The energy costs of data movement are limiting the performance scaling of future generations of high performance computing architectures targeted to data intensive applications. The result has been a resurgence in the interest in processing-in-memory (PIM) architectures. This challenge has spawned the development of a scalable, parametric data parallel architecture referred at the Heterogeneous Architecture Research Prototype (HARP) - a single instruction multiple thread (SIMT) architecture for integration into DRAM systems, particularly 3D memory stacks as a distinct processing layer to exploit the enormous internal memory bandwidth. However, this potential can only be realized with an optimizing compilation environment. This thesis addresses this challenge by i) the construction of an open source compiler for HARP, and ii) integrating optimizations for handling control flow divergence for HARP instances. The HARP compiler is built using the LLVM open source compiler infrastructure. Apart from traditional code generation, the HARP compiler backend handles unique challenges associated with the HARP instruction set. Chief among them is code generation for control divergence management techniques. The HARP architecture and compiler supports i) a hardware reconvergence stack and ii) predication to handle divergent branches. The HARP compiler addresses several challenges associated with generating code for these two control divergence management techniques and implements multiple analyses and transformations for code generation. Both of these techniques have unique advantages and disadvantages depending upon whether the conditional branch is likely to be unanimous or not. Two decision frameworks, guided by static analysis and dynamic profile information are implemented to choose between the control divergence management techniques by analyzing the nature of the conditional branches and utilizing this information during compilation.

This study investigates the moderating role of the agency conflict between controlling and minority shareholders on the investment-risk relationship. When the ownership-control structure is concentrated, the agency theory indicates that the separation between cash-flow rights and voting rights induces the controlling shareholder to extract private benefits. To assess the effect of ownership-control divergence on the investment-risk relation, we use system generalized method of moments estimator (SYS-GMM) in longitudinal data from 412 Brazilian firms between 1997 and 2010. Our results show that investment is less sensitive to idiosyncratic risk for companies in which the largest shareholder presents high levels of ownership-control divergence. The impact of excess voting rights on the investment-risk sensitivity holds after we group firms according to distinct corporate governance and financial characteristics, such as financial constraints, family control, board independence, and the type of control-enhancing mechanism. Board independence does not affect controlling shareholders\' behavior toward risky investments. Among the control-enhancing mechanisms, the issuance of dual class shares is the main driver of the lower investment sensitivity to idiosyncratic risk. Our findings are consistent with entrenchment effects in the sense that dominant shareholders may select riskier projects when investing other people\'s money, which have both managerial and policy implications. / Este estudo investiga o papel moderador do conflito de agência entre acionistas controladores e minoritários no relacionamento investimento-risco. Quando a estrutura de propriedade e controle é concentrada, a teoria da agência indica que a separação entre direitos de fluxo de caixa e direitos de voto induz o acionista controlador a extrair benefícios privados. Para avaliar o efeito da divergência propriedade-controle na relação investimento-risco, utilizamos o estimador de método dos momentos generalizado sistêmico (MMG-SIS) em dados longitudinais de 412 empresas brasileiras entre 1997 e 2010. Nossos resultados mostram que o investimento é menos sensível ao risco idiossincrático para empresas em que o maior acionista apresenta altos níveis de divergência propriedade-controle. O impacto dos direitos de voto em excesso na sensibilidade investimento-risco mantém-se após agruparmos as empresas de acordo com características de governança corporativa e financeiras, tais como restrições financeiras, controle familiar, independência do conselho e o tipo de mecanismo para aumento do controle. A independência do conselho não afeta o comportamento dos acionistas controladores em relação a investimentos arriscados. Entre os mecanismos para aumento do controle, a emissão de duas classes de ações é a principal direcionadora da menor sensibilidade do investimento ao risco idiossincrático. Nossas descobertas são consistentes com os efeitos de entrincheiramento no sentido de que os acionistas dominantes podem selecionar projetos mais arriscados ao investirem o dinheiro de outras pessoas, o que tem implicações gerenciais e políticas.

There has been a tremendous growth in the use of Graphics Processing Units (GPU) for the acceleration of general purpose applications. The growth is primarily due to the huge computing power offered by the GPUs and the emergence of programming languages such as CUDA and OpenCL. A typical GPU consists of several 100s to a few 1000s of Single Instruction Multiple Data (SIMD) cores, organized as 10s of Streaming Multiprocessors (SMs), each having several SIMD cores which operate in a lock-step manner, o ering a few TeraFLOPS of performance in a single socket. SMs execute instructions from a group of consecutive threads, called warps. At each cycle, an SM schedules a warp from a group of active warps and can context switch among the active warps to hide various stalls. However, various factors, such as global memory latency, divergence among warps of a thread block (TB), branch divergence among threads of a warp (Control Divergence), number of active warps, etc., can significantly impact the ability of a warp scheduler to hide stalls. This reduces the speedup of applications running on the GPU. Further, applications containing loops with potential cross iteration dependences, do not utilize the available resources (SIMD cores) effectively and hence su er in terms of performance. In this thesis, we propose several mechanisms which address the above issues and enhance the performance of GPU applications through efficient warp scheduling, taming branch and warp divergence, and runtime parallelization. First, we propose RLWS, a Reinforcement Learning (RL) based Warp Scheduler which uses unsupervised learning to schedule warps based on the current state of the core and the long-term benefits of scheduling actions. As the design space involving the state variables used by the RL and the RL parameters (such as learning and exploration rates, reward and penalty values, etc.) is large, we use a Genetic Algorithm to identify the useful subset of state variables and RL parameter values. We evaluated the proposed RL based scheduler using the GPGPU-SIM simulator on a large number of applications from the Rodinia, Parboil, CUDA-SDK and GPGPU-SIM benchmark suites. Our RL based implementation achieved an average speedup of 1.06x over the Loose Round Robin (LRR) strategy and 1.07x over the Two-Level (TL) strategy. A salient feature of RLWS is that it is robust, i.e., performs nearly as well as the best performing warp scheduler, consistently across a wide range of applications. Using the insights obtained from RLWS, we designed PRO, a heuristic warp scheduler which in addition to hiding the long latencies of certain operations, reduces the waiting time of warps at synchronization points. Evaluation of the proposed algorithm using the GPGPU-SIM simulator on a diverse set of applications showed an average speedup of 1.07x over the LRR warp scheduler and 1.08x over the TL warp scheduler. In the second part of the thesis, we address problems due to warp and branch divergences. First, many GPU kernels exhibit warp divergence due to various reasons such as, different amounts of work, cache misses, and thread divergence. Also, we observed that some kernels contain code which is redundant across TBs, i.e., all TBs will execute the code identically and hence compute the same results. To improve performance of such kernels, we propose a solution based on the concept of virtual TBs and loop independent code motion. We propose necessary code transformations which enable one virtual TB to execute the kernel code for multiple real TBs. We evaluated this technique using the GPGPU-SIM simulator on a diverse set of applications and observed an average improvement of 1.08x over the LRR and 1.04x over the Greedy Then Old (GTO) warp scheduling algorithms. Second, branch divergence causes execution of diverging branches to be serialized to execute only one control ow path at a time. Existing stack based hardware mechanism to reconverge threads causes duplicate execution of code for unstructured control ow graphs (CFG). We propose a simple and elegant transformation to convert an unstructured CFG to a structured CFG. The transformation eliminates duplicate execution of user code while incurring only a linear increase in the number of basic blocks and also the number of instructions. We implemented the proposed transformation at the PTX level using the Ocelot compiler infrastructure and demonstrate that the pro-posed technique is effective in handling the performance problem due to divergence in unstructured CFGs. Our third proposal is to enable efficient execution of loops with indirect memory accesses that can potentially cause cross iteration dependences. Such dependences are hard to detect using existing compilation techniques. We present an algorithm to compute at run-time, the cross iteration dependences in such loops, using both the CPU and the GPU. It effectively uses the compute capabilities of the GPU to collect the memory accesses performed by the iterations. Using the dependence information, the loop iterations are levelized such that each level contains independent iterations which can be executed in parallel. Experimental evaluation on real hardware (NVIDIA GPUs) reveals that the proposed technique can achieve an average speedup of 6.4x on loops with a reasonable number of cross iteration dependences.

This study investigates the moderating role of the agency conflict between controlling and minority shareholders on the investment-risk relationship. When the ownership-control structure is concentrated, the agency theory indicates that the separation between cash-flow rights and voting rights induces the controlling shareholder to extract private benefits. To assess the effect of ownership-control divergence on the investment-risk relation, we use system generalized method of moments estimator (SYS-GMM) in longitudinal data from 412 Brazilian firms between 1997 and 2010. Our results show that investment is less sensitive to idiosyncratic risk for companies in which the largest shareholder presents high levels of ownership-control divergence. The impact of excess voting rights on the investment-risk sensitivity holds after we group firms according to distinct corporate governance and financial characteristics, such as financial constraints, family control, board independence, and the type of control-enhancing mechanism. Board independence does not affect controlling shareholders\' behavior toward risky investments. Among the control-enhancing mechanisms, the issuance of dual class shares is the main driver of the lower investment sensitivity to idiosyncratic risk. Our findings are consistent with entrenchment effects in the sense that dominant shareholders may select riskier projects when investing other people\'s money, which have both managerial and policy implications. / Este estudo investiga o papel moderador do conflito de agência entre acionistas controladores e minoritários no relacionamento investimento-risco. Quando a estrutura de propriedade e controle é concentrada, a teoria da agência indica que a separação entre direitos de fluxo de caixa e direitos de voto induz o acionista controlador a extrair benefícios privados. Para avaliar o efeito da divergência propriedade-controle na relação investimento-risco, utilizamos o estimador de método dos momentos generalizado sistêmico (MMG-SIS) em dados longitudinais de 412 empresas brasileiras entre 1997 e 2010. Nossos resultados mostram que o investimento é menos sensível ao risco idiossincrático para empresas em que o maior acionista apresenta altos níveis de divergência propriedade-controle. O impacto dos direitos de voto em excesso na sensibilidade investimento-risco mantém-se após agruparmos as empresas de acordo com características de governança corporativa e financeiras, tais como restrições financeiras, controle familiar, independência do conselho e o tipo de mecanismo para aumento do controle. A independência do conselho não afeta o comportamento dos acionistas controladores em relação a investimentos arriscados. Entre os mecanismos para aumento do controle, a emissão de duas classes de ações é a principal direcionadora da menor sensibilidade do investimento ao risco idiossincrático. Nossas descobertas são consistentes com os efeitos de entrincheiramento no sentido de que os acionistas dominantes podem selecionar projetos mais arriscados ao investirem o dinheiro de outras pessoas, o que tem implicações gerenciais e políticas.