[NVPTX] Add SM versions for 101 and 120 (#124155)

This patch adds SM and PTX versions for SM
101, 120 and their arch-accelerated variants.

All these are supported in cuda-12.8.
sm120/120a requires ptx8.7 and the rest require ptx8.6.

Signed-off-by: Durgadoss R <[email protected]>

Author: durga4github

llvm/lib/Target/NVPTX/NVPTX.td

@@ -35,15 +35,18 @@ class FeaturePTX<int version>:
                     "Use PTX version " # version>;
 
 foreach sm = [20, 21, 30, 32, 35, 37, 50, 52, 53,
-              60, 61, 62, 70, 72, 75, 80, 86, 87, 89, 90, 100] in
+              60, 61, 62, 70, 72, 75, 80, 86, 87,
+              89, 90, 100, 101, 120] in
   def SM#sm: FeatureSM<""#sm, !mul(sm, 10)>;
 
 def SM90a: FeatureSM<"90a", 901>;
 def SM100a: FeatureSM<"100a", 1001>;
+def SM101a: FeatureSM<"101a", 1011>;
+def SM120a: FeatureSM<"120a", 1201>;
 
 foreach version = [32, 40, 41, 42, 43, 50, 60, 61, 62, 63, 64, 65,
                    70, 71, 72, 73, 74, 75, 76, 77, 78,
-                   80, 81, 82, 83, 84, 85, 86] in
+                   80, 81, 82, 83, 84, 85, 86, 87] in
   def PTX#version: FeaturePTX<version>;
 
 //===----------------------------------------------------------------------===//
@@ -76,6 +79,10 @@ def : Proc<"sm_90", [SM90, PTX78]>;
 def : Proc<"sm_90a", [SM90a, PTX80]>;
 def : Proc<"sm_100", [SM100, PTX86]>;
 def : Proc<"sm_100a", [SM100a, PTX86]>;
+def : Proc<"sm_101", [SM101, PTX86]>;
+def : Proc<"sm_101a", [SM101a, PTX86]>;
+def : Proc<"sm_120", [SM120, PTX87]>;
+def : Proc<"sm_120a", [SM120a, PTX87]>;
 
 def NVPTXInstrInfo : InstrInfo {
 }

llvm/lib/Target/NVPTX/NVPTXInstrInfo.td

@@ -172,6 +172,9 @@ class hasSM<int version>: Predicate<"Subtarget->getSmVersion() >= " # version>;
 
 // Explicit records for arch-accelerated SM versions
 def hasSM90a : Predicate<"Subtarget->getFullSmVersion() == 901">;
+def hasSM100a : Predicate<"Subtarget->getFullSmVersion() == 1001">;
+def hasSM101a : Predicate<"Subtarget->getFullSmVersion() == 1011">;
+def hasSM120a : Predicate<"Subtarget->getFullSmVersion() == 1201">;
 
 // non-sync shfl instructions are not available on sm_70+ in PTX6.4+
 def hasSHFL : Predicate<"!(Subtarget->getSmVersion() >= 70"

llvm/test/CodeGen/NVPTX/sm-version.ll

@@ -16,6 +16,12 @@
 ; RUN: llc < %s -mtriple=nvptx -mcpu=sm_86 | FileCheck %s --check-prefix=SM86
 ; RUN: llc < %s -mtriple=nvptx -mcpu=sm_90 | FileCheck %s --check-prefix=SM90
 ; RUN: llc < %s -mtriple=nvptx -mcpu=sm_90a | FileCheck %s --check-prefix=SM90a
+; RUN: llc < %s -mtriple=nvptx -mcpu=sm_100 | FileCheck %s --check-prefix=SM100
+; RUN: llc < %s -mtriple=nvptx -mcpu=sm_100a | FileCheck %s --check-prefix=SM100a
+; RUN: llc < %s -mtriple=nvptx -mcpu=sm_101 | FileCheck %s --check-prefix=SM101
+; RUN: llc < %s -mtriple=nvptx -mcpu=sm_101a | FileCheck %s --check-prefix=SM101a
+; RUN: llc < %s -mtriple=nvptx -mcpu=sm_120 | FileCheck %s --check-prefix=SM120
+; RUN: llc < %s -mtriple=nvptx -mcpu=sm_120a | FileCheck %s --check-prefix=SM120a
 
 ; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_20 | FileCheck %s --check-prefix=SM20
 ; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_21 | FileCheck %s --check-prefix=SM21
@@ -35,6 +41,12 @@
 ; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_86 | FileCheck %s --check-prefix=SM86
 ; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_90 | FileCheck %s --check-prefix=SM90
 ; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_90a | FileCheck %s --check-prefix=SM90a
+; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_100 | FileCheck %s --check-prefix=SM100
+; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_100a | FileCheck %s --check-prefix=SM100a
+; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_101 | FileCheck %s --check-prefix=SM101
+; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_101a | FileCheck %s --check-prefix=SM101a
+; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_120 | FileCheck %s --check-prefix=SM120
+; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_120a | FileCheck %s --check-prefix=SM120a
 
 ; SM20: .version 3.2
 ; SM21: .version 3.2
@@ -54,6 +66,12 @@
 ; SM86: .version 7.1
 ; SM90: .version 7.8
 ; SM90a: .version 8.0
+; SM100: .version 8.6
+; SM100a: .version 8.6
+; SM101: .version 8.6
+; SM101a: .version 8.6
+; SM120: .version 8.7
+; SM120a: .version 8.7
 
 ; SM20: .target sm_20
 ; SM21: .target sm_21
@@ -73,3 +91,9 @@
 ; SM86: .target sm_86
 ; SM90: .target sm_90
 ; SM90a: .target sm_90a
+; SM100: .target sm_100
+; SM100a: .target sm_100a
+; SM101: .target sm_101
+; SM101a: .target sm_101a
+; SM120: .target sm_120
+; SM120a: .target sm_120a