[llvm] [X86] Fix some values for Znver4 model (PR #161405)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Sep 30 10:08:36 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-x86
Author: None (NexusXe)
<details>
<summary>Changes</summary>
This PR fixes a handful of latency and uop changes between Znver3 and Znver4 that were otherwise copied from Znver3.
Latency and uop values listed that matched Zen3 on uops.info were updated to those for Zen4.
---
Full diff: https://github.com/llvm/llvm-project/pull/161405.diff
1 Files Affected:
- (modified) llvm/lib/Target/X86/X86ScheduleZnver4.td (+40-39)
``````````diff
diff --git a/llvm/lib/Target/X86/X86ScheduleZnver4.td b/llvm/lib/Target/X86/X86ScheduleZnver4.td
index cc300548a50e6..405c0a2e9fbd1 100644
--- a/llvm/lib/Target/X86/X86ScheduleZnver4.td
+++ b/llvm/lib/Target/X86/X86ScheduleZnver4.td
@@ -15,7 +15,7 @@
//===----------------------------------------------------------------------===//
def Znver4Model : SchedMachineModel {
- // AMD SOG Zen4, 2.9.6 Dispatch
+ // AMD SOG Zen4, 2.9.8 Dispatch
// The processor may dispatch up to 6 macro ops per cycle
// into the execution engine.
let IssueWidth = 6;
@@ -46,8 +46,9 @@ def Znver4Model : SchedMachineModel {
int VecLoadLatency = 7;
// Latency of a simple store operation.
int StoreLatency = 1;
- // FIXME:
- let HighLatency = 25; // FIXME: any better choice?
+ // Mean and median value for all instructions with latencies >6
+ // Source: Zen4 Instruction Latencies spreadsheet (included with SOG)
+ let HighLatency = 13;
// AMD SOG Zen4, 2.8 Optimizing Branching
// The branch misprediction penalty is in the range from 11 to 18 cycles,
// <...>. The common case penalty is 13 cycles.
@@ -585,10 +586,11 @@ def : InstRW<[Zn4WriteADC8mr_SBB8mr], (instrs ADC8mr, SBB8mr)>;
defm : Zn4WriteResInt<WriteLEA, [Zn4AGU012], 1, [1], 1>; // LEA instructions can't fold loads.
// This write is used for slow LEA instructions.
+// values from uops.info
def Zn4Write3OpsLEA : SchedWriteRes<[Zn4ALU0123]> {
- let Latency = 2;
- let ReleaseAtCycles = [1];
- let NumMicroOps = 2;
+ let Latency = 3;
+ let ReleaseAtCycles = [1, 1, 1, 2];
+ let NumMicroOps = 4;
}
// On Znver4, a slow LEA is either a 3Ops LEA (base, index, offset),
@@ -612,9 +614,10 @@ def Zn4WriteLEA : SchedWriteVariant<[
def : InstRW<[Zn4WriteLEA], (instrs LEA32r, LEA64r, LEA64_32r)>;
+// values from uops.info
def Zn4SlowLEA16r : SchedWriteRes<[Zn4ALU0123]> {
- let Latency = 2; // FIXME: not from llvm-exegesis
- let ReleaseAtCycles = [4];
+ let Latency = 2;
+ let ReleaseAtCycles = [1, 1];
let NumMicroOps = 2;
}
@@ -660,14 +663,14 @@ def : InstRW<[Zn4WriteCMPXCHG8rm_LCMPXCHG8], (instrs CMPXCHG8rm, LCMPXCHG8)>;
def Zn4WriteCMPXCHG8B : SchedWriteRes<[Zn4ALU0123]> {
let Latency = 3; // FIXME: not from llvm-exegesis
let ReleaseAtCycles = [24];
- let NumMicroOps = 19;
+ let NumMicroOps = 15;
}
def : InstRW<[Zn4WriteCMPXCHG8B], (instrs CMPXCHG8B)>;
def Zn4WriteCMPXCHG16B_LCMPXCHG16B : SchedWriteRes<[Zn4ALU0123]> {
let Latency = 4; // FIXME: not from llvm-exegesis
let ReleaseAtCycles = [59];
- let NumMicroOps = 28;
+ let NumMicroOps = 26;
}
def : InstRW<[Zn4WriteCMPXCHG16B_LCMPXCHG16B], (instrs CMPXCHG16B, LCMPXCHG16B)>;
@@ -681,7 +684,7 @@ def : InstRW<[Zn4WriteWriteXCHGUnrenameable], (instrs XCHG8rr, XCHG16rr, XCHG16a
def Zn4WriteXCHG8rm_XCHG16rm : SchedWriteRes<[Zn4AGU012, Zn4Load, Zn4ALU0123]> {
let Latency = !add(Znver4Model.LoadLatency, 3); // FIXME: not from llvm-exegesis
let ReleaseAtCycles = [1, 1, 2];
- let NumMicroOps = 5;
+ let NumMicroOps = 2;
}
def : InstRW<[Zn4WriteXCHG8rm_XCHG16rm], (instrs XCHG8rm, XCHG16rm)>;
@@ -693,19 +696,17 @@ def Zn4WriteXCHG32rm_XCHG64rm : SchedWriteRes<[Zn4AGU012, Zn4Load, Zn4ALU0123]>
def : InstRW<[Zn4WriteXCHG32rm_XCHG64rm], (instrs XCHG32rm, XCHG64rm)>;
// Integer division.
-// FIXME: uops for 8-bit division measures as 2. for others it's a guess.
-// FIXME: latency for 8-bit division measures as 10. for others it's a guess.
-defm : Zn4WriteResIntPair<WriteDiv8, [Zn4Divider], 10, [10], 2>;
-defm : Zn4WriteResIntPair<WriteDiv16, [Zn4Divider], 11, [11], 2>;
-defm : Zn4WriteResIntPair<WriteDiv32, [Zn4Divider], 13, [13], 2>;
-defm : Zn4WriteResIntPair<WriteDiv64, [Zn4Divider], 17, [17], 2>;
-defm : Zn4WriteResIntPair<WriteIDiv8, [Zn4Divider], 10, [10], 2>;
-defm : Zn4WriteResIntPair<WriteIDiv16, [Zn4Divider], 11, [11], 2>;
-defm : Zn4WriteResIntPair<WriteIDiv32, [Zn4Divider], 13, [13], 2>;
-defm : Zn4WriteResIntPair<WriteIDiv64, [Zn4Divider], 17, [17], 2>;
-
-defm : Zn4WriteResIntPair<WriteBSF, [Zn4ALU1], 1, [1], 6, /*LoadUOps=*/1>; // Bit scan forward.
-defm : Zn4WriteResIntPair<WriteBSR, [Zn4ALU1], 1, [1], 6, /*LoadUOps=*/1>; // Bit scan reverse.
+defm : Zn4WriteResIntPair<WriteDiv8, [Zn4Divider], 9, [9], 2>;
+defm : Zn4WriteResIntPair<WriteDiv16, [Zn4Divider], 10, [10], 2>;
+defm : Zn4WriteResIntPair<WriteDiv32, [Zn4Divider], 12, [12], 2>;
+defm : Zn4WriteResIntPair<WriteDiv64, [Zn4Divider], 18, [18], 2>;
+defm : Zn4WriteResIntPair<WriteIDiv8, [Zn4Divider], 9, [9], 2>;
+defm : Zn4WriteResIntPair<WriteIDiv16, [Zn4Divider], 10, [10], 2>;
+defm : Zn4WriteResIntPair<WriteIDiv32, [Zn4Divider], 12, [12], 2>;
+defm : Zn4WriteResIntPair<WriteIDiv64, [Zn4Divider], 18, [18], 2>;
+
+defm : Zn4WriteResIntPair<WriteBSF, [Zn4ALU1], 1, [1], 1, /*LoadUOps=*/1>; // Bit scan forward.
+defm : Zn4WriteResIntPair<WriteBSR, [Zn4ALU1], 1, [1], 1, /*LoadUOps=*/1>; // Bit scan reverse.
defm : Zn4WriteResIntPair<WritePOPCNT, [Zn4ALU0123], 1, [1], 1>; // Bit population count.
@@ -725,12 +726,12 @@ def Zn4WriteLZCNT16rr : SchedWriteRes<[Zn4ALU0123]> {
}
def : InstRW<[Zn4WriteLZCNT16rr], (instrs LZCNT16rr)>;
-defm : Zn4WriteResIntPair<WriteTZCNT, [Zn4ALU12], 2, [1], 2>; // Trailing zero count.
+defm : Zn4WriteResIntPair<WriteTZCNT, [Zn4ALU12], 1, [1], 1>; // Trailing zero count.
def Zn4WriteTZCNT16rr : SchedWriteRes<[Zn4ALU0123]> {
- let Latency = 2;
- let ReleaseAtCycles = [4];
- let NumMicroOps = 2;
+ let Latency = 1;
+ let ReleaseAtCycles = [1];
+ let NumMicroOps = 1;
}
def : InstRW<[Zn4WriteTZCNT16rr], (instrs TZCNT16rr)>;
@@ -1326,9 +1327,9 @@ def : InstRW<[Zn4WriteSHA256RNDS2rr], (instrs SHA256RNDS2rr)>;
// Strings instructions.
// Packed Compare Implicit Length Strings, Return Mask
-defm : Zn4WriteResXMMPair<WritePCmpIStrM, [Zn4FPVAdd0123], 6, [8], 3, /*LoadUOps=*/1>;
+defm : Zn4WriteResXMMPair<WritePCmpIStrM, [Zn4FPVAdd0123], 7, [8], 3, /*LoadUOps=*/1>;
// Packed Compare Explicit Length Strings, Return Mask
-defm : Zn4WriteResXMMPair<WritePCmpEStrM, [Zn4FPVAdd0123], 6, [12], 7, /*LoadUOps=*/5>;
+defm : Zn4WriteResXMMPair<WritePCmpEStrM, [Zn4FPVAdd0123], 7, [12], 7, /*LoadUOps=*/5>;
// Packed Compare Implicit Length Strings, Return Index
defm : Zn4WriteResXMMPair<WritePCmpIStrI, [Zn4FPVAdd0123], 2, [8], 4>;
// Packed Compare Explicit Length Strings, Return Index
@@ -1340,7 +1341,7 @@ defm : Zn4WriteResXMMPair<WriteAESIMC, [Zn4FPAES01], 4, [1], 1>; // InvMixColumn
defm : Zn4WriteResXMMPair<WriteAESKeyGen, [Zn4FPAES01], 4, [1], 1>; // Key Generation.
// Carry-less multiplication instructions.
-defm : Zn4WriteResXMMPair<WriteCLMul, [Zn4FPCLM01], 4, [4], 4>;
+defm : Zn4WriteResXMMPair<WriteCLMul, [Zn4FPCLM01], 4, [3], 4>;
// EMMS/FEMMS
defm : Zn4WriteResInt<WriteEMMS, [Zn4ALU0123], 2, [1], 1>; // FIXME: latency not from llvm-exegesis
@@ -1386,23 +1387,23 @@ def Zn4WriteVPERM2F128rm : SchedWriteRes<[Zn4AGU012, Zn4Load, Zn4FPVShuf]> {
def : InstRW<[Zn4WriteVPERM2F128rm], (instrs VPERM2F128rmi)>;
def Zn4WriteVPERMPSYrr : SchedWriteRes<[Zn4FPVShuf]> {
- let Latency = 7;
+ let Latency = 4;
let ReleaseAtCycles = [1];
- let NumMicroOps = 2;
+ let NumMicroOps = 1;
}
def : InstRW<[Zn4WriteVPERMPSYrr], (instrs VPERMPSYrr)>;
def Zn4WriteVPERMPSYrm : SchedWriteRes<[Zn4AGU012, Zn4Load, Zn4FPVShuf]> {
let Latency = !add(Znver4Model.VecLoadLatency, Zn4WriteVPERMPSYrr.Latency);
- let ReleaseAtCycles = [1, 1, 2];
- let NumMicroOps = !add(Zn4WriteVPERMPSYrr.NumMicroOps, 1);
+ let ReleaseAtCycles = [1];
+ let NumMicroOps = 1;
}
def : InstRW<[Zn4WriteVPERMPSYrm], (instrs VPERMPSYrm)>;
def Zn4WriteVPERMYri : SchedWriteRes<[Zn4FPVShuf]> {
- let Latency = 6;
+ let Latency = 4;
let ReleaseAtCycles = [1];
- let NumMicroOps = 2;
+ let NumMicroOps = 1;
}
def : InstRW<[Zn4WriteVPERMYri], (instrs VPERMPDYri, VPERMQYri)>;
@@ -1414,9 +1415,9 @@ def Zn4WriteVPERMPDYmi : SchedWriteRes<[Zn4AGU012, Zn4Load, Zn4FPVShuf]> {
def : InstRW<[Zn4WriteVPERMPDYmi], (instrs VPERMPDYmi)>;
def Zn4WriteVPERMDYrr : SchedWriteRes<[Zn4FPVShuf]> {
- let Latency = 5;
+ let Latency = 4;
let ReleaseAtCycles = [1];
- let NumMicroOps = 2;
+ let NumMicroOps = 1;
}
def : InstRW<[Zn4WriteVPERMDYrr], (instrs VPERMDYrr)>;
``````````
</details>
https://github.com/llvm/llvm-project/pull/161405
More information about the llvm-commits
mailing list