [SPRPort02_03_11, SPRPort04_09, SPRPort07_08], 1, [1, 1, 1], 3>;
-defm : X86WriteRes<WriteRotate, [SPRPort00_01_05_06_10, SPRPort00_06], 2, [1, 2], 3>;
-defm : X86WriteRes<WriteRotateLd, [SPRPort00_01_05_06_10, SPRPort00_06], 12, [1, 2], 3>;
+defm : X86WriteRes<WriteRMW, [SPRPort02_03_10, SPRPort04_09, SPRPort07_08], 1, [1, 1, 1], 3>;
+defm : X86WriteRes<WriteRotate, [SPRPort00_01_05_06_11, SPRPort00_06], 2, [1, 2], 3>;
+defm : X86WriteRes<WriteRotateLd, [SPRPort00_01_05_06_11, SPRPort00_06], 12, [1, 2], 3>;
defm : X86WriteRes<WriteRotateCL, [SPRPort00_06], 2, [2], 2>;
-defm : X86WriteRes<WriteRotateCLLd, [SPRPort00_01_05_06_10, SPRPort00_06, SPRPort01], 19, [2, 3, 2], 7>;
+defm : X86WriteRes<WriteRotateCLLd, [SPRPort00_01_05_06_11, SPRPort00_06, SPRPort01], 19, [2, 3, 2], 7>;
defm : X86WriteRes<WriteSETCC, [SPRPort00_06], 2, [2], 2>;
defm : X86WriteRes<WriteSETCCStore, [SPRPort00_06, SPRPort04_09, SPRPort07_08], 13, [2, 1, 1], 4>;
-defm : X86WriteRes<WriteSHDmrcl, [SPRPort00_01_05_06_10, SPRPort00_06, SPRPort01, SPRPort02_03_11, SPRPort04_09, SPRPort07_08], 12, [1, 1, 1, 1, 1, 1], 6>;
-defm : X86WriteRes<WriteSHDmri, [SPRPort00_01_05_06_10, SPRPort01, SPRPort02_03_11, SPRPort04_09, SPRPort07_08], 12, [1, 1, 1, 1, 1], 5>;
-defm : X86WriteRes<WriteSHDrrcl, [SPRPort00_01_05_06_10, SPRPort00_06, SPRPort01], 5, [1, 1, 1], 3>;
+defm : X86WriteRes<WriteSHDmrcl, [SPRPort00_01_05_06_11, SPRPort00_06, SPRPort01, SPRPort02_03_10, SPRPort04_09, SPRPort07_08], 12, [1, 1, 1, 1, 1, 1], 6>;
+defm : X86WriteRes<WriteSHDmri, [SPRPort00_01_05_06_11, SPRPort01, SPRPort02_03_10, SPRPort04_09, SPRPort07_08], 12, [1, 1, 1, 1, 1], 5>;
+defm : X86WriteRes<WriteSHDrrcl, [SPRPort00_01_05_06_11, SPRPort00_06, SPRPort01], 5, [1, 1, 1], 3>;
def : WriteRes<WriteSHDrri, [SPRPort01]> {
let Latency = 3;
}
@@ -434,7 +434,7 @@ defm : SPRWriteResPair<WriteVarBlendY, [SPRPort00_01_05], 1, [1], 1, 8>;
defm : SPRWriteResPair<WriteVarBlendZ, [SPRPort00_05], 1, [...
[truncated]
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Based on intel/perfmon#149, the documentation is incorrect and the pfm counter names are actually correct. This patch adjusts the SapphireRapids scheduling model to match the performance counter naming/ correct naming that will soon be reflected in the optimization manual.
This fixes part of #117360.