2be8054b49
This makes one substantive change and a few stylistic changes to the VSX swap optimization pass. The substantive change is to permit LXSDX and LXSSPX instructions to participate in swap optimization computations. The previous change to insert a swap following a SUBREG_TO_REG widening operation makes this almost trivial. I experimented with also permitting STXSDX and STXSSPX instructions. This can be done using similar techniques: we could insert a swap prior to a narrowing COPY operation, and then permit these stores to participate. I prototyped this, but discovered that the pattern of a narrowing COPY followed by an STXSDX does not occur in any of our test-suite code. So instead, I added commentary indicating that this could be done. Other TLC: - I changed SH_COPYSCALAR to SH_COPYWIDEN to more clearly indicate the direction of the copy. - I factored the insertion of swap instructions into a separate function. Finally, I added a new test case to check that the scalar-to-vector loads are working properly with swap optimization. llvm-svn: 242838
45 lines
1.4 KiB
LLVM
45 lines
1.4 KiB
LLVM
; RUN: llc -mcpu=pwr8 -mtriple=powerpc64le-unknown-linux-gnu -O3 < %s | FileCheck %s
|
|
|
|
; These tests verify that VSX swap optimization works when loading a scalar
|
|
; into a vector register.
|
|
|
|
|
|
@x = global <2 x double> <double 9.970000e+01, double -1.032220e+02>, align 16
|
|
@z = global <2 x double> <double 2.332000e+01, double 3.111111e+01>, align 16
|
|
@y = global double 1.780000e+00, align 8
|
|
|
|
define void @bar0() {
|
|
entry:
|
|
%0 = load <2 x double>, <2 x double>* @x, align 16
|
|
%1 = load double, double* @y, align 8
|
|
%vecins = insertelement <2 x double> %0, double %1, i32 0
|
|
store <2 x double> %vecins, <2 x double>* @z, align 16
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: @bar0
|
|
; CHECK-DAG: lxvd2x [[REG1:[0-9]+]]
|
|
; CHECK-DAG: lxsdx [[REG2:[0-9]+]]
|
|
; CHECK: xxswapd [[REG3:[0-9]+]], [[REG2]]
|
|
; CHECK: xxspltd [[REG4:[0-9]+]], [[REG3]], 1
|
|
; CHECK: xxpermdi [[REG5:[0-9]+]], [[REG4]], [[REG1]], 1
|
|
; CHECK: stxvd2x [[REG5]]
|
|
|
|
define void @bar1() {
|
|
entry:
|
|
%0 = load <2 x double>, <2 x double>* @x, align 16
|
|
%1 = load double, double* @y, align 8
|
|
%vecins = insertelement <2 x double> %0, double %1, i32 1
|
|
store <2 x double> %vecins, <2 x double>* @z, align 16
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: @bar1
|
|
; CHECK-DAG: lxvd2x [[REG1:[0-9]+]]
|
|
; CHECK-DAG: lxsdx [[REG2:[0-9]+]]
|
|
; CHECK: xxswapd [[REG3:[0-9]+]], [[REG2]]
|
|
; CHECK: xxspltd [[REG4:[0-9]+]], [[REG3]], 1
|
|
; CHECK: xxmrghd [[REG5:[0-9]+]], [[REG1]], [[REG4]]
|
|
; CHECK: stxvd2x [[REG5]]
|
|
|