mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-23 13:02:52 +02:00
7d64810efd
The benchmarking summarized in http://lists.llvm.org/pipermail/llvm-dev/2017-May/113525.html showed this is beneficial for a wide range of cores. As is to be expected, quite a few small adaptations are needed to the regressions tests, as the difference in scheduling results in: - Quite a few small instruction schedule differences. - A few changes in register allocation decisions caused by different instruction schedules. - A few changes in IfConversion decisions, due to a difference in instruction schedule and/or the estimated cost of a branch mispredict. llvm-svn: 306514
60 lines
1.9 KiB
LLVM
60 lines
1.9 KiB
LLVM
; RUN: llc -mtriple=arm-eabi %s -o - | FileCheck %s
|
|
|
|
define i64 @test_shl(i64 %val, i64 %amt) {
|
|
; CHECK-LABEL: test_shl:
|
|
; First calculate the hi part when the shift amount is small enough that it
|
|
; contains components from both halves. It'll be returned in r1 so that's a
|
|
; reasonable place for it to end up.
|
|
; CHECK: rsb [[REVERSE_SHIFT:.*]], r2, #32
|
|
; CHECK: lsr [[TMP:.*]], r0, [[REVERSE_SHIFT]]
|
|
; CHECK: orr r1, [[TMP]], r1, lsl r2
|
|
|
|
; Check whether the shift was in fact small (< 32 bits).
|
|
; CHECK: sub [[EXTRA_SHIFT:.*]], r2, #32
|
|
; CHECK: cmp [[EXTRA_SHIFT]], #0
|
|
|
|
; If not, the high part of the answer is just the low part shifted by the
|
|
; excess.
|
|
; CHECK: lslge r1, r0, [[EXTRA_SHIFT]]
|
|
|
|
; The low part is either a direct shift (1st inst) or 0. We can reuse the same
|
|
; NZCV.
|
|
; CHECK: lsl r0, r0, r2
|
|
; CHECK: movge r0, #0
|
|
|
|
%res = shl i64 %val, %amt
|
|
ret i64 %res
|
|
}
|
|
|
|
; Explanation for lshr is pretty much the reverse of shl.
|
|
define i64 @test_lshr(i64 %val, i64 %amt) {
|
|
; CHECK-LABEL: test_lshr:
|
|
; CHECK: rsb [[REVERSE_SHIFT:.*]], r2, #32
|
|
; CHECK: lsr r0, r0, r2
|
|
; CHECK: orr r0, r0, r1, lsl [[REVERSE_SHIFT]]
|
|
; CHECK: sub [[EXTRA_SHIFT:.*]], r2, #32
|
|
; CHECK: cmp [[EXTRA_SHIFT]], #0
|
|
; CHECK: lsrge r0, r1, [[EXTRA_SHIFT]]
|
|
; CHECK: lsr r1, r1, r2
|
|
; CHECK: movge r1, #0
|
|
%res = lshr i64 %val, %amt
|
|
ret i64 %res
|
|
}
|
|
|
|
; One minor difference for ashr: the high bits must be "hi >> 31" if the shift
|
|
; amount is large to get the right sign bit.
|
|
define i64 @test_ashr(i64 %val, i64 %amt) {
|
|
; CHECK-LABEL: test_ashr:
|
|
; CHECK: sub [[EXTRA_SHIFT:.*]], r2, #32
|
|
; CHECK: asr [[HI_TMP:.*]], r1, r2
|
|
; CHECK: lsr r0, r0, r2
|
|
; CHECK: rsb [[REVERSE_SHIFT:.*]], r2, #32
|
|
; CHECK: cmp [[EXTRA_SHIFT]], #0
|
|
; CHECK: orr r0, r0, r1, lsl [[REVERSE_SHIFT]]
|
|
; CHECK: asrge [[HI_TMP]], r1, #31
|
|
; CHECK: asrge r0, r1, [[EXTRA_SHIFT]]
|
|
; CHECK: mov r1, [[HI_TMP]]
|
|
%res = ashr i64 %val, %amt
|
|
ret i64 %res
|
|
}
|