X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=lib%2FTarget%2FARM%2FREADME.txt;h=2f6842e8cb6094f792fd25379883ae796d39aee8;hb=6248a546f23e7ffa84c171dc364b922e28467275;hp=6e5a7a151e063c7b8906c17a517accda6097d053;hpb=e3b88fc01e64200c3685c1b14eb23a3f4625edf2;p=oota-llvm.git diff --git a/lib/Target/ARM/README.txt b/lib/Target/ARM/README.txt index 6e5a7a151e0..2f6842e8cb6 100644 --- a/lib/Target/ARM/README.txt +++ b/lib/Target/ARM/README.txt @@ -8,11 +8,12 @@ Reimplement 'select' in terms of 'SEL'. add doesn't need to overflow between the two 16-bit chunks. * Implement pre/post increment support. (e.g. PR935) -* Coalesce stack slots! * Implement smarter constant generation for binops with large immediates. -* Consider materializing FP constants like 0.0f and 1.0f using integer - immediate instructions then copy to FPU. Slower than load into FPU? +A few ARMv6T2 ops should be pattern matched: BFI, SBFX, and UBFX + +Interesting optimization for PIC codegen on arm-linux: +http://gcc.gnu.org/bugzilla/show_bug.cgi?id=43129 //===---------------------------------------------------------------------===// @@ -75,26 +76,6 @@ were disabled due to badness with the ARM carry flag on subtracts. //===---------------------------------------------------------------------===// -We currently compile abs: -int foo(int p) { return p < 0 ? -p : p; } - -into: - -_foo: - rsb r1, r0, #0 - cmn r0, #1 - movgt r1, r0 - mov r0, r1 - bx lr - -This is very, uh, literal. This could be a 3 operation sequence: - t = (p sra 31); - res = (p xor t)-t - -Which would be better. This occurs in png decode. - -//===---------------------------------------------------------------------===// - More load / store optimizations: 1) Better representation for block transfer? This is from Olden/power: @@ -325,7 +306,7 @@ time. 4) Once we added support for multiple result patterns, write indexed loads patterns instead of C++ instruction selection code. -5) Use FLDM / FSTM to emulate indexed FP load / store. +5) Use VLDM / VSTM to emulate indexed FP load / store. //===---------------------------------------------------------------------===// @@ -422,14 +403,6 @@ are not remembered when the same two values are compared twice. //===---------------------------------------------------------------------===// -More register scavenging work: - -1. Use the register scavenger to track frame index materialized into registers - (those that do not fit in addressing modes) to allow reuse in the same BB. -2. Finish scavenging for Thumb. - -//===---------------------------------------------------------------------===// - More LSR enhancements possible: 1. Teach LSR about pre- and post- indexed ops to allow iv increment be merged @@ -540,10 +513,6 @@ while ARMConstantIslandPass only need to worry about LDR (literal). //===---------------------------------------------------------------------===// -We need to fix constant isel for ARMv6t2 to use MOVT. - -//===---------------------------------------------------------------------===// - Constant island pass should make use of full range SoImm values for LEApcrel. Be careful though as the last attempt caused infinite looping on lencod. @@ -593,11 +562,6 @@ it saves an instruction and a register. //===---------------------------------------------------------------------===// -add/sub/and/or + i32 imm can be simplified by folding part of the immediate -into the operation. - -//===---------------------------------------------------------------------===// - It might be profitable to cse MOVi16 if there are lots of 32-bit immediates with the same bottom half. @@ -612,3 +576,126 @@ http://lists.cs.uiuc.edu/pipermail/llvmdev/2009-June/022763.html //===---------------------------------------------------------------------===// Make use of the "rbit" instruction. + +//===---------------------------------------------------------------------===// + +Take a look at test/CodeGen/Thumb2/machine-licm.ll. ARM should be taught how +to licm and cse the unnecessary load from cp#1. + +//===---------------------------------------------------------------------===// + +The CMN instruction sets the flags like an ADD instruction, while CMP sets +them like a subtract. Therefore to be able to use CMN for comparisons other +than the Z bit, we'll need additional logic to reverse the conditionals +associated with the comparison. Perhaps a pseudo-instruction for the comparison, +with a post-codegen pass to clean up and handle the condition codes? +See PR5694 for testcase. + +//===---------------------------------------------------------------------===// + +Given the following on armv5: +int test1(int A, int B) { + return (A&-8388481)|(B&8388480); +} + +We currently generate: + ldr r2, .LCPI0_0 + and r0, r0, r2 + ldr r2, .LCPI0_1 + and r1, r1, r2 + orr r0, r1, r0 + bx lr + +We should be able to replace the second ldr+and with a bic (i.e. reuse the +constant which was already loaded). Not sure what's necessary to do that. + +//===---------------------------------------------------------------------===// + +The code generated for bswap on armv4/5 (CPUs without rev) is less than ideal: + +int a(int x) { return __builtin_bswap32(x); } + +a: + mov r1, #255, 24 + mov r2, #255, 16 + and r1, r1, r0, lsr #8 + and r2, r2, r0, lsl #8 + orr r1, r1, r0, lsr #24 + orr r0, r2, r0, lsl #24 + orr r0, r0, r1 + bx lr + +Something like the following would be better (fewer instructions/registers): + eor r1, r0, r0, ror #16 + bic r1, r1, #0xff0000 + mov r1, r1, lsr #8 + eor r0, r1, r0, ror #8 + bx lr + +A custom Thumb version would also be a slight improvement over the generic +version. + +//===---------------------------------------------------------------------===// + +Consider the following simple C code: + +void foo(unsigned char *a, unsigned char *b, int *c) { + if ((*a | *b) == 0) *c = 0; +} + +currently llvm-gcc generates something like this (nice branchless code I'd say): + + ldrb r0, [r0] + ldrb r1, [r1] + orr r0, r1, r0 + tst r0, #255 + moveq r0, #0 + streq r0, [r2] + bx lr + +Note that both "tst" and "moveq" are redundant. + +//===---------------------------------------------------------------------===// + +When loading immediate constants with movt/movw, if there are multiple +constants needed with the same low 16 bits, and those values are not live at +the same time, it would be possible to use a single movw instruction, followed +by multiple movt instructions to rewrite the high bits to different values. +For example: + + volatile store i32 -1, i32* inttoptr (i32 1342210076 to i32*), align 4, + !tbaa +!0 + volatile store i32 -1, i32* inttoptr (i32 1342341148 to i32*), align 4, + !tbaa +!0 + +is compiled and optimized to: + + movw r0, #32796 + mov.w r1, #-1 + movt r0, #20480 + str r1, [r0] + movw r0, #32796 @ <= this MOVW is not needed, value is there already + movt r0, #20482 + str r1, [r0] + +//===---------------------------------------------------------------------===// + +Improve codegen for select's: +if (x != 0) x = 1 +if (x == 1) x = 1 + +ARM codegen used to look like this: + mov r1, r0 + cmp r1, #1 + mov r0, #0 + moveq r0, #1 + +The naive lowering select between two different values. It should recognize the +test is equality test so it's more a conditional move rather than a select: + cmp r0, #1 + movne r0, #0 + +Currently this is a ARM specific dag combine. We probably should make it into a +target-neutral one.