[NVPTX] Add support for PTX ISA v8.8 (#136639)

Support PTX version 8.8 (`-mattr=+ptx88`) from CUDA 12.9. The following
new targets are also added:

- SM103 and SM121: sm_103, sm_103a, sm_121, sm_121a.

Also, some things were reformatted.

https://docs.nvidia.com/cuda/parallel-thread-execution/#changes-in-ptx-isa-version-8-8

Author: Prince781

llvm/lib/Target/NVPTX/NVPTX.td

@@ -36,17 +36,21 @@ class FeaturePTX<int version>:
 
 foreach sm = [20, 21, 30, 32, 35, 37, 50, 52, 53,
               60, 61, 62, 70, 72, 75, 80, 86, 87,
-              89, 90, 100, 101, 120] in
+              89, 90, 100, 101, 103, 120, 121] in
   def SM#sm: FeatureSM<""#sm, !mul(sm, 10)>;
 
-def SM90a: FeatureSM<"90a", 901>;
+// Arch-specific targets. PTX for these is not compatible with any other
+// architectures.
+def SM90a : FeatureSM<"90a", 901>;
 def SM100a: FeatureSM<"100a", 1001>;
 def SM101a: FeatureSM<"101a", 1011>;
+def SM103a: FeatureSM<"103a", 1031>;
 def SM120a: FeatureSM<"120a", 1201>;
+def SM121a: FeatureSM<"121a", 1211>;
 
 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, 87] in
+                   80, 81, 82, 83, 84, 85, 86, 87, 88] in
   def PTX#version: FeaturePTX<version>;
 
 //===----------------------------------------------------------------------===//
@@ -56,33 +60,37 @@ foreach version = [32, 40, 41, 42, 43, 50, 60, 61, 62, 63, 64, 65,
 class Proc<string Name, list<SubtargetFeature> Features>
  : Processor<Name, NoItineraries, Features>;
 
-def : Proc<"sm_20", [SM20, PTX32]>;
-def : Proc<"sm_21", [SM21, PTX32]>;
-def : Proc<"sm_30", [SM30]>;
-def : Proc<"sm_32", [SM32, PTX40]>;
-def : Proc<"sm_35", [SM35, PTX32]>;
-def : Proc<"sm_37", [SM37, PTX41]>;
-def : Proc<"sm_50", [SM50, PTX40]>;
-def : Proc<"sm_52", [SM52, PTX41]>;
-def : Proc<"sm_53", [SM53, PTX42]>;
-def : Proc<"sm_60", [SM60, PTX50]>;
-def : Proc<"sm_61", [SM61, PTX50]>;
-def : Proc<"sm_62", [SM62, PTX50]>;
-def : Proc<"sm_70", [SM70, PTX60]>;
-def : Proc<"sm_72", [SM72, PTX61]>;
-def : Proc<"sm_75", [SM75, PTX63]>;
-def : Proc<"sm_80", [SM80, PTX70]>;
-def : Proc<"sm_86", [SM86, PTX71]>;
-def : Proc<"sm_87", [SM87, PTX74]>;
-def : Proc<"sm_89", [SM89, PTX78]>;
-def : Proc<"sm_90", [SM90, PTX78]>;
-def : Proc<"sm_90a", [SM90a, PTX80]>;
-def : Proc<"sm_100", [SM100, PTX86]>;
+def : Proc<"sm_20",   [SM20, PTX32]>;
+def : Proc<"sm_21",   [SM21, PTX32]>;
+def : Proc<"sm_30",   [SM30]>;
+def : Proc<"sm_32",   [SM32, PTX40]>;
+def : Proc<"sm_35",   [SM35, PTX32]>;
+def : Proc<"sm_37",   [SM37, PTX41]>;
+def : Proc<"sm_50",   [SM50, PTX40]>;
+def : Proc<"sm_52",   [SM52, PTX41]>;
+def : Proc<"sm_53",   [SM53, PTX42]>;
+def : Proc<"sm_60",   [SM60, PTX50]>;
+def : Proc<"sm_61",   [SM61, PTX50]>;
+def : Proc<"sm_62",   [SM62, PTX50]>;
+def : Proc<"sm_70",   [SM70, PTX60]>;
+def : Proc<"sm_72",   [SM72, PTX61]>;
+def : Proc<"sm_75",   [SM75, PTX63]>;
+def : Proc<"sm_80",   [SM80, PTX70]>;
+def : Proc<"sm_86",   [SM86, PTX71]>;
+def : Proc<"sm_87",   [SM87, PTX74]>;
+def : Proc<"sm_89",   [SM89, PTX78]>;
+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_101",  [SM101, PTX86]>;
 def : Proc<"sm_101a", [SM101a, PTX86]>;
-def : Proc<"sm_120", [SM120, PTX87]>;
+def : Proc<"sm_103",  [SM103, PTX88]>;
+def : Proc<"sm_103a", [SM103a, PTX88]>;
+def : Proc<"sm_120",  [SM120, PTX87]>;
 def : Proc<"sm_120a", [SM120a, PTX87]>;
+def : Proc<"sm_121",  [SM121, PTX88]>;
+def : Proc<"sm_121a", [SM121a, PTX88]>;
 
 def NVPTXInstrInfo : InstrInfo {
 }

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

@@ -20,8 +20,12 @@
 ; 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_103 | FileCheck %s --check-prefix=SM103
+; RUN: llc < %s -mtriple=nvptx -mcpu=sm_103a | FileCheck %s --check-prefix=SM103a
 ; 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=nvptx -mcpu=sm_121 | FileCheck %s --check-prefix=SM121
+; RUN: llc < %s -mtriple=nvptx -mcpu=sm_121a | FileCheck %s --check-prefix=SM121a
 
 ; 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
@@ -45,8 +49,12 @@
 ; 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_103 | FileCheck %s --check-prefix=SM103
+; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_103a | FileCheck %s --check-prefix=SM103a
 ; 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
+; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_121 | FileCheck %s --check-prefix=SM121
+; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_121a | FileCheck %s --check-prefix=SM121a
 
 ; SM20: .version 3.2
 ; SM21: .version 3.2
@@ -70,8 +78,12 @@
 ; SM100a: .version 8.6
 ; SM101: .version 8.6
 ; SM101a: .version 8.6
+; SM103: .version 8.8
+; SM103a: .version 8.8
 ; SM120: .version 8.7
 ; SM120a: .version 8.7
+; SM121: .version 8.8
+; SM121a: .version 8.8
 
 ; SM20: .target sm_20
 ; SM21: .target sm_21
@@ -95,5 +107,9 @@
 ; SM100a: .target sm_100a
 ; SM101: .target sm_101
 ; SM101a: .target sm_101a
+; SM103: .target sm_103
+; SM103a: .target sm_103a
 ; SM120: .target sm_120
 ; SM120a: .target sm_120a
+; SM121: .target sm_121
+; SM121a: .target sm_121a