From c8a344e16acf6df8d402729da2e1dff7c5187633 Mon Sep 17 00:00:00 2001 From: Pawel Wodnicki Date: Mon, 19 Nov 2012 22:25:44 +0000 Subject: Merging r167948, r168198: into the 3.2 release branch r168198 [NVPTX] Order global variables in def-use order before emiting them in the final assembly r167948 [NVPTX] Implement custom lowering of loads/stores for i1 Loads from i1 become loads from i8 followed by trunc Stores to i1 become zext to i8 followed by store to i8 git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_32@168335 91177308-0d34-0410-b5e6-96231b3b80d8 --- test/CodeGen/NVPTX/global-ordering.ll | 20 ++++++++++++++++++++ test/CodeGen/NVPTX/pr13291-i1-store.ll | 26 ++++++++++++++++++++++++++ 2 files changed, 46 insertions(+) create mode 100644 test/CodeGen/NVPTX/global-ordering.ll create mode 100644 test/CodeGen/NVPTX/pr13291-i1-store.ll (limited to 'test') diff --git a/test/CodeGen/NVPTX/global-ordering.ll b/test/CodeGen/NVPTX/global-ordering.ll new file mode 100644 index 0000000000..43394a79e9 --- /dev/null +++ b/test/CodeGen/NVPTX/global-ordering.ll @@ -0,0 +1,20 @@ +; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s --check-prefix=PTX32 +; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 | FileCheck %s --check-prefix=PTX64 + +; Make sure we emit these globals in def-use order + + +; PTX32: .visible .global .align 1 .u8 a = 2; +; PTX32-NEXT: .visible .global .align 4 .u32 a2 = a; +; PTX64: .visible .global .align 1 .u8 a = 2; +; PTX64-NEXT: .visible .global .align 8 .u64 a2 = a; +@a2 = addrspace(1) global i8 addrspace(1)* @a +@a = addrspace(1) global i8 2 + + +; PTX32: .visible .global .align 1 .u8 b = 1; +; PTX32-NEXT: .visible .global .align 4 .u32 b2[2] = {b, b}; +; PTX64: .visible .global .align 1 .u8 b = 1; +; PTX64-NEXT: .visible .global .align 8 .u64 b2[2] = {b, b}; +@b2 = addrspace(1) global [2 x i8 addrspace(1)*] [i8 addrspace(1)* @b, i8 addrspace(1)* @b] +@b = addrspace(1) global i8 1 diff --git a/test/CodeGen/NVPTX/pr13291-i1-store.ll b/test/CodeGen/NVPTX/pr13291-i1-store.ll new file mode 100644 index 0000000000..779f7798d8 --- /dev/null +++ b/test/CodeGen/NVPTX/pr13291-i1-store.ll @@ -0,0 +1,26 @@ +; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s --check-prefix=PTX32 +; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 | FileCheck %s --check-prefix=PTX64 + +define ptx_kernel void @t1(i1* %a) { +; PTX32: mov.u16 %rc{{[0-9]+}}, 0; +; PTX32-NEXT: st.u8 [%r{{[0-9]+}}], %rc{{[0-9]+}}; +; PTX64: mov.u16 %rc{{[0-9]+}}, 0; +; PTX64-NEXT: st.u8 [%rl{{[0-9]+}}], %rc{{[0-9]+}}; + store i1 false, i1* %a + ret void +} + + +define ptx_kernel void @t2(i1* %a, i8* %b) { +; PTX32: ld.u8 %rc{{[0-9]+}}, [%r{{[0-9]+}}] +; PTX32: and.b16 temp, %rc{{[0-9]+}}, 1; +; PTX32: setp.b16.eq %p{{[0-9]+}}, temp, 1; +; PTX64: ld.u8 %rc{{[0-9]+}}, [%rl{{[0-9]+}}] +; PTX64: and.b16 temp, %rc{{[0-9]+}}, 1; +; PTX64: setp.b16.eq %p{{[0-9]+}}, temp, 1; + + %t1 = load i1* %a + %t2 = select i1 %t1, i8 1, i8 2 + store i8 %t2, i8* %b + ret void +} -- cgit v1.2.3