[NVPTX] Implemented bar.warp.sync, barrier.sync, and vote{.sync} instructions/intrinsics/builtins.

Differential Revision: https://reviews.llvm.org/D38148

llvm-svn: 313898

2 files changed, 97 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/NVPTX/barrier.ll b/llvm/test/CodeGen/NVPTX/barrier.ll
new file mode 100644
index 00000000000..0bca04e6dda
--- /dev/null
+++ b/llvm/test/CodeGen/NVPTX/barrier.ll
@@ -0,0 +1,32 @@
+; RUN: llc < %s -march=nvptx64 -mcpu=sm_30 -mattr=+ptx60 | FileCheck %s
+
+declare void @llvm.nvvm.bar.warp.sync(i32)
+declare void @llvm.nvvm.barrier.sync(i32)
+declare void @llvm.nvvm.barrier.sync.cnt(i32, i32)
+
+; CHECK-LABEL: .func{{.*}}barrier.sync
+define void @barrier.sync(i32 %id, i32 %cnt) {
+  ; CHECK: ld.param.u32 	[[ID:%r[0-9]+]], [barrier.sync_param_0];
+  ; CHECK: ld.param.u32 	[[CNT:%r[0-9]+]], [barrier.sync_param_1];
+
+  ; CHECK:  barrier.sync [[ID]], [[CNT]];
+  call void @llvm.nvvm.barrier.sync.cnt(i32 %id, i32 %cnt)
+  ; CHECK:  barrier.sync [[ID]], 2;
+  call void @llvm.nvvm.barrier.sync.cnt(i32 %id, i32 2)
+  ; CHECK:  barrier.sync 3, [[CNT]];
+  call void @llvm.nvvm.barrier.sync.cnt(i32 3, i32 %cnt)
+  ; CHECK:  barrier.sync 4, 5;
+  call void @llvm.nvvm.barrier.sync.cnt(i32 4, i32 5)
+
+  ; CHECK: barrier.sync [[ID]];
+  call void @llvm.nvvm.barrier.sync(i32 %id)
+  ; CHECK: barrier.sync 1;
+  call void @llvm.nvvm.barrier.sync(i32 1)
+
+  ; CHECK: bar.warp.sync [[ID]];
+  call void @llvm.nvvm.bar.warp.sync(i32 %id)
+  ; CHECK: bar.warp.sync 6;
+  call void @llvm.nvvm.bar.warp.sync(i32 6)
+  ret void;
+}
+
diff --git a/llvm/test/CodeGen/NVPTX/vote.ll b/llvm/test/CodeGen/NVPTX/vote.ll
new file mode 100644
index 00000000000..c28e795fe57
--- /dev/null
+++ b/llvm/test/CodeGen/NVPTX/vote.ll
@@ -0,0 +1,65 @@
+; RUN: llc < %s -march=nvptx64 -mcpu=sm_30 -mattr=+ptx60 | FileCheck %s
+
+declare i1 @llvm.nvvm.vote.all(i1)
+; CHECK-LABEL: .func{{.*}}vote.all
+define i1 @vote.all(i1 %pred) {
+  ; CHECK: vote.all.pred
+  %val = call i1 @llvm.nvvm.vote.all(i1 %pred)
+  ret i1 %val
+}
+
+declare i1 @llvm.nvvm.vote.any(i1)
+; CHECK-LABEL: .func{{.*}}vote.any
+define i1 @vote.any(i1 %pred) {
+  ; CHECK: vote.any.pred
+  %val = call i1 @llvm.nvvm.vote.any(i1 %pred)
+  ret i1 %val
+}
+
+declare i1 @llvm.nvvm.vote.uni(i1)
+; CHECK-LABEL: .func{{.*}}vote.uni
+define i1 @vote.uni(i1 %pred) {
+  ; CHECK: vote.uni.pred
+  %val = call i1 @llvm.nvvm.vote.uni(i1 %pred)
+  ret i1 %val
+}
+
+declare i32 @llvm.nvvm.vote.ballot(i1)
+; CHECK-LABEL: .func{{.*}}vote.ballot
+define i32 @vote.ballot(i1 %pred) {
+  ; CHECK: vote.ballot.b32
+  %val = call i32 @llvm.nvvm.vote.ballot(i1 %pred)
+  ret i32 %val
+}
+
+declare i1 @llvm.nvvm.vote.all.sync(i32, i1)
+; CHECK-LABEL: .func{{.*}}vote.sync.all
+define i1 @vote.sync.all(i32 %mask, i1 %pred) {
+  ; CHECK: vote.sync.all.pred
+  %val = call i1 @llvm.nvvm.vote.all.sync(i32 %mask, i1 %pred)
+  ret i1 %val
+}
+
+declare i1 @llvm.nvvm.vote.any.sync(i32, i1)
+; CHECK-LABEL: .func{{.*}}vote.sync.any
+define i1 @vote.sync.any(i32 %mask, i1 %pred) {
+  ; CHECK: vote.sync.any.pred
+  %val = call i1 @llvm.nvvm.vote.any.sync(i32 %mask, i1 %pred)
+  ret i1 %val
+}
+
+declare i1 @llvm.nvvm.vote.uni.sync(i32, i1)
+; CHECK-LABEL: .func{{.*}}vote.sync.uni
+define i1 @vote.sync.uni(i32 %mask, i1 %pred) {
+  ; CHECK: vote.sync.uni.pred
+  %val = call i1 @llvm.nvvm.vote.uni.sync(i32 %mask, i1 %pred)
+  ret i1 %val
+}
+
+declare i32 @llvm.nvvm.vote.ballot.sync(i32, i1)
+; CHECK-LABEL: .func{{.*}}vote.sync.ballot
+define i32 @vote.sync.ballot(i32 %mask, i1 %pred) {
+  ; CHECK: vote.sync.ballot.b32
+  %val = call i32 @llvm.nvvm.vote.ballot.sync(i32 %mask, i1 %pred)
+  ret i32 %val
+}