Use 32-bit divides instead of 64-bit divides where possible.

For NVPTX, try to use 32-bit division instead of 64-bit division when the dividend and divisor
fit in 32 bits. This speeds up some internal benchmarks significantly. The underlying reason
is that many index computations are carried out in 64-bits but never actually exceed the
capacity of a 32-bit word.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@244684 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/NVPTX/NVPTXISelLowering.cpp b/lib/Target/NVPTX/NVPTXISelLowering.cpp
index 98ecd3b782a71559128b5c098289f02e98893763..724d7bce16ae067821fc1c514a0d84b620eec47f 100644 (file)
--- a/lib/Target/NVPTX/NVPTXISelLowering.cpp
+++ b/lib/Target/NVPTX/NVPTXISelLowering.cpp
@@ -124,6 +124,10 @@ NVPTXTargetLowering::NVPTXTargetLowering(const NVPTXTargetMachine &TM,
   // condition branches.
   setJumpIsExpensive(true);
 
+  // Wide divides are _very_ slow. Try to reduce the width of the divide if
+  // possible.
+  addBypassSlowDiv(64, 32);
+
   // By default, use the Source scheduling
   if (sched4reg)
     setSchedulingPreference(Sched::RegPressure);

diff --git a/test/CodeGen/NVPTX/bypass-div.ll b/test/CodeGen/NVPTX/bypass-div.ll
new file mode 100644 (file)
index 0000000..bd98c9a
--- /dev/null
+++ b/test/CodeGen/NVPTX/bypass-div.ll
@@ -0,0 +1,80 @@
+; RUN: llc < %s -march=nvptx -mcpu=sm_35 | FileCheck %s
+
+; 64-bit divides and rems should be split into a fast and slow path where
+; the fast path uses a 32-bit operation.
+
+define void @sdiv64(i64 %a, i64 %b, i64* %retptr) {
+; CHECK-LABEL: sdiv64(
+; CHECK:        div.s64
+; CHECK:        div.u32
+; CHECK:        ret
+  %d = sdiv i64 %a, %b
+  store i64 %d, i64* %retptr
+  ret void
+}
+
+define void @udiv64(i64 %a, i64 %b, i64* %retptr) {
+; CHECK-LABEL: udiv64(
+; CHECK:        div.u64
+; CHECK:        div.u32
+; CHECK:        ret
+  %d = udiv i64 %a, %b
+  store i64 %d, i64* %retptr
+  ret void
+}
+
+define void @srem64(i64 %a, i64 %b, i64* %retptr) {
+; CHECK-LABEL: srem64(
+; CHECK:        rem.s64
+; CHECK:        rem.u32
+; CHECK:        ret
+  %d = srem i64 %a, %b
+  store i64 %d, i64* %retptr
+  ret void
+}
+
+define void @urem64(i64 %a, i64 %b, i64* %retptr) {
+; CHECK-LABEL: urem64(
+; CHECK:        rem.u64
+; CHECK:        rem.u32
+; CHECK:        ret
+  %d = urem i64 %a, %b
+  store i64 %d, i64* %retptr
+  ret void
+}
+
+define void @sdiv32(i32 %a, i32 %b, i32* %retptr) {
+; CHECK-LABEL: sdiv32(
+; CHECK: div.s32
+; CHECK-NOT: div.
+  %d = sdiv i32 %a, %b
+  store i32 %d, i32* %retptr
+  ret void
+}
+
+define void @udiv32(i32 %a, i32 %b, i32* %retptr) {
+; CHECK-LABEL: udiv32(
+; CHECK: div.u32
+; CHECK-NOT: div.
+  %d = udiv i32 %a, %b
+  store i32 %d, i32* %retptr
+  ret void
+}
+
+define void @srem32(i32 %a, i32 %b, i32* %retptr) {
+; CHECK-LABEL: srem32(
+; CHECK: rem.s32
+; CHECK-NOT: rem.
+  %d = srem i32 %a, %b
+  store i32 %d, i32* %retptr
+  ret void
+}
+
+define void @urem32(i32 %a, i32 %b, i32* %retptr) {
+; CHECK-LABEL: urem32(
+; CHECK: rem.u32
+; CHECK-NOT: rem.
+  %d = urem i32 %a, %b
+  store i32 %d, i32* %retptr
+  ret void
+}