OSchip
/
llvm-project
mirror of https://github.com/THU-DSP-LAB/llvm-project.git
13
0
Fork 6
Code Issues Packages Projects Releases Wiki Activity
llvm-project/llvm/lib
History
Nate Begeman fac8529df8 Implement floating point select for lt, gt, le, ge using the powerpc fsel 
instruction.

Now, rather than emitting the following loop out of bisect:
.LBB_main_19:	; no_exit.0.i
	rlwinm r3, r2, 3, 0, 28
	lfdx f1, r3, r27
	addis r3, r30, ha16(.CPI_main_1-"L00000$pb")
	lfd f2, lo16(.CPI_main_1-"L00000$pb")(r3)
	fsub f2, f2, f1
	addis r3, r30, ha16(.CPI_main_1-"L00000$pb")
	lfd f4, lo16(.CPI_main_1-"L00000$pb")(r3)
	fcmpu cr0, f1, f4
	bge .LBB_main_64	; no_exit.0.i
.LBB_main_63:	; no_exit.0.i
	b .LBB_main_65	; no_exit.0.i
.LBB_main_64:	; no_exit.0.i
	fmr f2, f1
.LBB_main_65:	; no_exit.0.i
	addi r3, r2, 1
	rlwinm r3, r3, 3, 0, 28
	lfdx f1, r3, r27
	addis r3, r30, ha16(.CPI_main_1-"L00000$pb")
	lfd f4, lo16(.CPI_main_1-"L00000$pb")(r3)
	fsub f4, f4, f1
	addis r3, r30, ha16(.CPI_main_1-"L00000$pb")
	lfd f5, lo16(.CPI_main_1-"L00000$pb")(r3)
	fcmpu cr0, f1, f5
	bge .LBB_main_67	; no_exit.0.i
.LBB_main_66:	; no_exit.0.i
	b .LBB_main_68	; no_exit.0.i
.LBB_main_67:	; no_exit.0.i
	fmr f4, f1
.LBB_main_68:	; no_exit.0.i
	fadd f1, f2, f4
	addis r3, r30, ha16(.CPI_main_2-"L00000$pb")
	lfd f2, lo16(.CPI_main_2-"L00000$pb")(r3)
	fmul f1, f1, f2
	rlwinm r3, r2, 3, 0, 28
	lfdx f2, r3, r28
	fadd f4, f2, f1
	fcmpu cr0, f4, f0
	bgt .LBB_main_70	; no_exit.0.i
.LBB_main_69:	; no_exit.0.i
	b .LBB_main_71	; no_exit.0.i
.LBB_main_70:	; no_exit.0.i
	fmr f0, f4
.LBB_main_71:	; no_exit.0.i
	fsub f1, f2, f1
	addi r2, r2, -1
	fcmpu cr0, f1, f3
	blt .LBB_main_73	; no_exit.0.i
.LBB_main_72:	; no_exit.0.i
	b .LBB_main_74	; no_exit.0.i
.LBB_main_73:	; no_exit.0.i
	fmr f3, f1
.LBB_main_74:	; no_exit.0.i
	cmpwi cr0, r2, -1
	fmr f16, f0
	fmr f17, f3
	bgt .LBB_main_19	; no_exit.0.i

We emit this instead:
.LBB_main_19:	; no_exit.0.i
	rlwinm r3, r2, 3, 0, 28
	lfdx f1, r3, r27
	addis r3, r30, ha16(.CPI_main_1-"L00000$pb")
	lfd f2, lo16(.CPI_main_1-"L00000$pb")(r3)
	fsub f2, f2, f1
	fsel f1, f1, f1, f2
	addi r3, r2, 1
	rlwinm r3, r3, 3, 0, 28
	lfdx f2, r3, r27
	addis r3, r30, ha16(.CPI_main_1-"L00000$pb")
	lfd f4, lo16(.CPI_main_1-"L00000$pb")(r3)
	fsub f4, f4, f2
	fsel f2, f2, f2, f4
	fadd f1, f1, f2
	addis r3, r30, ha16(.CPI_main_2-"L00000$pb")
	lfd f2, lo16(.CPI_main_2-"L00000$pb")(r3)
	fmul f1, f1, f2
	rlwinm r3, r2, 3, 0, 28
	lfdx f2, r3, r28
	fadd f4, f2, f1
	fsub f5, f0, f4
	fsel f0, f5, f0, f4
	fsub f1, f2, f1
	addi r2, r2, -1
	fsub f2, f1, f3
	fsel f3, f2, f3, f1
	cmpwi cr0, r2, -1
	fmr f16, f0
	fmr f17, f3
	bgt .LBB_main_19	; no_exit.0.i

llvm-svn: 16764
 		2004-10-06 09:53:04 +00:00
..
Analysis 'Pass' should now not be derived from by clients. Instead, they should derive 2004-09-20 04:48:05 +00:00
AsmParser Okay, the list of link-time passes wasn't such a hot idea. Its prone to 2004-09-14 05:43:23 +00:00
Bytecode Fix doxygen comment 2004-09-28 16:57:46 +00:00
CodeGen Do not repeat the map lookup 2004-10-01 23:16:43 +00:00
Debugger Changes For Bug 352 2004-09-01 22:55:40 +00:00
ExecutionEngine Convert code to compile with vc7.1. 2004-09-15 17:06:42 +00:00
Support Excise the ill-advised RLCOMP compression algorithm and simply leave the 2004-10-04 17:45:44 +00:00
System Must include sys/stat.h before declaring a 'struct stat' 2004-10-05 18:46:59 +00:00
Target Implement floating point select for lt, gt, le, ge using the powerpc fsel 2004-10-06 09:53:04 +00:00
Transforms Reduce code growth implied by the tail duplication pass by not duplicating 2004-10-06 03:27:37 +00:00
VMCore Make sure the const bit gets inherited correctly when linking declarations 2004-10-05 02:28:11 +00:00
Makefile Wrap long line 2004-09-15 01:34:42 +00:00