RPCSX/llvm
1
0
Fork 0
mirror of https://github.com/RPCSX/llvm.git synced 2025-01-24 05:09:34 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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
This commit is contained in:
Mark Heffernan 2015-08-11 22:16:34 +00:00
parent bbf32bd275
commit 67278b1774
2 changed files with 84 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
lib/Target/NVPTX/NVPTXISelLowering.cpp
View File

@ -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);

80
test/CodeGen/NVPTX/bypass-div.ll Normal file
View File

@ -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
}