Skip to content
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
50 changes: 29 additions & 21 deletions llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -2290,12 +2290,14 @@ GFX940_SMFMA_N_PassWritesVGPROverlappedSrcABWaitStates(int NumPasses) {
return NumPasses + 2;
}

static int GFX940_XDL_N_PassWritesVGPROverlappedSrcABWaitStates(int NumPasses) {
// 2 pass -> 5
// 4 pass -> 7
// 8 pass -> 11
// 16 pass -> 19
return NumPasses + 3;
static int GFX940_XDL_N_PassWritesVGPROverlappedSrcABWaitStates(int NumPasses,
bool IsGFX950) {
// xdl def cycles | gfx940 | gfx950
// 2 pass | 5 5
// 4 pass | 7 8
// 8 pass | 11 12
// 16 pass | 19 20
return NumPasses + 3 + (NumPasses != 2 && IsGFX950);
}

int GCNHazardRecognizer::checkMAIHazards90A(MachineInstr *MI) {
Expand Down Expand Up @@ -2464,7 +2466,7 @@ int GCNHazardRecognizer::checkMAIHazards90A(MachineInstr *MI) {
NeedWaitStates =
isXDL(ST, *MI1)
? GFX940_XDL_N_PassWritesVGPROverlappedSrcABWaitStates(
NumPasses)
NumPasses, ST.hasGFX950Insts())
: GFX940_SMFMA_N_PassWritesVGPROverlappedSrcABWaitStates(
NumPasses);
break;
Expand Down Expand Up @@ -2596,20 +2598,24 @@ static int GFX940_SMFMA_N_PassWriteVgprVALUWawWaitStates(int NumPasses) {
return NumPasses + 2;
}

static int GFX940_XDL_N_PassWriteVgprVALUWawWaitStates(int NumPasses) {
// 2 pass -> 5
// 4 pass -> 7
// 8 pass -> 11
// 16 pass -> 19
return NumPasses + 3;
static int GFX940_XDL_N_PassWriteVgprVALUWawWaitStates(int NumPasses,
bool IsGFX950) {
// xdl def cycles | gfx940 | gfx950
// 2 pass | 5 5
// 4 pass | 7 8
// 8 pass | 11 12
// 16 pass | 19 20
return NumPasses + 3 + (NumPasses != 2 && IsGFX950);
}

static int GFX940_XDL_N_PassWriteVgprVALUMemExpReadWaitStates(int NumPasses) {
// 2 pass -> 5
// 4 pass -> 7
// 8 pass -> 11
// 16 pass -> 19
return NumPasses + 3;
static int GFX940_XDL_N_PassWriteVgprVALUMemExpReadWaitStates(int NumPasses,
bool IsGFX950) {
// xdl def cycles | gfx940 | gfx950
// 2 pass | 5 5
// 4 pass | 7 8
// 8 pass | 11 12
// 16 pass | 19 20
return NumPasses + 3 + (NumPasses != 2 && IsGFX950);
}

static int GFX940_SMFMA_N_PassWriteVgprVALUMemExpReadWaitStates(int NumPasses) {
Expand Down Expand Up @@ -2760,7 +2766,8 @@ int GCNHazardRecognizer::checkMAIVALUHazards(MachineInstr *MI) {
} else if (ST.hasGFX940Insts()) {
NeedWaitStates =
isXDL(ST, *MFMA)
? GFX940_XDL_N_PassWriteVgprVALUMemExpReadWaitStates(NumPasses)
? GFX940_XDL_N_PassWriteVgprVALUMemExpReadWaitStates(
NumPasses, ST.hasGFX950Insts())
: GFX940_SMFMA_N_PassWriteVgprVALUMemExpReadWaitStates(
NumPasses);
} else {
Expand Down Expand Up @@ -2846,7 +2853,8 @@ int GCNHazardRecognizer::checkMAIVALUHazards(MachineInstr *MI) {
} else if (ST.hasGFX940Insts()) {
NeedWaitStates =
isXDL(ST, *MFMA)
? GFX940_XDL_N_PassWriteVgprVALUWawWaitStates(NumPasses)
? GFX940_XDL_N_PassWriteVgprVALUWawWaitStates(
NumPasses, ST.hasGFX950Insts())
: GFX940_SMFMA_N_PassWriteVgprVALUWawWaitStates(NumPasses);
} else {
switch (NumPasses) {
Expand Down
Loading