t-vi commented on a change in pull request #4342: Add workgroup size attribute
to AMDGPU functions in codegen
URL: https://github.com/apache/incubator-tvm/pull/4342#discussion_r346595415
##########
File path: src/codegen/llvm/codegen_amdgpu.cc
##########
@@ -36,13 +36,39 @@
namespace tvm {
namespace codegen {
+namespace {
+
+// calls the device api to get the max threads per block
+static inline int DetectROCMmaxThreadsPerBlock() {
+ TVMContext tvm_ctx;
+ tvm_ctx.device_type = kDLROCM;
+ tvm_ctx.device_id = 0;
+ tvm::runtime::DeviceAPI* api = tvm::runtime::DeviceAPI::Get(tvm_ctx, true);
+ if (api != nullptr) {
+ TVMRetValue val;
+ api->GetAttr(tvm_ctx, tvm::runtime::kExist, &val);
+ if (val.operator int() == 1) {
+ tvm::runtime::DeviceAPI::Get(tvm_ctx)->
+ GetAttr(tvm_ctx, tvm::runtime::kMaxThreadsPerBlock, &val);
+ return val.operator int();
+ }
+ }
+ LOG(WARNING) << "Cannot get maximum number of threads for AMD codegen";
+ return 1024;
Review comment:
But this is the max workgroup size at compile time, so the kernels will use
fewer VGPRs when set larger.
Personally, I'd have half a mind to make it a LOG(FATAL).
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
