Skip to content

[NVPTX][NFC] Use NAME macro for TMA intrinsic defs #117907

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 28, 2024
Merged

[NVPTX][NFC] Use NAME macro for TMA intrinsic defs #117907

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
64 changes: 32 additions & 32 deletions llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -536,22 +536,22 @@ multiclass CP_ASYNC_BULK_TENSOR_G2S_INTR<int dim, bit is_shared32, string mode>
defvar asm_str = !if(!eq(mode, "im2col"),
!strconcat(asm_str_default, im2col_asm_str), asm_str_default);

def "": NVPTXInst<(outs),
!con((ins rc:$dst, rc:$mbar, Int64Regs:$tmap), dims_dag, im2col_dag),
!strconcat(G2S_STRINGS<dim, mode, 0, 0>.inst_name, asm_str, ";"), []>,
Requires<[hasPTX<80>, hasSM<90>]>;
def _MC: NVPTXInst<(outs),
!con((ins rc:$dst, rc:$mbar, Int64Regs:$tmap), dims_dag, im2col_dag, (ins Int16Regs:$mc)),
!strconcat(G2S_STRINGS<dim, mode, 1, 0>.inst_name, asm_str, ", $mc;"), []>,
Requires<[hasPTX<80>, hasSM<90>]>;
def _CH: NVPTXInst<(outs),
!con((ins rc:$dst, rc:$mbar, Int64Regs:$tmap), dims_dag, im2col_dag, (ins Int64Regs:$ch)),
!strconcat(G2S_STRINGS<dim, mode, 0, 1>.inst_name, asm_str, ", $ch;"), []>,
Requires<[hasPTX<80>, hasSM<90>]>;
def _MC_CH: NVPTXInst<(outs),
!con((ins rc:$dst, rc:$mbar, Int64Regs:$tmap), dims_dag, im2col_dag, (ins Int16Regs:$mc, Int64Regs:$ch)),
!strconcat(G2S_STRINGS<dim, mode, 1, 1>.inst_name, asm_str, ", $mc, $ch;"), []>,
Requires<[hasPTX<80>, hasSM<90>]>;
def NAME: NVPTXInst<(outs),
!con((ins rc:$dst, rc:$mbar, Int64Regs:$tmap), dims_dag, im2col_dag),
!strconcat(G2S_STRINGS<dim, mode, 0, 0>.inst_name, asm_str, ";"), []>,
Requires<[hasPTX<80>, hasSM<90>]>;
def NAME # _MC: NVPTXInst<(outs),
!con((ins rc:$dst, rc:$mbar, Int64Regs:$tmap), dims_dag, im2col_dag, (ins Int16Regs:$mc)),
!strconcat(G2S_STRINGS<dim, mode, 1, 0>.inst_name, asm_str, ", $mc;"), []>,
Requires<[hasPTX<80>, hasSM<90>]>;
def NAME # _CH: NVPTXInst<(outs),
!con((ins rc:$dst, rc:$mbar, Int64Regs:$tmap), dims_dag, im2col_dag, (ins Int64Regs:$ch)),
!strconcat(G2S_STRINGS<dim, mode, 0, 1>.inst_name, asm_str, ", $ch;"), []>,
Requires<[hasPTX<80>, hasSM<90>]>;
def NAME # _MC_CH: NVPTXInst<(outs),
!con((ins rc:$dst, rc:$mbar, Int64Regs:$tmap), dims_dag, im2col_dag, (ins Int16Regs:$mc, Int64Regs:$ch)),
!strconcat(G2S_STRINGS<dim, mode, 1, 1>.inst_name, asm_str, ", $mc, $ch;"), []>,
Requires<[hasPTX<80>, hasSM<90>]>;
}

foreach dim = [1, 2, 3, 4, 5] in {
Expand Down Expand Up @@ -588,14 +588,14 @@ multiclass CP_ASYNC_BULK_TENSOR_S2G_INTR<int dim, bit shared32, string mode> {
defvar asm_str = " [$tmap, {{" # dims_str # "}}], [$src]";
defvar rc = !if(shared32, Int32Regs, Int64Regs);

def "": NVPTXInst<(outs),
!con((ins rc:$src, Int64Regs:$tmap), dims_dag),
!strconcat(S2G_STRINGS<dim, mode, 0>.inst_name, asm_str, ";"), []>,
Requires<[hasPTX<80>, hasSM<90>]>;
def _CH: NVPTXInst<(outs),
!con((ins rc:$src, Int64Regs:$tmap), dims_dag, (ins Int64Regs:$ch)),
!strconcat(S2G_STRINGS<dim, mode, 1>.inst_name, asm_str, ", $ch;"), []>,
Requires<[hasPTX<80>, hasSM<90>]>;
def NAME: NVPTXInst<(outs),
!con((ins rc:$src, Int64Regs:$tmap), dims_dag),
!strconcat(S2G_STRINGS<dim, mode, 0>.inst_name, asm_str, ";"), []>,
Requires<[hasPTX<80>, hasSM<90>]>;
def NAME # _CH: NVPTXInst<(outs),
!con((ins rc:$src, Int64Regs:$tmap), dims_dag, (ins Int64Regs:$ch)),
!strconcat(S2G_STRINGS<dim, mode, 1>.inst_name, asm_str, ", $ch;"), []>,
Requires<[hasPTX<80>, hasSM<90>]>;
}

def TMAReductionFlags : Operand<i32> {
Expand Down Expand Up @@ -662,14 +662,14 @@ multiclass CP_ASYNC_BULK_TENSOR_PREFETCH_INTR<int dim, string mode> {
defvar asm_str = !if(!eq(mode, "im2col"),
!strconcat(asm_str_default, im2col_asm_str), asm_str_default);

def "": NVPTXInst<(outs),
!con((ins Int64Regs:$tmap), dims_dag, im2col_dag),
!strconcat(PREFETCH_STRINGS<dim, mode, 0>.inst_name, asm_str, ";"), []>,
Requires<[hasPTX<80>, hasSM<90>]>;
def _CH: NVPTXInst<(outs),
!con((ins Int64Regs:$tmap), dims_dag, im2col_dag, (ins Int64Regs:$ch)),
!strconcat(PREFETCH_STRINGS<dim, mode, 1>.inst_name, asm_str, ", $ch;"), []>,
Requires<[hasPTX<80>, hasSM<90>]>;
def NAME: NVPTXInst<(outs),
!con((ins Int64Regs:$tmap), dims_dag, im2col_dag),
!strconcat(PREFETCH_STRINGS<dim, mode, 0>.inst_name, asm_str, ";"), []>,
Requires<[hasPTX<80>, hasSM<90>]>;
def NAME # _CH: NVPTXInst<(outs),
!con((ins Int64Regs:$tmap), dims_dag, im2col_dag, (ins Int64Regs:$ch)),
!strconcat(PREFETCH_STRINGS<dim, mode, 1>.inst_name, asm_str, ", $ch;"), []>,
Requires<[hasPTX<80>, hasSM<90>]>;
}

foreach dim = [1, 2, 3, 4, 5] in {
Expand Down