From cf77dd37e7e7ae8eefe8c21a9ff3f04de989b808 Mon Sep 17 00:00:00 2001
From: =?utf8?q?R=C3=A9my=20Oudompheng?= <oudomphe@phare.normalesup.org>
Date: Thu, 3 Jan 2013 00:44:31 +0100
Subject: [PATCH] cmd/8g: extend elimination of temporaries to SSE2 code.

Before:
(erf.go:188)    TEXT     Erf+0(SB),$220
(erf.go:265)    TEXT     Erfc+0(SB),$204
(lgamma.go:174) TEXT     Lgamma+0(SB),$948

After:
(erf.go:188)    TEXT     Erf+0(SB),$84
(erf.go:265)    TEXT     Erfc+0(SB),$84
(lgamma.go:174) TEXT     Lgamma+0(SB),$44

SSE before vs. SSE after:

benchmark             old ns/op    new ns/op    delta
BenchmarkAcosh               81           49  -39.14%
BenchmarkAsinh              109          109   +0.00%
BenchmarkAtanh               73           74   +0.68%
BenchmarkLgamma             138           42  -69.20%
BenchmarkModf                24           15  -36.95%
BenchmarkSqrtGo             565          556   -1.59%

R=rsc
CC=golang-dev
https://golang.org/cl/7028048
---
 src/cmd/8g/reg.c | 43 ++++++++++++++++++++++++++-----------------
 1 file changed, 26 insertions(+), 17 deletions(-)

diff --git a/src/cmd/8g/reg.c b/src/cmd/8g/reg.c
index 2ae819548b..80230bc866 100644
--- a/src/cmd/8g/reg.c
+++ b/src/cmd/8g/reg.c
@@ -1845,26 +1845,33 @@ fixtemp(Prog *firstp)
 	for(p=firstp; p!=P; p=p->link) {
 		if(debug['R'] && debug['v'])
 			print("%P\n", p);
-		if(p->link == P
-			|| !RtoB(p->from.type)
-			|| p->to.type != D_AUTO
-			|| isfloat[p->to.etype])
+		if(p->link == P || p->to.type != D_AUTO)
 			continue;
-		switch(p->as) {
-		case AMOVB:
-			if(p->to.width == 1)
-				break;
-		case AMOVW:
-			if(p->to.width == 2)
+		if(isfloat[p->to.etype] && FtoB(p->from.type)) {
+			switch(p->as) {
+			case AMOVSS:
+			case AMOVSD:
 				break;
-		case AMOVL:
-			if(p->to.width == 4)
-				break;
-		default:
+			default:
+				continue;
+			}
+		} else if(!isfloat[p->to.etype] && RtoB(p->from.type)) {
+			switch(p->as) {
+			case AMOVB:
+				if(p->to.width == 1)
+					break;
+			case AMOVW:
+				if(p->to.width == 2)
+					break;
+			case AMOVL:
+				if(p->to.width == 4)
+					break;
+			default:
+				continue;
+			}
+		} else
 			continue;
-		}
 		// p is a MOV reg, mem.
-		// and it is not a float.
 		p2 = p->link;
 		h = hash32to16(fnv1(p->to.sym));
 		if(counts[h] != 2) {
@@ -1872,7 +1879,9 @@ fixtemp(Prog *firstp)
 		}
 		switch(p2->as) {
 		case ALEAL:
-		case AFMOVL: 
+		case AFMOVD:
+		case AFMOVF:
+		case AFMOVL:
 		case AFMOVW:
 		case AFMOVV:
 			// funny
-- 
2.48.1