Changed Full SM version according to the review comments.

Author: rajatbajpai

llvm/lib/Target/NVPTX/NVPTX.td

@@ -36,19 +36,26 @@ 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] in
-  def SM#sm: FeatureSM<""#sm, !mul(sm, 10)>;
-
-// Full SM version for sm_90a is 901
-def SM90a: FeatureSM<"90a", 901>;
-
-foreach sm = [100, 101, 103, 120, 121] in {
-  def SM#sm: FeatureSM<""#sm, !mul(sm, 10)>;
-  // Arch-specific targets. PTX for these is not compatible with any other
-  // architectures.
-  def SM#sm#a: FeatureSM<""#sm#"a", !add(!mul(sm, 10), 1)>;
-  // Family-specific targets. PTX for these is compatible within the same family.
-  def SM#sm#f: FeatureSM<""#sm#"f", !add(!mul(sm, 10), 2)>;
+              89, 90, 100, 101, 103, 120, 121] in {
+  // Base SM version (e.g. FullSMVersion for sm_100 is 10000)
+  def SM#sm : FeatureSM<""#sm, !mul(sm, 100)>;
+
+  // Note: Subset of the architecture-specific features, normally
+  // available in "a" variants that will be compatible with subsequent targets
+  // in the same family. I.e they are only ordered within the major architecture,
+  // but are not comparable with other major architectures
+
+  // Family-specific targets which are compatible within same family
+  // (e.g. FullSMVersion for sm_100f is 10010)
+  if !ge(sm, 100) then {
+    def SM#sm#f : FeatureSM<""#sm#"f", !add(!mul(sm, 100), 10)>;
+  }
+
+  // Architecture-specific targets which are incompatible across architectures
+  // (e.g. FullSMVersion for sm_100a is 10011)
+  if !ge(sm, 90) then {
+    def SM#sm#a : FeatureSM<""#sm#"a", !add(!mul(sm, 100), 11)>;
+  }
 }
 
 foreach version = [32, 40, 41, 42, 43, 50, 60, 61, 62, 63, 64, 65,

llvm/lib/Target/NVPTX/NVPTXInstrInfo.td

@@ -166,10 +166,10 @@ class hasPTX<int version>: Predicate<"Subtarget->getPTXVersion() >= " # version>
 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">;
+def hasSM90a : Predicate<"Subtarget->getSmVersion() == 90 && Subtarget->hasArchAccelFeatures()">;
+def hasSM100a : Predicate<"Subtarget->getSmVersion() == 100 && Subtarget->hasArchAccelFeatures()">;
+def hasSM101a : Predicate<"Subtarget->getSmVersion() == 101 && Subtarget->hasArchAccelFeatures()">;
+def hasSM120a : Predicate<"Subtarget->getSmVersion() == 120 && Subtarget->hasArchAccelFeatures()">;
 
 // non-sync shfl instructions are not available on sm_70+ in PTX6.4+
 def hasSHFL : Predicate<"!(Subtarget->getSmVersion() >= 70"

llvm/lib/Target/NVPTX/NVPTXSubtarget.h

@@ -108,8 +108,8 @@ class NVPTXSubtarget : public NVPTXGenSubtargetInfo {
     switch (FullSmVersion) {
     default:
       break;
-    case 1001: // sm_100a
-    case 1011: // sm_101a
+    case 10011: // sm_100a
+    case 10111: // sm_101a
       HasTcgen05 = true;
       break;
     }
@@ -127,33 +127,21 @@ class NVPTXSubtarget : public NVPTXGenSubtargetInfo {
   bool hasPTXASUnreachableBug() const { return PTXVersion < 83; }
   bool hasCvtaParam() const { return SmVersion >= 70 && PTXVersion >= 77; }
   unsigned int getFullSmVersion() const { return FullSmVersion; }
-  unsigned int getSmVersion() const { return getFullSmVersion() / 10; }
+  unsigned int getSmVersion() const { return getFullSmVersion() / 100; }
   // GPUs with "a" suffix have include architecture-accelerated features that
   // are supported on the specified architecture only, hence such targets do not
   // follow the onion layer model. hasArchAccelFeatures() allows
   // distinguishing such GPU variants from the base GPU architecture.
   // - false represents non-accelerated architecture.
   // - true represents architecture-accelerated variant.
-  bool hasArchAccelFeatures() const {
-    auto FullSMVersionMod = getFullSmVersion() % 10;
-    assert(FullSMVersionMod < 3 && "Invalid architecture!");
-    return FullSMVersionMod == 1;
-  }
+  bool hasArchAccelFeatures() const { return getFullSmVersion() % 10; }
   // GPUs with 'f' suffix have architecture-accelerated features which are
   // portable across all future architectures under same SM major. For example,
   // sm_100f features will work for sm_10X future architectures.
   // - false represents non-family-specific architecture.
   // - true represents family-specific variant.
   bool hasFamilySpecificFeatures() const {
-    auto FullSMVersionMod = getFullSmVersion() % 10;
-    assert(FullSMVersionMod < 3 && "Invalid architecture!");
-    return FullSMVersionMod == 2 && PTXVersion >= 88;
-  }
-  // Checks if architecture is accelerated or family-specific.
-  // - false represents neither arch-accelerated nor family-specific arch.
-  // - true represents either arch-accelerated or family-specific arch.
-  bool hasArchAccelOrFamilySpecificFeatures() const {
-    return hasArchAccelFeatures() || hasFamilySpecificFeatures();
+    return getFullSmVersion() % 100 != 0 && PTXVersion >= 88;
   }
   // If the user did not provide a target we default to the `sm_30` target.
   std::string getTargetName() const {