[NVPTX] Add family-specific architectures support #141899
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@llvm/pr-subscribers-backend-nvptx Author: Rajat Bajpai (rajatbajpai) ChangesThis change adds family-specific architectures support added in PTX ISA 8.8. These architectures have "f" suffix. For example, sm_100f. This change doesn't promote existing features to family-specific architecture. Full diff: https://github.com/llvm/llvm-project/pull/141899.diff 2 Files Affected:
diff --git a/llvm/lib/Target/NVPTX/NVPTX.td b/llvm/lib/Target/NVPTX/NVPTX.td
index ff9a187ecf723..3ed2553fa4232 100644
--- a/llvm/lib/Target/NVPTX/NVPTX.td
+++ b/llvm/lib/Target/NVPTX/NVPTX.td
@@ -41,12 +41,14 @@ foreach sm = [20, 21, 30, 32, 35, 37, 50, 52, 53,
// 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 sm = [90, 100, 101, 103, 120, 121] in {
+ def SM#sm#a : FeatureSM<""#sm#"a", !add(!mul(sm, 10), 1)>;
+}
+
+// Family-specific targets. PTX for these is compatible within the same family.
+foreach sm = [100, 101, 103, 120, 121] in {
+ def SM#sm#f : FeatureSM<""#sm#"f", !add(!mul(sm, 10), 2)>;
+}
foreach version = [32, 40, 41, 42, 43, 50, 60, 61, 62, 63, 64, 65,
70, 71, 72, 73, 74, 75, 76, 77, 78,
@@ -83,14 +85,19 @@ 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_100f", [SM100f, PTX88]>;
def : Proc<"sm_101", [SM101, PTX86]>;
def : Proc<"sm_101a", [SM101a, PTX86]>;
+def : Proc<"sm_101f", [SM101f, PTX88]>;
def : Proc<"sm_103", [SM103, PTX88]>;
def : Proc<"sm_103a", [SM103a, PTX88]>;
+def : Proc<"sm_103f", [SM103f, PTX88]>;
def : Proc<"sm_120", [SM120, PTX87]>;
def : Proc<"sm_120a", [SM120a, PTX87]>;
+def : Proc<"sm_120f", [SM120f, PTX88]>;
def : Proc<"sm_121", [SM121, PTX88]>;
def : Proc<"sm_121a", [SM121a, PTX88]>;
+def : Proc<"sm_121f", [SM121f, PTX88]>;
def NVPTXInstrInfo : InstrInfo {
}
diff --git a/llvm/lib/Target/NVPTX/NVPTXSubtarget.h b/llvm/lib/Target/NVPTX/NVPTXSubtarget.h
index 5136b1ee28502..5e4ab9476cb31 100644
--- a/llvm/lib/Target/NVPTX/NVPTXSubtarget.h
+++ b/llvm/lib/Target/NVPTX/NVPTXSubtarget.h
@@ -132,10 +132,29 @@ class NVPTXSubtarget : public NVPTXGenSubtargetInfo {
// 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.
- // - 0 represents base GPU model,
- // - non-zero value identifies particular architecture-accelerated variant.
- bool hasArchAccelFeatures() const { return getFullSmVersion() % 10; }
-
+ // - 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;
+ }
+ // 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();
+ }
// If the user did not provide a target we default to the `sm_30` target.
std::string getTargetName() const {
return TargetName.empty() ? "sm_30" : TargetName;
|
Artem-B
reviewed
May 29, 2025
rajatbajpai
force-pushed
the
dev/rbajpai/add-family-specific-arch-support
branch
from
e4d1b4d to
e2837d1
Compare
Artem-B
reviewed
May 30, 2025
rajatbajpai
force-pushed
the
dev/rbajpai/add-family-specific-arch-support
branch
from
e542576 to
1ec1528
Compare
|
@Artem-B @durga4github Could you please approve this MR? The latest revision contains minor change in |
durga4github
reviewed
Jun 9, 2025
durga4github
approved these changes
Jun 9, 2025
Artem-B
reviewed
Jun 9, 2025
rajatbajpai
force-pushed
the
dev/rbajpai/add-family-specific-arch-support
branch
from
1ec1528 to
4ed46f8
Compare
|
@Artem-B Please see the recent doc comments update, I hope it is clear now. |
Artem-B
reviewed
Jun 11, 2025
AlexMaclean
reviewed
Jun 12, 2025
|
Guys, I have tried to fix the nits. If this change looks good overall, I would prefer to merge this and refine as we go. So, I'll appreciate an upvote. Thanks for understanding. |
rajatbajpai
force-pushed
the
dev/rbajpai/add-family-specific-arch-support
branch
from
6b26f71 to
f007e3a
Compare
AlexMaclean
approved these changes
Jun 16, 2025
There was a problem hiding this comment.
LGTM. While there are still some points I think could be clarified further I think this is a step in the right direction. Please wait for @Artem-B's review prior to landing.
Artem-B
approved these changes
Jun 17, 2025
rajatbajpai
force-pushed
the
dev/rbajpai/add-family-specific-arch-support
branch
from
f007e3a to
444c468
Compare
This change adds family-specific architecture variants support. These architecture variants have "f" suffix. For example, sm_100f. This change doesn't promote existing features to family-specific architecture.
rajatbajpai
force-pushed
the
dev/rbajpai/add-family-specific-arch-support
branch
from
444c468 to
7d756fe
Compare
|
LLVM Buildbot has detected a new failure on builder Full details are available at: https://lab.llvm.org/buildbot/#/builders/199/builds/4162 Here is the relevant piece of the build log for the reference |
|
LLVM Buildbot has detected a new failure on builder Full details are available at: https://lab.llvm.org/buildbot/#/builders/84/builds/2066 Here is the relevant piece of the build log for the reference |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This change adds family-specific architectures support added in PTX ISA 8.8. These architectures have "f" suffix. For example, sm_100f.
This change doesn't promote existing features to family-specific architecture.