Add RTX 3060 Laptop hw_def; fix CLK_FREQUENCY macro collision#89
Open
AndrewVu23 wants to merge 1 commit into
Open
Add RTX 3060 Laptop hw_def; fix CLK_FREQUENCY macro collision#89AndrewVu23 wants to merge 1 commit into
AndrewVu23 wants to merge 1 commit into
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds an hw_def header for the RTX 3060 Laptop GPU so the GPU_Microbenchmark suite can target it, and fixes a build-breaking macro collision that affects every existing hw_def header on modern toolchains.
Motivation / root cause
Each
*_hw_def.hdoes#define CLK_FREQUENCY <MHz>.hw_def/common/gpuConfig.hdefines a gpuConfig struct with a member also spelledCLK_FREQUENCY, so the macro rewrites the member name and the tuner fails to compile:error: expected identifier before numeric constant (CLK_FREQUENCY -> 1410)I found this bug by looking at the default config (Blackwell B200 -> the
CLK_FREQUENCYis commented out)Changes
ampere_RTX3060_MOBILE_hw_def.h: GA106 specs (30 SM, 1536 thr/SM, 128 KB L1, 3 MB L2, 192-bit, cap 8.6).hw_def.h: activate the RTX3060 include.All sibling
*_hw_def.h: comment out #define CLK_FREQUENCY with a reviewer noteEvidence (before / after)
Before:
#define CLK_FREQUENCY 1410→ compile error aboveAfter: header set builds;
config_int/configreport the real card (30 SM, cap 8.6)Test plan
make -C src/cuda/GPU_Microbenchmark builds the RTX3060 target