Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
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
1 change: 1 addition & 0 deletions llvm/lib/Target/NVPTX/NVPTXInstrInfo.td
Original file line number Diff line number Diff line change
Expand Up @@ -142,6 +142,7 @@ def hasLDU : Predicate<"Subtarget->hasLDU()">;
def hasPTXASUnreachableBug : Predicate<"Subtarget->hasPTXASUnreachableBug()">;
def noPTXASUnreachableBug : Predicate<"!Subtarget->hasPTXASUnreachableBug()">;
def hasOptEnabled : Predicate<"TM.getOptLevel() != CodeGenOptLevel::None">;
def hasAcceleratedFeatures : Predicate<"Subtarget->hasAAFeatures()">;

def doF32FTZ : Predicate<"useF32FTZ()">;
def doNoF32FTZ : Predicate<"!useF32FTZ()">;
Expand Down
2 changes: 1 addition & 1 deletion llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
Original file line number Diff line number Diff line change
Expand Up @@ -7547,7 +7547,7 @@ multiclass SET_MAXNREG<string Action, Intrinsic Intr> {
def : NVPTXInst<(outs), (ins i32imm:$reg_count),
"setmaxnreg." # Action # ".sync.aligned.u32 $reg_count;",
[(Intr timm:$reg_count)]>,
Requires<[hasSM90a, hasPTX<80>]>;
Requires<[hasAcceleratedFeatures, hasSM<90>, hasPTX<80>]>;
}

defm INT_SET_MAXNREG_INC : SET_MAXNREG<"inc", int_nvvm_setmaxnreg_inc_sync_aligned_u32>;
Expand Down
13 changes: 13 additions & 0 deletions llvm/test/CodeGen/NVPTX/setmaxnreg-sm100a.ll
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
; RUN: llc < %s -march=nvptx64 -mcpu=sm_100a -mattr=+ptx86 | FileCheck --check-prefixes=CHECK %s
; RUN: %if ptxas-12.8 %{ llc < %s -march=nvptx64 -mcpu=sm_100a -mattr=+ptx86 | %ptxas-verify -arch=sm_100a %}

; CHECK-LABEL: test_set_maxn_reg_sm100a
define void @test_set_maxn_reg_sm100a() {
; CHECK: setmaxnreg.inc.sync.aligned.u32 96;
call void @llvm.nvvm.setmaxnreg.inc.sync.aligned.u32(i32 96)

; CHECK: setmaxnreg.dec.sync.aligned.u32 64;
call void @llvm.nvvm.setmaxnreg.dec.sync.aligned.u32(i32 64)

ret void
}