cmd/compile: add SSA rules for s390x compare-and-branch instructions

This commit adds SSA rules for the s390x combined compare-and-branch
instructions. These have a shorter encoding than separate compare
and branch instructions and they also don't clobber the condition
code (a.k.a. flag register) reducing pressure on the flag allocator.

I have deleted the 'loop_test.go' file and replaced it with a new
codegen test which performs a wider range of checks.

Object sizes from compilebench:

name                      old object-bytes  new object-bytes  delta
Template                        562kB ± 0%        561kB ± 0%   -0.28%  (p=0.000 n=10+10)
Unicode                         217kB ± 0%        217kB ± 0%   -0.17%  (p=0.000 n=10+10)
GoTypes                        2.03MB ± 0%       2.02MB ± 0%   -0.59%  (p=0.000 n=10+10)
Compiler                       8.16MB ± 0%       8.11MB ± 0%   -0.62%  (p=0.000 n=10+10)
SSA                            27.4MB ± 0%       27.0MB ± 0%   -1.45%  (p=0.000 n=10+10)
Flate                           356kB ± 0%        356kB ± 0%   -0.12%  (p=0.000 n=10+10)
GoParser                        438kB ± 0%        436kB ± 0%   -0.51%  (p=0.000 n=10+10)
Reflect                        1.37MB ± 0%       1.37MB ± 0%   -0.42%  (p=0.000 n=10+10)
Tar                             485kB ± 0%        483kB ± 0%   -0.39%  (p=0.000 n=10+10)
XML                             630kB ± 0%        621kB ± 0%   -1.45%  (p=0.000 n=10+10)
[Geo mean]                     1.14MB            1.13MB        -0.60%

name                      old text-bytes    new text-bytes    delta
HelloSize                       763kB ± 0%        754kB ± 0%   -1.30%  (p=0.000 n=10+10)
CmdGoSize                      10.7MB ± 0%       10.6MB ± 0%   -0.91%  (p=0.000 n=10+10)
[Geo mean]                     2.86MB            2.82MB        -1.10%

Change-Id: Ibca55d9c0aa1254aee69433731ab5d26a43a7c18
Reviewed-on: https://go-review.googlesource.com/c/go/+/198037
Run-TryBot: Michael Munday <mike.munday@ibm.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>

1 files changed, 154 insertions, 0 deletions

diff --git a/test/codegen/compare_and_branch.go b/test/codegen/compare_and_branch.go
new file mode 100644
index 0000000000..33d8d7bd52
--- /dev/null
+++ b/test/codegen/compare_and_branch.go
@@ -0,0 +1,154 @@
+// asmcheck
+
+// Copyright 2019 The Go Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style
+// license that can be found in the LICENSE file.
+
+package codegen
+
+//go:noinline
+func dummy() {}
+
+// Signed 64-bit compare-and-branch.
+func si64(x, y chan int64) {
+	// s390x:"CGRJ\t[$]4, R[0-9]+, R[0-9]+, "
+	for <-x < <-y {
+		dummy()
+	}
+
+	// s390x:"CL?GRJ\t[$]8, R[0-9]+, R[0-9]+, "
+	for <-x == <-y {
+		dummy()
+	}
+}
+
+// Signed 64-bit compare-and-branch with 8-bit immediate.
+func si64x8() {
+	// s390x:"CGIJ\t[$]12, R[0-9]+, [$]127, "
+	for i := int64(0); i < 128; i++ {
+		dummy()
+	}
+
+	// s390x:"CGIJ\t[$]10, R[0-9]+, [$]-128, "
+	for i := int64(0); i > -129; i-- {
+		dummy()
+	}
+
+	// s390x:"CGIJ\t[$]2, R[0-9]+, [$]127, "
+	for i := int64(0); i >= 128; i++ {
+		dummy()
+	}
+
+	// s390x:"CGIJ\t[$]4, R[0-9]+, [$]-128, "
+	for i := int64(0); i <= -129; i-- {
+		dummy()
+	}
+}
+
+// Unsigned 64-bit compare-and-branch.
+func ui64(x, y chan uint64) {
+	// s390x:"CLGRJ\t[$]2, R[0-9]+, R[0-9]+, "
+	for <-x > <-y {
+		dummy()
+	}
+
+	// s390x:"CL?GRJ\t[$]6, R[0-9]+, R[0-9]+, "
+	for <-x != <-y {
+		dummy()
+	}
+}
+
+// Unsigned 64-bit comparison with 8-bit immediate.
+func ui64x8() {
+	// s390x:"CLGIJ\t[$]4, R[0-9]+, [$]128, "
+	for i := uint64(0); i < 128; i++ {
+		dummy()
+	}
+
+	// s390x:"CLGIJ\t[$]12, R[0-9]+, [$]255, "
+	for i := uint64(0); i < 256; i++ {
+		dummy()
+	}
+
+	// s390x:"CLGIJ\t[$]2, R[0-9]+, [$]255, "
+	for i := uint64(0); i >= 256; i-- {
+		dummy()
+	}
+
+	// s390x:"CLGIJ\t[$]2, R[0-9]+, [$]0, "
+	for i := uint64(1024); i > 0; i-- {
+		dummy()
+	}
+}
+
+// Signed 32-bit compare-and-branch.
+func si32(x, y chan int32) {
+	// s390x:"CRJ\t[$]4, R[0-9]+, R[0-9]+, "
+	for <-x < <-y {
+		dummy()
+	}
+
+	// s390x:"CL?RJ\t[$]8, R[0-9]+, R[0-9]+, "
+	for <-x == <-y {
+		dummy()
+	}
+}
+
+// Signed 32-bit compare-and-branch with 8-bit immediate.
+func si32x8() {
+	// s390x:"CIJ\t[$]12, R[0-9]+, [$]127, "
+	for i := int32(0); i < 128; i++ {
+		dummy()
+	}
+
+	// s390x:"CIJ\t[$]10, R[0-9]+, [$]-128, "
+	for i := int32(0); i > -129; i-- {
+		dummy()
+	}
+
+	// s390x:"CIJ\t[$]2, R[0-9]+, [$]127, "
+	for i := int32(0); i >= 128; i++ {
+		dummy()
+	}
+
+	// s390x:"CIJ\t[$]4, R[0-9]+, [$]-128, "
+	for i := int32(0); i <= -129; i-- {
+		dummy()
+	}
+}
+
+// Unsigned 32-bit compare-and-branch.
+func ui32(x, y chan uint32) {
+	// s390x:"CLRJ\t[$]2, R[0-9]+, R[0-9]+, "
+	for <-x > <-y {
+		dummy()
+	}
+
+	// s390x:"CL?RJ\t[$]6, R[0-9]+, R[0-9]+, "
+	for <-x != <-y {
+		dummy()
+	}
+}
+
+// Unsigned 32-bit comparison with 8-bit immediate.
+func ui32x8() {
+	// s390x:"CLIJ\t[$]4, R[0-9]+, [$]128, "
+	for i := uint32(0); i < 128; i++ {
+		dummy()
+	}
+
+	// s390x:"CLIJ\t[$]12, R[0-9]+, [$]255, "
+	for i := uint32(0); i < 256; i++ {
+		dummy()
+	}
+
+	// s390x:"CLIJ\t[$]2, R[0-9]+, [$]255, "
+	for i := uint32(0); i >= 256; i-- {
+		dummy()
+	}
+
+	// s390x:"CLIJ\t[$]2, R[0-9]+, [$]0, "
+	for i := uint32(1024); i > 0; i-- {
+		dummy()
+	}
+}