• Josh Bleecher Snyder's avatar
    cmd/compile: make panicwrap argument-free · 2c91bb4c
    Josh Bleecher Snyder authored
    When code defines a method on T,
    the compiler generates a corresponding wrapper method on *T.
    The first thing the wrapper does is check whether
    the pointer is nil and if so, call panicwrap.
    This is done to provide a useful error message.
    
    The existing implementation gets its information
    from arguments set up by the compiler.
    However, with some trouble, this information can
    be extracted from the name of the wrapper method itself.
    
    Removing the arguments to panicwrap simplifies and
    shrinks the wrapper method.
    It also means that the call to panicwrap does not
    require any stack space.
    This enables a further optimization on amd64/x86,
    which is to skip the function prologue if nothing
    else in the method requires stack space.
    This is frequently the case in simple, hot methods,
    such as Less and Swap in sort.Interface implementations.
    
    Fixes #19040.
    
    Benchmarks for package sort on amd64:
    
    name                  old time/op  new time/op  delta
    SearchWrappers-8       104ns ± 1%   104ns ± 1%    ~     (p=0.286 n=27+27)
    SortString1K-8         128µs ± 1%   128µs ± 1%  -0.44%  (p=0.004 n=30+30)
    SortString1K_Slice-8   118µs ± 2%   117µs ± 1%    ~     (p=0.106 n=30+30)
    StableString1K-8      18.6µs ± 1%  18.6µs ± 1%    ~     (p=0.446 n=28+26)
    SortInt1K-8           65.9µs ± 1%  60.7µs ± 1%  -7.96%  (p=0.000 n=28+30)
    StableInt1K-8         75.3µs ± 2%  72.8µs ± 1%  -3.41%  (p=0.000 n=30+30)
    StableInt1K_Slice-8   57.7µs ± 1%  57.7µs ± 1%    ~     (p=0.515 n=30+30)
    SortInt64K-8          6.28ms ± 1%  6.01ms ± 1%  -4.19%  (p=0.000 n=28+28)
    SortInt64K_Slice-8    5.04ms ± 1%  5.04ms ± 1%    ~     (p=0.927 n=28+27)
    StableInt64K-8        6.65ms ± 1%  6.38ms ± 1%  -3.97%  (p=0.000 n=26+30)
    Sort1e2-8             37.9µs ± 1%  37.2µs ± 1%  -1.89%  (p=0.000 n=29+27)
    Stable1e2-8           77.0µs ± 1%  74.7µs ± 1%  -3.06%  (p=0.000 n=27+30)
    Sort1e4-8             8.21ms ± 2%  7.98ms ± 1%  -2.77%  (p=0.000 n=29+30)
    Stable1e4-8           24.8ms ± 1%  24.3ms ± 1%  -2.31%  (p=0.000 n=28+30)
    Sort1e6-8              1.27s ± 4%   1.22s ± 1%  -3.42%  (p=0.000 n=30+29)
    Stable1e6-8            5.06s ± 1%   4.92s ± 1%  -2.77%  (p=0.000 n=25+29)
    [Geo mean]             731µs        714µs       -2.29%
    
    Before/after assembly for sort.(*intPairs).Less follows.
    It can be optimized further, but that's for a follow-up CL.
    
    Before:
    
    "".(*intPairs).Less t=1 size=214 args=0x20 locals=0x38
    	0x0000 00000 (<autogenerated>:1)	TEXT	"".(*intPairs).Less(SB), $56-32
    	0x0000 00000 (<autogenerated>:1)	MOVQ	(TLS), CX
    	0x0009 00009 (<autogenerated>:1)	CMPQ	SP, 16(CX)
    	0x000d 00013 (<autogenerated>:1)	JLS	204
    	0x0013 00019 (<autogenerated>:1)	SUBQ	$56, SP
    	0x0017 00023 (<autogenerated>:1)	MOVQ	BP, 48(SP)
    	0x001c 00028 (<autogenerated>:1)	LEAQ	48(SP), BP
    	0x0021 00033 (<autogenerated>:1)	MOVQ	32(CX), BX
    	0x0025 00037 (<autogenerated>:1)	TESTQ	BX, BX
    	0x0028 00040 (<autogenerated>:1)	JEQ	55
    	0x002a 00042 (<autogenerated>:1)	LEAQ	64(SP), DI
    	0x002f 00047 (<autogenerated>:1)	CMPQ	(BX), DI
    	0x0032 00050 (<autogenerated>:1)	JNE	55
    	0x0034 00052 (<autogenerated>:1)	MOVQ	SP, (BX)
    	0x0037 00055 (<autogenerated>:1)	NOP
    	0x0037 00055 (<autogenerated>:1)	FUNCDATA	$0, gclocals·4032f753396f2012ad1784f398b170f4(SB)
    	0x0037 00055 (<autogenerated>:1)	FUNCDATA	$1, gclocals·69c1753bd5f81501d95132d08af04464(SB)
    	0x0037 00055 (<autogenerated>:1)	MOVQ	""..this+64(FP), AX
    	0x003c 00060 (<autogenerated>:1)	TESTQ	AX, AX
    	0x003f 00063 (<autogenerated>:1)	JEQ	$0, 135
    	0x0041 00065 (<autogenerated>:1)	MOVQ	(AX), CX
    	0x0044 00068 (<autogenerated>:1)	MOVQ	8(AX), AX
    	0x0048 00072 (<autogenerated>:1)	MOVQ	"".i+72(FP), DX
    	0x004d 00077 (<autogenerated>:1)	CMPQ	DX, AX
    	0x0050 00080 (<autogenerated>:1)	JCC	$0, 128
    	0x0052 00082 (<autogenerated>:1)	SHLQ	$4, DX
    	0x0056 00086 (<autogenerated>:1)	MOVQ	(CX)(DX*1), DX
    	0x005a 00090 (<autogenerated>:1)	MOVQ	"".j+80(FP), BX
    	0x005f 00095 (<autogenerated>:1)	CMPQ	BX, AX
    	0x0062 00098 (<autogenerated>:1)	JCC	$0, 128
    	0x0064 00100 (<autogenerated>:1)	SHLQ	$4, BX
    	0x0068 00104 (<autogenerated>:1)	MOVQ	(CX)(BX*1), AX
    	0x006c 00108 (<autogenerated>:1)	CMPQ	DX, AX
    	0x006f 00111 (<autogenerated>:1)	SETLT	AL
    	0x0072 00114 (<autogenerated>:1)	MOVB	AL, "".~r2+88(FP)
    	0x0076 00118 (<autogenerated>:1)	MOVQ	48(SP), BP
    	0x007b 00123 (<autogenerated>:1)	ADDQ	$56, SP
    	0x007f 00127 (<autogenerated>:1)	RET
    	0x0080 00128 (<autogenerated>:1)	PCDATA	$0, $1
    	0x0080 00128 (<autogenerated>:1)	CALL	runtime.panicindex(SB)
    	0x0085 00133 (<autogenerated>:1)	UNDEF
    	0x0087 00135 (<autogenerated>:1)	LEAQ	go.string."sort_test"(SB), AX
    	0x008e 00142 (<autogenerated>:1)	MOVQ	AX, (SP)
    	0x0092 00146 (<autogenerated>:1)	MOVQ	$9, 8(SP)
    	0x009b 00155 (<autogenerated>:1)	LEAQ	go.string."intPairs"(SB), AX
    	0x00a2 00162 (<autogenerated>:1)	MOVQ	AX, 16(SP)
    	0x00a7 00167 (<autogenerated>:1)	MOVQ	$8, 24(SP)
    	0x00b0 00176 (<autogenerated>:1)	LEAQ	go.string."Less"(SB), AX
    	0x00b7 00183 (<autogenerated>:1)	MOVQ	AX, 32(SP)
    	0x00bc 00188 (<autogenerated>:1)	MOVQ	$4, 40(SP)
    	0x00c5 00197 (<autogenerated>:1)	PCDATA	$0, $1
    	0x00c5 00197 (<autogenerated>:1)	CALL	runtime.panicwrap(SB)
    	0x00ca 00202 (<autogenerated>:1)	UNDEF
    	0x00cc 00204 (<autogenerated>:1)	NOP
    	0x00cc 00204 (<autogenerated>:1)	PCDATA	$0, $-1
    	0x00cc 00204 (<autogenerated>:1)	CALL	runtime.morestack_noctxt(SB)
    	0x00d1 00209 (<autogenerated>:1)	JMP	0
    
    After:
    
    "".(*intPairs).Swap t=1 size=147 args=0x18 locals=0x8
    	0x0000 00000 (<autogenerated>:1)	TEXT	"".(*intPairs).Swap(SB), $8-24
    	0x0000 00000 (<autogenerated>:1)	MOVQ	(TLS), CX
    	0x0009 00009 (<autogenerated>:1)	SUBQ	$8, SP
    	0x000d 00013 (<autogenerated>:1)	MOVQ	BP, (SP)
    	0x0011 00017 (<autogenerated>:1)	LEAQ	(SP), BP
    	0x0015 00021 (<autogenerated>:1)	MOVQ	32(CX), BX
    	0x0019 00025 (<autogenerated>:1)	TESTQ	BX, BX
    	0x001c 00028 (<autogenerated>:1)	JEQ	43
    	0x001e 00030 (<autogenerated>:1)	LEAQ	16(SP), DI
    	0x0023 00035 (<autogenerated>:1)	CMPQ	(BX), DI
    	0x0026 00038 (<autogenerated>:1)	JNE	43
    	0x0028 00040 (<autogenerated>:1)	MOVQ	SP, (BX)
    	0x002b 00043 (<autogenerated>:1)	NOP
    	0x002b 00043 (<autogenerated>:1)	FUNCDATA	$0, gclocals·e6397a44f8e1b6e77d0f200b4fba5269(SB)
    	0x002b 00043 (<autogenerated>:1)	FUNCDATA	$1, gclocals·69c1753bd5f81501d95132d08af04464(SB)
    	0x002b 00043 (<autogenerated>:1)	MOVQ	""..this+16(FP), AX
    	0x0030 00048 (<autogenerated>:1)	TESTQ	AX, AX
    	0x0033 00051 (<autogenerated>:1)	JEQ	$0, 140
    	0x0035 00053 (<autogenerated>:1)	MOVQ	(AX), CX
    	0x0038 00056 (<autogenerated>:1)	MOVQ	8(AX), AX
    	0x003c 00060 (<autogenerated>:1)	MOVQ	"".i+24(FP), DX
    	0x0041 00065 (<autogenerated>:1)	CMPQ	DX, AX
    	0x0044 00068 (<autogenerated>:1)	JCC	$0, 133
    	0x0046 00070 (<autogenerated>:1)	SHLQ	$4, DX
    	0x004a 00074 (<autogenerated>:1)	MOVQ	8(CX)(DX*1), BX
    	0x004f 00079 (<autogenerated>:1)	MOVQ	(CX)(DX*1), SI
    	0x0053 00083 (<autogenerated>:1)	MOVQ	"".j+32(FP), DI
    	0x0058 00088 (<autogenerated>:1)	CMPQ	DI, AX
    	0x005b 00091 (<autogenerated>:1)	JCC	$0, 133
    	0x005d 00093 (<autogenerated>:1)	SHLQ	$4, DI
    	0x0061 00097 (<autogenerated>:1)	MOVQ	8(CX)(DI*1), AX
    	0x0066 00102 (<autogenerated>:1)	MOVQ	(CX)(DI*1), R8
    	0x006a 00106 (<autogenerated>:1)	MOVQ	R8, (CX)(DX*1)
    	0x006e 00110 (<autogenerated>:1)	MOVQ	AX, 8(CX)(DX*1)
    	0x0073 00115 (<autogenerated>:1)	MOVQ	SI, (CX)(DI*1)
    	0x0077 00119 (<autogenerated>:1)	MOVQ	BX, 8(CX)(DI*1)
    	0x007c 00124 (<autogenerated>:1)	MOVQ	(SP), BP
    	0x0080 00128 (<autogenerated>:1)	ADDQ	$8, SP
    	0x0084 00132 (<autogenerated>:1)	RET
    	0x0085 00133 (<autogenerated>:1)	PCDATA	$0, $1
    	0x0085 00133 (<autogenerated>:1)	CALL	runtime.panicindex(SB)
    	0x008a 00138 (<autogenerated>:1)	UNDEF
    	0x008c 00140 (<autogenerated>:1)	PCDATA	$0, $1
    	0x008c 00140 (<autogenerated>:1)	CALL	runtime.panicwrap(SB)
    	0x0091 00145 (<autogenerated>:1)	UNDEF
    
    Change-Id: I15bb8435f0690badb868799f313ed8817335efd3
    Reviewed-on: https://go-review.googlesource.com/36809
    Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com>
    Reviewed-by: default avatarBrad Fitzpatrick <bradfitz@golang.org>
    2c91bb4c
runtime.go 5.79 KB