From 80cdbed4382792460f67b8feca5278cb0eed78bc Mon Sep 17 00:00:00 2001
From: foreman
Date: Sat, 19 Mar 2016 00:43:22 -0400
Subject: [PATCH] P4 to Git Change 1249103 by smekhano@stas-rampitec-hsa on
2016/03/19 00:35:23
SWDEV-77584 - HSA HLC: constant fold get_local_size() with reqd_work_group_size attribute
Testing: smoke, precheckin, conformance non_uniform_work_group
Reviewed by Valery Pykhtin
Affected files ...
... //depot/stg/opencl/drivers/opencl/compiler/lib/backends/common/optimizer.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/compiler/llvm/include/llvm/AMDUtils.h#5 edit
... //depot/stg/opencl/drivers/opencl/compiler/llvm/include/llvm/Transforms/AMDIntrinsic.h#5 edit
... //depot/stg/opencl/drivers/opencl/compiler/llvm/include/llvm/Transforms/AMDMetadataUtils.h#4 edit
... //depot/stg/opencl/drivers/opencl/compiler/llvm/include/llvm/Transforms/Utils/AMDLibCalls.h#37 edit
... //depot/stg/opencl/drivers/opencl/compiler/llvm/lib/Target/HSAIL/HSAILKernelManager.cpp#53 edit
... //depot/stg/opencl/drivers/opencl/compiler/llvm/lib/Transforms/IntrinsicUtils/AMDIntrinsic.src_cpp#8 edit
... //depot/stg/opencl/drivers/opencl/compiler/llvm/lib/Transforms/SPIR/AMDMetadataUtils.cpp#6 edit
... //depot/stg/opencl/drivers/opencl/compiler/llvm/lib/Transforms/Utils/AMDLibCalls.cpp#61 edit
... //depot/stg/opencl/drivers/opencl/compiler/llvm/lib/Transforms/Utils/AMDUtils.cpp#9 edit
... //depot/stg/opencl/drivers/opencl/tests/hsa/src/ocl/features/metadata/local_size_reqd.cl#1 add
... //depot/stg/opencl/drivers/opencl/tests/hsa/src/ocl/features/metadata/local_size_reqd_intr.cl#1 add
... //depot/stg/opencl/drivers/opencl/tests/hsa/tlst/llc_opt.tlst#87 edit
... //depot/stg/opencl/drivers/opencl/tests/hsa/tlst/ocl_features.tlst#53 edit
---
rocclr/compiler/lib/backends/common/optimizer.cpp | 2 ++
1 file changed, 2 insertions(+)
diff --git a/rocclr/compiler/lib/backends/common/optimizer.cpp b/rocclr/compiler/lib/backends/common/optimizer.cpp
index 77df3988d6..6fa561e647 100644
--- a/rocclr/compiler/lib/backends/common/optimizer.cpp
+++ b/rocclr/compiler/lib/backends/common/optimizer.cpp
@@ -77,6 +77,7 @@ CPUOptimizer::optimize(llvm::Module *input)
start_time = amd::Os::timeNanos();
}
ret = preOptimizer(LLVMBinary());
+ setUniformWorkGroupSize(Options()->oVariables->UniformWorkGroupSize);
OptLevel* cpuOpt = getOptLevel(Options(), false);
if (Options()->oVariables->EnableBuildTiming) {
time_opt = amd::Os::timeNanos();
@@ -139,6 +140,7 @@ GPUOptimizer::optimize(llvm::Module *input)
hookup_.amdoptions.NumAvailGPRs = Options()->NumAvailGPRs;
}
#endif
+ setUniformWorkGroupSize(Options()->oVariables->UniformWorkGroupSize);
OptLevel* gpuOpt = getOptLevel(Options(), true);
if (Options()->oVariables->EnableBuildTiming) {
time_opt = amd::Os::timeNanos();